improvise a max vit with register tokens

finish core idea of NaViT

.github/FUNDING.yml

@@ -0,0 +1,3 @@
+# These are supported funding model platforms
+
+github: [lucidrains]

.github/workflows/python-publish.yml

@@ -1,11 +1,16 @@
-# This workflows will upload a Python Package using Twine when a release is created
+# This workflow will upload a Python Package using Twine when a release is created
 # For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
 
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
 name: Upload Python Package
 
 on:
   release:
-    types: [created]
+    types: [published]
 
 jobs:
   deploy:
@@ -21,11 +26,11 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install setuptools wheel twine
-    - name: Build and publish
-      env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-      run: |
-        python setup.py sdist bdist_wheel
-        twine upload dist/*
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/python-test.yml

@@ -27,6 +27,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         python -m pip install pytest
+        python -m pip install wheel
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Test with pytest
       run: |

README.md

@@ -6,6 +6,8 @@
 - [Install](#install)
 - [Usage](#usage)
 - [Parameters](#parameters)
+- [Simple ViT](#simple-vit)
+- [NaViT](#navit)
 - [Distillation](#distillation)
 - [Deep ViT](#deep-vit)
 - [CaiT](#cait)
@@ -18,13 +20,24 @@
 - [Twins SVT](#twins-svt)
 - [CrossFormer](#crossformer)
 - [RegionViT](#regionvit)
+- [ScalableViT](#scalablevit)
+- [SepViT](#sepvit)
+- [MaxViT](#maxvit)
 - [NesT](#nest)
 - [MobileViT](#mobilevit)
 - [Masked Autoencoder](#masked-autoencoder)
 - [Simple Masked Image Modeling](#simple-masked-image-modeling)
 - [Masked Patch Prediction](#masked-patch-prediction)
+- [Masked Position Prediction](#masked-position-prediction)
 - [Adaptive Token Sampling](#adaptive-token-sampling)
+- [Patch Merger](#patch-merger)
+- [Vision Transformer for Small Datasets](#vision-transformer-for-small-datasets)
+- [3D Vit](#3d-vit)
+- [ViVit](#vivit)
+- [Parallel ViT](#parallel-vit)
+- [Learnable Memory ViT](#learnable-memory-vit)
 - [Dino](#dino)
+- [EsViT](#esvit)
 - [Accessing Attention](#accessing-attention)
 - [Research Ideas](#research-ideas)
   * [Efficient Attention](#efficient-attention)
@@ -41,6 +54,10 @@ For a Pytorch implementation with pretrained models, please see Ross Wightman's
 
 The official Jax repository is <a href="https://github.com/google-research/vision_transformer">here</a>.
 
+A tensorflow2 translation also exists <a href="https://github.com/taki0112/vit-tensorflow">here</a>, created by research scientist <a href="https://github.com/taki0112">Junho Kim</a>! 🙏
+
+<a href="https://github.com/conceptofmind/vit-flax">Flax translation</a> by <a href="https://github.com/conceptofmind">Enrico Shippole</a>!
+
 ## Install
 
 ```bash
@@ -96,6 +113,90 @@ Embedding dropout rate.
 - `pool`: string, either `cls` token pooling or `mean` pooling
 
 
+## Simple ViT
+
+<a href="https://arxiv.org/abs/2205.01580">An update</a> from some of the same authors of the original paper proposes simplifications to `ViT` that allows it to train faster and better.
+
+Among these simplifications include 2d sinusoidal positional embedding, global average pooling (no CLS token), no dropout, batch sizes of 1024 rather than 4096, and use of RandAugment and MixUp augmentations. They also show that a simple linear at the end is not significantly worse than the original MLP head
+
+You can use it by importing the `SimpleViT` as shown below
+
+```python
+import torch
+from vit_pytorch import SimpleViT
+
+v = SimpleViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+```
+
+## NaViT
+
+<img src="./images/navit.png" width="450px"></img>
+
+<a href="https://arxiv.org/abs/2307.06304">This paper</a> proposes to leverage the flexibility of attention and masking for variable lengthed sequences to train images of multiple resolution, packed into a single batch. They demonstrate much faster training and improved accuracies, with the only cost being extra complexity in the architecture and dataloading. They use factorized 2d positional encodings, token dropping, as well as query-key normalization.
+
+You can use it as follows
+
+```python
+import torch
+from vit_pytorch.na_vit import NaViT
+
+v = NaViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1,
+    token_dropout_prob = 0.1  # token dropout of 10% (keep 90% of tokens)
+)
+
+# 5 images of different resolutions - List[List[Tensor]]
+
+# for now, you'll have to correctly place images in same batch element as to not exceed maximum allowed sequence length for self-attention w/ masking
+
+images = [
+    [torch.randn(3, 256, 256), torch.randn(3, 128, 128)],
+    [torch.randn(3, 128, 256), torch.randn(3, 256, 128)],
+    [torch.randn(3, 64, 256)]
+]
+
+preds = v(images) # (5, 1000) - 5, because 5 images of different resolution above
+
+```
+
+Or if you would rather that the framework auto group the images into variable lengthed sequences that do not exceed a certain max length
+
+```python
+images = [
+    torch.randn(3, 256, 256),
+    torch.randn(3, 128, 128),
+    torch.randn(3, 128, 256),
+    torch.randn(3, 256, 128),
+    torch.randn(3, 64, 256)
+]
+
+preds = v(
+    images,
+    group_images = True,
+    group_max_seq_len = 64
+) # (5, 1000)
+```
+
 ## Distillation
 
 <img src="./images/distill.png" width="300px"></img>
@@ -237,6 +338,7 @@ preds = v(img) # (1, 1000)
 ```
 
 ## CCT
+
 <img src="https://raw.githubusercontent.com/SHI-Labs/Compact-Transformers/main/images/model_sym.png" width="400px"></img>
 
 <a href="https://arxiv.org/abs/2104.05704">CCT</a> proposes compact transformers
@@ -248,22 +350,25 @@ You can use this with two methods
 import torch
 from vit_pytorch.cct import CCT
 
-model = CCT(
-        img_size=224,
-        embedding_dim=384,
-        n_conv_layers=2,
-        kernel_size=7,
-        stride=2,
-        padding=3,
-        pooling_kernel_size=3,
-        pooling_stride=2,
-        pooling_padding=1,
-        num_layers=14,
-        num_heads=6,
-        mlp_radio=3.,
-        num_classes=1000,
-        positional_embedding='learnable', # ['sine', 'learnable', 'none']
-        )
+cct = CCT(
+    img_size = (224, 448),
+    embedding_dim = 384,
+    n_conv_layers = 2,
+    kernel_size = 7,
+    stride = 2,
+    padding = 3,
+    pooling_kernel_size = 3,
+    pooling_stride = 2,
+    pooling_padding = 1,
+    num_layers = 14,
+    num_heads = 6,
+    mlp_ratio = 3.,
+    num_classes = 1000,
+    positional_embedding = 'learnable', # ['sine', 'learnable', 'none']
+)
+
+img = torch.randn(1, 3, 224, 448)
+pred = cct(img) # (1, 1000)
 ```
 
 Alternatively you can use one of several pre-defined models `[2,4,6,7,8,14,16]`
@@ -274,23 +379,23 @@ and the embedding dimension.
 import torch
 from vit_pytorch.cct import cct_14
 
-model = cct_14(
-        img_size=224,
-        n_conv_layers=1,
-        kernel_size=7,
-        stride=2,
-        padding=3,
-        pooling_kernel_size=3,
-        pooling_stride=2,
-        pooling_padding=1,
-        num_classes=1000,
-        positional_embedding='learnable', # ['sine', 'learnable', 'none']  
-        )
+cct = cct_14(
+    img_size = 224,
+    n_conv_layers = 1,
+    kernel_size = 7,
+    stride = 2,
+    padding = 3,
+    pooling_kernel_size = 3,
+    pooling_stride = 2,
+    pooling_padding = 1,
+    num_classes = 1000,
+    positional_embedding = 'learnable', # ['sine', 'learnable', 'none']
+)
 ```
+
 <a href="https://github.com/SHI-Labs/Compact-Transformers">Official
 Repository</a> includes links to pretrained model checkpoints.
 
-
 ## Cross ViT
 
 <img src="./images/cross_vit.png" width="400px"></img>
@@ -523,11 +628,103 @@ img = torch.randn(1, 3, 224, 224)
 pred = model(img) # (1, 1000)
 ```
 
+## ScalableViT
+
+<img src="./images/scalable-vit-1.png" width="400px"></img>
+
+<img src="./images/scalable-vit-2.png" width="400px"></img>
+
+This Bytedance AI <a href="https://arxiv.org/abs/2203.10790">paper</a> proposes the Scalable Self Attention (SSA) and the Interactive Windowed Self Attention (IWSA) modules. The SSA alleviates the computation needed at earlier stages by reducing the key / value feature map by some factor (`reduction_factor`), while modulating the dimension of the queries and keys (`ssa_dim_key`). The IWSA performs self attention within local windows, similar to other vision transformer papers. However, they add a residual of the values, passed through a convolution of kernel size 3, which they named Local Interactive Module (LIM).
+
+They make the claim in this paper that this scheme outperforms Swin Transformer, and also demonstrate competitive performance against Crossformer.
+
+You can use it as follows (ex. ScalableViT-S)
+
+```python
+import torch
+from vit_pytorch.scalable_vit import ScalableViT
+
+model = ScalableViT(
+    num_classes = 1000,
+    dim = 64,                               # starting model dimension. at every stage, dimension is doubled
+    heads = (2, 4, 8, 16),                  # number of attention heads at each stage
+    depth = (2, 2, 20, 2),                  # number of transformer blocks at each stage
+    ssa_dim_key = (40, 40, 40, 32),         # the dimension of the attention keys (and queries) for SSA. in the paper, they represented this as a scale factor on the base dimension per key (ssa_dim_key / dim_key)
+    reduction_factor = (8, 4, 2, 1),        # downsampling of the key / values in SSA. in the paper, this was represented as (reduction_factor ** -2)
+    window_size = (64, 32, None, None),     # window size of the IWSA at each stage. None means no windowing needed
+    dropout = 0.1,                          # attention and feedforward dropout
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+preds = model(img) # (1, 1000)
+```
+
+## SepViT
+
+<img src="./images/sep-vit.png" width="400px"></img>
+
+Another <a href="https://arxiv.org/abs/2203.15380">Bytedance AI paper</a>, it proposes a depthwise-pointwise self-attention layer that seems largely inspired by mobilenet's depthwise-separable convolution. The most interesting aspect is the reuse of the feature map from the depthwise self-attention stage as the values for the pointwise self-attention, as shown in the diagram above.
+
+I have decided to include only the version of `SepViT` with this specific self-attention layer, as the grouped attention layers are not remarkable nor novel, and the authors were not clear on how they treated the window tokens for the group self-attention layer. Besides, it seems like with `DSSA` layer alone, they were able to beat Swin.
+
+ex. SepViT-Lite
+
+```python
+import torch
+from vit_pytorch.sep_vit import SepViT
+
+v = SepViT(
+    num_classes = 1000,
+    dim = 32,               # dimensions of first stage, which doubles every stage (32, 64, 128, 256) for SepViT-Lite
+    dim_head = 32,          # attention head dimension
+    heads = (1, 2, 4, 8),   # number of heads per stage
+    depth = (1, 2, 6, 2),   # number of transformer blocks per stage
+    window_size = 7,        # window size of DSS Attention block
+    dropout = 0.1           # dropout
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+preds = v(img) # (1, 1000)
+```
+
+## MaxViT
+
+<img src="./images/max-vit.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2204.01697">This paper</a> proposes a hybrid convolutional / attention network, using MBConv from the convolution side, and then block / grid axial sparse attention.
+
+They also claim this specific vision transformer is good for generative models (GANs).
+
+ex. MaxViT-S
+
+```python
+import torch
+from vit_pytorch.max_vit import MaxViT
+
+v = MaxViT(
+    num_classes = 1000,
+    dim_conv_stem = 64,               # dimension of the convolutional stem, would default to dimension of first layer if not specified
+    dim = 96,                         # dimension of first layer, doubles every layer
+    dim_head = 32,                    # dimension of attention heads, kept at 32 in paper
+    depth = (2, 2, 5, 2),             # number of MaxViT blocks per stage, which consists of MBConv, block-like attention, grid-like attention
+    window_size = 7,                  # window size for block and grids
+    mbconv_expansion_rate = 4,        # expansion rate of MBConv
+    mbconv_shrinkage_rate = 0.25,     # shrinkage rate of squeeze-excitation in MBConv
+    dropout = 0.1                     # dropout
+)
+
+img = torch.randn(2, 3, 224, 224)
+
+preds = v(img) # (2, 1000)
+```
+
 ## NesT
 
 <img src="./images/nest.png" width="400px"></img>
 
-This <a href="https://arxiv.org/abs/2105.12723">paper</a> decided to process the image in hierarchical stages, with attention only within tokens of local blocks, which aggregate as it moves up the heirarchy. The aggregation is done in the image plane, and contains a convolution and subsequent maxpool to allow it to pass information across the boundary.
+This <a href="https://arxiv.org/abs/2105.12723">paper</a> decided to process the image in hierarchical stages, with attention only within tokens of local blocks, which aggregate as it moves up the hierarchy. The aggregation is done in the image plane, and contains a convolution and subsequent maxpool to allow it to pass information across the boundary.
 
 You can use it with the following code (ex. NesT-T)
 
@@ -541,7 +738,7 @@ nest = NesT(
     dim = 96,
     heads = 3,
     num_hierarchies = 3,        # number of hierarchies
-    block_repeats = (8, 4, 1),  # the number of transformer blocks at each heirarchy, starting from the bottom
+    block_repeats = (2, 2, 8),  # the number of transformer blocks at each hierarchy, starting from the bottom
     num_classes = 1000
 )
 
@@ -706,6 +903,44 @@ for _ in range(100):
 torch.save(model.state_dict(), './pretrained-net.pt')
 ```
 
+## Masked Position Prediction
+
+<img src="./images/mp3.png" width="400px"></img>
+
+New <a href="https://arxiv.org/abs/2207.07611">paper</a> that introduces masked position prediction pre-training criteria. This strategy is more efficient than the Masked Autoencoder strategy and has comparable performance.  
+
+```python
+import torch
+from vit_pytorch.mp3 import ViT, MP3
+
+v = ViT(
+    num_classes = 1000,
+    image_size = 256,
+    patch_size = 8,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048,
+    dropout = 0.1,
+)
+
+mp3 = MP3(
+    vit = v,
+    masking_ratio = 0.75
+)
+
+images = torch.randn(8, 3, 256, 256)
+
+loss = mp3(images)
+loss.backward()
+
+# that's all!
+# do the above in a for loop many times with a lot of images and your vision transformer will learn
+
+# save your improved vision transformer
+torch.save(v.state_dict(), './trained-vit.pt')
+```
+
 ## Adaptive Token Sampling
 
 <img src="./images/ats.png" width="400px"></img>
@@ -731,12 +966,301 @@ v = ViT(
 
 img = torch.randn(4, 3, 256, 256)
 
-preds = v(img) # (1, 1000)
+preds = v(img) # (4, 1000)
 
 # you can also get a list of the final sampled patch ids
 # a value of -1 denotes padding
 
-preds, token_ids = v(img, return_sampled_token_ids = True) # (1, 1000), (1, <=8)
+preds, token_ids = v(img, return_sampled_token_ids = True) # (4, 1000), (4, <=8)
+```
+
+## Patch Merger
+
+
+<img src="./images/patch_merger.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2202.12015">paper</a> proposes a simple module (Patch Merger) for reducing the number of tokens at any layer of a vision transformer without sacrificing performance.
+
+```python
+import torch
+from vit_pytorch.vit_with_patch_merger import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 16,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 12,
+    heads = 8,
+    patch_merge_layer = 6,        # at which transformer layer to do patch merging
+    patch_merge_num_tokens = 8,   # the output number of tokens from the patch merge
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(4, 3, 256, 256)
+
+preds = v(img) # (4, 1000)
+```
+
+One can also use the `PatchMerger` module by itself
+
+```python
+import torch
+from vit_pytorch.vit_with_patch_merger import PatchMerger
+
+merger = PatchMerger(
+    dim = 1024,
+    num_tokens_out = 8   # output number of tokens
+)
+
+features = torch.randn(4, 256, 1024) # (batch, num tokens, dimension)
+
+out = merger(features) # (4, 8, 1024)
+```
+
+## Vision Transformer for Small Datasets
+
+<img src="./images/vit_for_small_datasets.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2112.13492">paper</a> proposes a new image to patch function that incorporates shifts of the image, before normalizing and dividing the image into patches. I have found shifting to be extremely helpful in some other transformers work, so decided to include this for further explorations. It also includes the `LSA` with the learned temperature and masking out of a token's attention to itself.
+
+You can use as follows:
+
+```python
+import torch
+from vit_pytorch.vit_for_small_dataset import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 16,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(4, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+```
+
+You can also use the `SPT` from this paper as a standalone module
+
+```python
+import torch
+from vit_pytorch.vit_for_small_dataset import SPT
+
+spt = SPT(
+    dim = 1024,
+    patch_size = 16,
+    channels = 3
+)
+
+img = torch.randn(4, 3, 256, 256)
+
+tokens = spt(img) # (4, 256, 1024)
+```
+
+## 3D ViT
+
+By popular request, I will start extending a few of the architectures in this repository to 3D ViTs, for use with video, medical imaging, etc.
+
+You will need to pass in two additional hyperparameters: (1) the number of frames `frames` and (2) patch size along the frame dimension `frame_patch_size`
+
+For starters, 3D ViT
+
+```python
+import torch
+from vit_pytorch.vit_3d import ViT
+
+v = ViT(
+    image_size = 128,          # image size
+    frames = 16,               # number of frames
+    image_patch_size = 16,     # image patch size
+    frame_patch_size = 2,      # frame patch size
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+video = torch.randn(4, 3, 16, 128, 128) # (batch, channels, frames, height, width)
+
+preds = v(video) # (4, 1000)
+```
+
+3D Simple ViT
+
+```python
+import torch
+from vit_pytorch.simple_vit_3d import SimpleViT
+
+v = SimpleViT(
+    image_size = 128,          # image size
+    frames = 16,               # number of frames
+    image_patch_size = 16,     # image patch size
+    frame_patch_size = 2,      # frame patch size
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048
+)
+
+video = torch.randn(4, 3, 16, 128, 128) # (batch, channels, frames, height, width)
+
+preds = v(video) # (4, 1000)
+```
+
+3D version of <a href="https://github.com/lucidrains/vit-pytorch#cct">CCT</a>
+
+```python
+import torch
+from vit_pytorch.cct_3d import CCT
+
+cct = CCT(
+    img_size = 224,
+    num_frames = 8,
+    embedding_dim = 384,
+    n_conv_layers = 2,
+    frame_kernel_size = 3,
+    kernel_size = 7,
+    stride = 2,
+    padding = 3,
+    pooling_kernel_size = 3,
+    pooling_stride = 2,
+    pooling_padding = 1,
+    num_layers = 14,
+    num_heads = 6,
+    mlp_ratio = 3.,
+    num_classes = 1000,
+    positional_embedding = 'learnable'
+)
+
+video = torch.randn(1, 3, 8, 224, 224) # (batch, channels, frames, height, width)
+pred = cct(video)
+```
+
+## ViViT
+
+<img src="./images/vivit.png" width="350px"></img>
+
+This <a href="https://arxiv.org/abs/2103.15691">paper</a> offers 3 different types of architectures for efficient attention of videos, with the main theme being factorizing the attention across space and time. This repository will offer the first variant, which is a spatial transformer followed by a temporal one.
+
+```python
+import torch
+from vit_pytorch.vivit import ViT
+
+v = ViT(
+    image_size = 128,          # image size
+    frames = 16,               # number of frames
+    image_patch_size = 16,     # image patch size
+    frame_patch_size = 2,      # frame patch size
+    num_classes = 1000,
+    dim = 1024,
+    spatial_depth = 6,         # depth of the spatial transformer
+    temporal_depth = 6,        # depth of the temporal transformer
+    heads = 8,
+    mlp_dim = 2048
+)
+
+video = torch.randn(4, 3, 16, 128, 128) # (batch, channels, frames, height, width)
+
+preds = v(video) # (4, 1000)
+```
+
+## Parallel ViT
+
+<img src="./images/parallel-vit.png" width="350px"></img>
+
+This <a href="https://arxiv.org/abs/2203.09795">paper</a> propose parallelizing multiple attention and feedforward blocks per layer (2 blocks), claiming that it is easier to train without loss of performance.
+
+You can try this variant as follows
+
+```python
+import torch
+from vit_pytorch.parallel_vit import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 16,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048,
+    num_parallel_branches = 2,  # in paper, they claimed 2 was optimal
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(4, 3, 256, 256)
+
+preds = v(img) # (4, 1000)
+```
+
+## Learnable Memory ViT
+
+<img src="./images/learnable-memory-vit.png" width="350px"></img>
+
+This <a href="https://arxiv.org/abs/2203.15243">paper</a> shows that adding learnable memory tokens at each layer of a vision transformer can greatly enhance fine-tuning results (in addition to learnable task specific CLS token and adapter head).
+
+You can use this with a specially modified `ViT` as follows
+
+```python
+import torch
+from vit_pytorch.learnable_memory_vit import ViT, Adapter
+
+# normal base ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 16,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(4, 3, 256, 256)
+logits = v(img) # (4, 1000)
+
+# do your usual training with ViT
+# ...
+
+
+# then, to finetune, just pass the ViT into the Adapter class
+# you can do this for multiple Adapters, as shown below
+
+adapter1 = Adapter(
+    vit = v,
+    num_classes = 2,               # number of output classes for this specific task
+    num_memories_per_layer = 5     # number of learnable memories per layer, 10 was sufficient in paper
+)
+
+logits1 = adapter1(img) # (4, 2) - predict 2 classes off frozen ViT backbone with learnable memories and task specific head
+
+# yet another task to finetune on, this time with 4 classes
+
+adapter2 = Adapter(
+    vit = v,
+    num_classes = 4,
+    num_memories_per_layer = 10
+)
+
+logits2 = adapter2(img) # (4, 4) - predict 4 classes off frozen ViT backbone with learnable memories and task specific head
+
 ```
 
 ## Dino
@@ -793,6 +1317,80 @@ for _ in range(100):
 torch.save(model.state_dict(), './pretrained-net.pt')
 ```
 
+## EsViT
+
+<img src="./images/esvit.png" width="350px"></img>
+
+<a href="https://arxiv.org/abs/2106.09785">`EsViT`</a> is a variant of Dino (from above) re-engineered to support efficient `ViT`s with patch merging / downsampling by taking into an account an extra regional loss between the augmented views. To quote the abstract, it `outperforms its supervised counterpart on 17 out of 18 datasets` at 3 times higher throughput.
+
+Even though it is named as though it were a new `ViT` variant, it actually is just a strategy for training any multistage `ViT` (in the paper, they focused on Swin). The example below will show how to use it with `CvT`. You'll need to set the `hidden_layer` to the name of the layer within your efficient ViT that outputs the non-average pooled visual representations, just before the global pooling and projection to logits.
+
+```python
+import torch
+from vit_pytorch.cvt import CvT
+from vit_pytorch.es_vit import EsViTTrainer
+
+cvt = CvT(
+    num_classes = 1000,
+    s1_emb_dim = 64,
+    s1_emb_kernel = 7,
+    s1_emb_stride = 4,
+    s1_proj_kernel = 3,
+    s1_kv_proj_stride = 2,
+    s1_heads = 1,
+    s1_depth = 1,
+    s1_mlp_mult = 4,
+    s2_emb_dim = 192,
+    s2_emb_kernel = 3,
+    s2_emb_stride = 2,
+    s2_proj_kernel = 3,
+    s2_kv_proj_stride = 2,
+    s2_heads = 3,
+    s2_depth = 2,
+    s2_mlp_mult = 4,
+    s3_emb_dim = 384,
+    s3_emb_kernel = 3,
+    s3_emb_stride = 2,
+    s3_proj_kernel = 3,
+    s3_kv_proj_stride = 2,
+    s3_heads = 4,
+    s3_depth = 10,
+    s3_mlp_mult = 4,
+    dropout = 0.
+)
+
+learner = EsViTTrainer(
+    cvt,
+    image_size = 256,
+    hidden_layer = 'layers',           # hidden layer name or index, from which to extract the embedding
+    projection_hidden_size = 256,      # projector network hidden dimension
+    projection_layers = 4,             # number of layers in projection network
+    num_classes_K = 65336,             # output logits dimensions (referenced as K in paper)
+    student_temp = 0.9,                # student temperature
+    teacher_temp = 0.04,               # teacher temperature, needs to be annealed from 0.04 to 0.07 over 30 epochs
+    local_upper_crop_scale = 0.4,      # upper bound for local crop - 0.4 was recommended in the paper
+    global_lower_crop_scale = 0.5,     # lower bound for global crop - 0.5 was recommended in the paper
+    moving_average_decay = 0.9,        # moving average of encoder - paper showed anywhere from 0.9 to 0.999 was ok
+    center_moving_average_decay = 0.9, # moving average of teacher centers - paper showed anywhere from 0.9 to 0.999 was ok
+)
+
+opt = torch.optim.AdamW(learner.parameters(), lr = 3e-4)
+
+def sample_unlabelled_images():
+    return torch.randn(8, 3, 256, 256)
+
+for _ in range(1000):
+    images = sample_unlabelled_images()
+    loss = learner(images)
+    opt.zero_grad()
+    loss.backward()
+    opt.step()
+    learner.update_moving_average() # update moving average of teacher encoder and teacher centers
+
+# save your improved network
+torch.save(cvt.state_dict(), './pretrained-net.pt')
+```
+
 ## Accessing Attention
 
 If you would like to visualize the attention weights (post-softmax) for your research, just follow the procedure below
@@ -869,6 +1467,47 @@ logits, embeddings = v(img)
 embeddings # (1, 65, 1024) - (batch x patches x model dim)
 ```
 
+Or say for `CrossViT`, which has a multi-scale encoder that outputs two sets of embeddings for 'large' and 'small' scales
+
+```python
+import torch
+from vit_pytorch.cross_vit import CrossViT
+
+v = CrossViT(
+    image_size = 256,
+    num_classes = 1000,
+    depth = 4,
+    sm_dim = 192,
+    sm_patch_size = 16,
+    sm_enc_depth = 2,
+    sm_enc_heads = 8,
+    sm_enc_mlp_dim = 2048,
+    lg_dim = 384,
+    lg_patch_size = 64,
+    lg_enc_depth = 3,
+    lg_enc_heads = 8,
+    lg_enc_mlp_dim = 2048,
+    cross_attn_depth = 2,
+    cross_attn_heads = 8,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+# wrap the CrossViT
+
+from vit_pytorch.extractor import Extractor
+v = Extractor(v, layer_name = 'multi_scale_encoder') # take embedding coming from the output of multi-scale-encoder
+
+# forward pass now returns predictions and the attention maps
+
+img = torch.randn(1, 3, 256, 256)
+logits, embeddings = v(img)
+
+# there is one extra token due to the CLS token
+
+embeddings # ((1, 257, 192), (1, 17, 384)) - (batch x patches x dimension) <- large and small scales respectively
+```
+
 ## Research Ideas
 
 ### Efficient Attention
@@ -1236,6 +1875,131 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{lee2021vision,
+    title   = {Vision Transformer for Small-Size Datasets}, 
+    author  = {Seung Hoon Lee and Seunghyun Lee and Byung Cheol Song},
+    year    = {2021},
+    eprint  = {2112.13492},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{renggli2022learning,
+    title   = {Learning to Merge Tokens in Vision Transformers},
+    author  = {Cedric Renggli and André Susano Pinto and Neil Houlsby and Basil Mustafa and Joan Puigcerver and Carlos Riquelme},
+    year    = {2022},
+    eprint  = {2202.12015},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{yang2022scalablevit,
+    title   = {ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer}, 
+    author  = {Rui Yang and Hailong Ma and Jie Wu and Yansong Tang and Xuefeng Xiao and Min Zheng and Xiu Li},
+    year    = {2022},
+    eprint  = {2203.10790},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@inproceedings{Touvron2022ThreeTE,
+    title   = {Three things everyone should know about Vision Transformers},
+    author  = {Hugo Touvron and Matthieu Cord and Alaaeldin El-Nouby and Jakob Verbeek and Herv'e J'egou},
+    year    = {2022}
+}
+```
+
+```bibtex
+@inproceedings{Sandler2022FinetuningIT,
+    title   = {Fine-tuning Image Transformers using Learnable Memory},
+    author  = {Mark Sandler and Andrey Zhmoginov and Max Vladymyrov and Andrew Jackson},
+    year    = {2022}
+}
+```
+
+```bibtex
+@inproceedings{Li2022SepViTSV,
+    title   = {SepViT: Separable Vision Transformer},
+    author  = {Wei Li and Xing Wang and Xin Xia and Jie Wu and Xuefeng Xiao and Minghang Zheng and Shiping Wen},
+    year    = {2022}
+}
+```
+
+```bibtex
+@inproceedings{Tu2022MaxViTMV,
+    title   = {MaxViT: Multi-Axis Vision Transformer},
+    author  = {Zhengzhong Tu and Hossein Talebi and Han Zhang and Feng Yang and Peyman Milanfar and Alan Conrad Bovik and Yinxiao Li},
+    year    = {2022}
+}
+```
+
+```bibtex
+@article{Li2021EfficientSV,
+    title   = {Efficient Self-supervised Vision Transformers for Representation Learning},
+    author  = {Chunyuan Li and Jianwei Yang and Pengchuan Zhang and Mei Gao and Bin Xiao and Xiyang Dai and Lu Yuan and Jianfeng Gao},
+    journal = {ArXiv},
+    year    = {2021},
+    volume  = {abs/2106.09785}
+}
+```
+
+```bibtex
+@misc{Beyer2022BetterPlainViT
+    title     = {Better plain ViT baselines for ImageNet-1k},
+    author    = {Beyer, Lucas and Zhai, Xiaohua and Kolesnikov, Alexander},
+    publisher = {arXiv},
+    year      = {2022}
+}
+
+```
+
+```bibtex
+@article{Arnab2021ViViTAV,
+    title   = {ViViT: A Video Vision Transformer},
+    author  = {Anurag Arnab and Mostafa Dehghani and Georg Heigold and Chen Sun and Mario Lucic and Cordelia Schmid},
+    journal = {2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
+    year    = {2021},
+    pages   = {6816-6826}
+}
+```
+
+```bibtex
+@article{Liu2022PatchDropoutEV,
+    title   = {PatchDropout: Economizing Vision Transformers Using Patch Dropout},
+    author  = {Yue Liu and Christos Matsoukas and Fredrik Strand and Hossein Azizpour and Kevin Smith},
+    journal = {ArXiv},
+    year    = {2022},
+    volume  = {abs/2208.07220}
+}
+```
+
+```bibtex
+@misc{https://doi.org/10.48550/arxiv.2302.01327,
+    doi     = {10.48550/ARXIV.2302.01327},
+    url     = {https://arxiv.org/abs/2302.01327},
+    author  = {Kumar, Manoj and Dehghani, Mostafa and Houlsby, Neil},
+    title   = {Dual PatchNorm},
+    publisher = {arXiv},
+    year    = {2023},
+    copyright = {Creative Commons Attribution 4.0 International}
+}
+```
+
+```bibtex
+@inproceedings{Dehghani2023PatchNP,
+    title   = {Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution},
+    author  = {Mostafa Dehghani and Basil Mustafa and Josip Djolonga and Jonathan Heek and Matthias Minderer and Mathilde Caron and Andreas Steiner and Joan Puigcerver and Robert Geirhos and Ibrahim M. Alabdulmohsin and Avital Oliver and Piotr Padlewski and Alexey A. Gritsenko and Mario Luvci'c and Neil Houlsby},
+    year    = {2023}
+}
+```
+
 ```bibtex
 @misc{vaswani2017attention,
     title   = {Attention Is All You Need},
@@ -1247,4 +2011,22 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@inproceedings{dao2022flashattention,
+    title   = {Flash{A}ttention: Fast and Memory-Efficient Exact Attention with {IO}-Awareness},
+    author  = {Dao, Tri and Fu, Daniel Y. and Ermon, Stefano and Rudra, Atri and R{\'e}, Christopher},
+    booktitle = {Advances in Neural Information Processing Systems},
+    year    = {2022}
+}
+```
+
+```bibtex
+@inproceedings{Darcet2023VisionTN,
+    title   = {Vision Transformers Need Registers},
+    author  = {Timoth'ee Darcet and Maxime Oquab and Julien Mairal and Piotr Bojanowski},
+    year    = {2023},
+    url     = {https://api.semanticscholar.org/CorpusID:263134283}
+}
+```
+
 *I visualise a time when we will be to robots what dogs are to humans, and I’m rooting for the machines.* — Claude Shannon

examples/cats_and_dogs.ipynb

@@ -16,7 +16,7 @@
     "\n",
     "* Dogs vs. Cats Redux: Kernels Edition - https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition\n",
     "* Base Code - https://www.kaggle.com/reukki/pytorch-cnn-tutorial-with-cats-and-dogs/\n",
-    "* Effecient Attention Implementation - https://github.com/lucidrains/vit-pytorch#efficient-attention"
+    "* Efficient Attention Implementation - https://github.com/lucidrains/vit-pytorch#efficient-attention"
    ]
   },
   {
@@ -342,7 +342,7 @@
     "id": "ZhYDJXk2SRDu"
    },
    "source": [
-    "## Image Augumentation"
+    "## Image Augmentation"
    ]
   },
   {
@@ -497,7 +497,7 @@
     "id": "TF9yMaRrSvmv"
    },
    "source": [
-    "## Effecient Attention"
+    "## Efficient Attention"
    ]
   },
   {
@@ -1307,7 +1307,7 @@
   "celltoolbar": "Edit Metadata",
   "colab": {
    "collapsed_sections": [],
-   "name": "Effecient Attention | Cats & Dogs",
+   "name": "Efficient Attention | Cats & Dogs",
    "provenance": [],
    "toc_visible": true
   },

setup.py

@@ -3,9 +3,10 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.25.6',
+  version = '1.5.2',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
+  long_description_content_type = 'text/markdown',
   author = 'Phil Wang',
   author_email = 'lucidrains@gmail.com',
   url = 'https://github.com/lucidrains/vit-pytorch',
@@ -15,15 +16,17 @@ setup(
     'image recognition'
   ],
   install_requires=[
-    'einops>=0.3',
-    'torch>=1.6',
+    'einops>=0.7.0',
+    'torch>=1.10',
     'torchvision'
   ],
   setup_requires=[
     'pytest-runner',
   ],
   tests_require=[
-    'pytest'
+    'pytest',
+    'torch==1.12.1',
+    'torchvision==0.13.1'
   ],
   classifiers=[
     'Development Status :: 4 - Beta',

vit_pytorch/__init__.py

@@ -1,3 +1,12 @@
+import torch
+from packaging import version
+
+if version.parse(torch.__version__) >= version.parse('2.0.0'):
+    from einops._torch_specific import allow_ops_in_compiled_graph
+    allow_ops_in_compiled_graph()
+
 from vit_pytorch.vit import ViT
+from vit_pytorch.simple_vit import SimpleViT
+
 from vit_pytorch.mae import MAE
 from vit_pytorch.dino import Dino

vit_pytorch/ats_vit.py

@@ -110,18 +110,11 @@ class AdaptiveTokenSampling(nn.Module):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -138,7 +131,10 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.output_num_tokens = output_num_tokens
@@ -152,6 +148,7 @@ class Attention(nn.Module):
     def forward(self, x, *, mask):
         num_tokens = x.shape[1]
 
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -163,6 +160,7 @@ class Attention(nn.Module):
             dots = dots.masked_fill(~dots_mask, mask_value)
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         sampled_token_ids = None
 
@@ -186,8 +184,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _, output_num_tokens in zip(range(depth), max_tokens_per_depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, output_num_tokens = output_num_tokens, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, output_num_tokens = output_num_tokens, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
 
     def forward(self, x):
@@ -227,7 +225,9 @@ class ViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/cait.py

@@ -44,18 +44,11 @@ class LayerScale(nn.Module):
     def forward(self, x, **kwargs):
         return self.fn(x, **kwargs) * self.scale
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -72,10 +65,12 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.to_q = nn.Linear(dim, inner_dim, bias = False)
         self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
 
         self.mix_heads_pre_attn = nn.Parameter(torch.randn(heads, heads))
         self.mix_heads_post_attn = nn.Parameter(torch.randn(heads, heads))
@@ -88,6 +83,7 @@ class Attention(nn.Module):
     def forward(self, x, context = None):
         b, n, _, h = *x.shape, self.heads
 
+        x = self.norm(x)
         context = x if not exists(context) else torch.cat((x, context), dim = 1)
 
         qkv = (self.to_q(x), *self.to_kv(context).chunk(2, dim = -1))
@@ -96,7 +92,10 @@ class Attention(nn.Module):
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         dots = einsum('b h i j, h g -> b g i j', dots, self.mix_heads_pre_attn)    # talking heads, pre-softmax
+
         attn = self.attend(dots)
+        attn = self.dropout(attn)
+
         attn = einsum('b h i j, h g -> b g i j', attn, self.mix_heads_post_attn)   # talking heads, post-softmax
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
@@ -111,8 +110,8 @@ class Transformer(nn.Module):
 
         for ind in range(depth):
             self.layers.append(nn.ModuleList([
-                LayerScale(dim, PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)), depth = ind + 1),
-                LayerScale(dim, PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout)), depth = ind + 1)
+                LayerScale(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout), depth = ind + 1),
+                LayerScale(dim, FeedForward(dim, mlp_dim, dropout = dropout), depth = ind + 1)
             ]))
     def forward(self, x, context = None):
         layers = dropout_layers(self.layers, dropout = self.layer_dropout)
@@ -146,7 +145,9 @@ class CaiT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches, dim))

vit_pytorch/cct.py

@@ -1,8 +1,22 @@
 import torch
-import torch.nn as nn
+from torch import nn, einsum
 import torch.nn.functional as F
 
-# Pre-defined CCT Models
+from einops import rearrange, repeat
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# CCT Models
+
 __all__ = ['cct_2', 'cct_4', 'cct_6', 'cct_7', 'cct_8', 'cct_14', 'cct_16']
 
 
@@ -44,8 +58,9 @@ def cct_16(*args, **kwargs):
 def _cct(num_layers, num_heads, mlp_ratio, embedding_dim,
          kernel_size=3, stride=None, padding=None,
          *args, **kwargs):
-    stride = stride if stride is not None else max(1, (kernel_size // 2) - 1)
-    padding = padding if padding is not None else max(1, (kernel_size // 2))
+    stride = default(stride, max(1, (kernel_size // 2) - 1))
+    padding = default(padding, max(1, (kernel_size // 2)))
+
     return CCT(num_layers=num_layers,
                num_heads=num_heads,
                mlp_ratio=mlp_ratio,
@@ -55,13 +70,22 @@ def _cct(num_layers, num_heads, mlp_ratio, embedding_dim,
                padding=padding,
                *args, **kwargs)
 
+# positional
+
+def sinusoidal_embedding(n_channels, dim):
+    pe = torch.FloatTensor([[p / (10000 ** (2 * (i // 2) / dim)) for i in range(dim)]
+                            for p in range(n_channels)])
+    pe[:, 0::2] = torch.sin(pe[:, 0::2])
+    pe[:, 1::2] = torch.cos(pe[:, 1::2])
+    return rearrange(pe, '... -> 1 ...')
+
+# modules
 
-# Modules
 class Attention(nn.Module):
     def __init__(self, dim, num_heads=8, attention_dropout=0.1, projection_dropout=0.1):
         super().__init__()
-        self.num_heads = num_heads
-        head_dim = dim // self.num_heads
+        self.heads = num_heads
+        head_dim = dim // self.heads
         self.scale = head_dim ** -0.5
 
         self.qkv = nn.Linear(dim, dim * 3, bias=False)
@@ -71,17 +95,20 @@ class Attention(nn.Module):
 
     def forward(self, x):
         B, N, C = x.shape
-        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
-        q, k, v = qkv[0], qkv[1], qkv[2]
 
-        attn = (q @ k.transpose(-2, -1)) * self.scale
+        qkv = self.qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        q = q * self.scale
+
+        attn = einsum('b h i d, b h j d -> b h i j', q, k)
         attn = attn.softmax(dim=-1)
         attn = self.attn_drop(attn)
 
-        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
-        x = self.proj(x)
-        x = self.proj_drop(x)
-        return x
+        x = einsum('b h i j, b h j d -> b h i d', attn, v)
+        x = rearrange(x, 'b h n d -> b n (h d)')
+
+        return self.proj_drop(self.proj(x))
 
 
 class TransformerEncoderLayer(nn.Module):
@@ -91,7 +118,8 @@ class TransformerEncoderLayer(nn.Module):
     """
     def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1,
                  attention_dropout=0.1, drop_path_rate=0.1):
-        super(TransformerEncoderLayer, self).__init__()
+        super().__init__()
+
         self.pre_norm = nn.LayerNorm(d_model)
         self.self_attn = Attention(dim=d_model, num_heads=nhead,
                                    attention_dropout=attention_dropout, projection_dropout=dropout)
@@ -102,50 +130,34 @@ class TransformerEncoderLayer(nn.Module):
         self.linear2  = nn.Linear(dim_feedforward, d_model)
         self.dropout2 = nn.Dropout(dropout)
 
-        self.drop_path = DropPath(drop_path_rate) if drop_path_rate > 0 else nn.Identity()
+        self.drop_path = DropPath(drop_path_rate)
 
         self.activation = F.gelu
 
-    def forward(self, src: torch.Tensor, *args, **kwargs) -> torch.Tensor:
+    def forward(self, src, *args, **kwargs):
         src = src + self.drop_path(self.self_attn(self.pre_norm(src)))
         src = self.norm1(src)
         src2 = self.linear2(self.dropout1(self.activation(self.linear1(src))))
         src = src + self.drop_path(self.dropout2(src2))
         return src
 
-
-def drop_path(x, drop_prob: float = 0., training: bool = False):
-    """
-    Obtained from: github.com:rwightman/pytorch-image-models
-    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
-    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
-    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
-    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
-    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
-    'survival rate' as the argument.
-    """
-    if drop_prob == 0. or not training:
-        return x
-    keep_prob = 1 - drop_prob
-    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
-    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
-    random_tensor.floor_()  # binarize
-    output = x.div(keep_prob) * random_tensor
-    return output
-
-
 class DropPath(nn.Module):
-    """
-    Obtained from: github.com:rwightman/pytorch-image-models
-    Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
-    """
     def __init__(self, drop_prob=None):
-        super(DropPath, self).__init__()
-        self.drop_prob = drop_prob
+        super().__init__()
+        self.drop_prob = float(drop_prob)
 
     def forward(self, x):
-        return drop_path(x, self.drop_prob, self.training)
+        batch, drop_prob, device, dtype = x.shape[0], self.drop_prob, x.device, x.dtype
 
+        if drop_prob <= 0. or not self.training:
+            return x
+
+        keep_prob = 1 - self.drop_prob
+        shape = (batch, *((1,) * (x.ndim - 1)))
+
+        keep_mask = torch.zeros(shape, device = device).float().uniform_(0, 1) < keep_prob
+        output = x.div(keep_prob) * keep_mask.float()
+        return output
 
 class Tokenizer(nn.Module):
     def __init__(self,
@@ -158,34 +170,35 @@ class Tokenizer(nn.Module):
                  activation=None,
                  max_pool=True,
                  conv_bias=False):
-        super(Tokenizer, self).__init__()
+        super().__init__()
 
         n_filter_list = [n_input_channels] + \
                         [in_planes for _ in range(n_conv_layers - 1)] + \
                         [n_output_channels]
 
+        n_filter_list_pairs = zip(n_filter_list[:-1], n_filter_list[1:])
+
         self.conv_layers = nn.Sequential(
             *[nn.Sequential(
-                nn.Conv2d(n_filter_list[i], n_filter_list[i + 1],
+                nn.Conv2d(chan_in, chan_out,
                           kernel_size=(kernel_size, kernel_size),
                           stride=(stride, stride),
                           padding=(padding, padding), bias=conv_bias),
-                nn.Identity() if activation is None else activation(),
+                nn.Identity() if not exists(activation) else activation(),
                 nn.MaxPool2d(kernel_size=pooling_kernel_size,
                              stride=pooling_stride,
                              padding=pooling_padding) if max_pool else nn.Identity()
             )
-                for i in range(n_conv_layers)
+                for chan_in, chan_out in n_filter_list_pairs
             ])
 
-        self.flattener = nn.Flatten(2, 3)
         self.apply(self.init_weight)
 
     def sequence_length(self, n_channels=3, height=224, width=224):
         return self.forward(torch.zeros((1, n_channels, height, width))).shape[1]
 
     def forward(self, x):
-        return self.flattener(self.conv_layers(x)).transpose(-2, -1)
+        return rearrange(self.conv_layers(x), 'b c h w -> b (h w) c')
 
     @staticmethod
     def init_weight(m):
@@ -208,106 +221,105 @@ class TransformerClassifier(nn.Module):
                  sequence_length=None,
                  *args, **kwargs):
         super().__init__()
-        positional_embedding = positional_embedding if \
-            positional_embedding in ['sine', 'learnable', 'none'] else 'sine'
+        assert positional_embedding in {'sine', 'learnable', 'none'}
+
         dim_feedforward = int(embedding_dim * mlp_ratio)
         self.embedding_dim = embedding_dim
         self.sequence_length = sequence_length
         self.seq_pool = seq_pool
 
-        assert sequence_length is not None or positional_embedding == 'none', \
+        assert exists(sequence_length) or positional_embedding == 'none', \
             f"Positional embedding is set to {positional_embedding} and" \
             f" the sequence length was not specified."
 
         if not seq_pool:
             sequence_length += 1
-            self.class_emb = nn.Parameter(torch.zeros(1, 1, self.embedding_dim),
-                                          requires_grad=True)
+            self.class_emb = nn.Parameter(torch.zeros(1, 1, self.embedding_dim), requires_grad=True)
         else:
             self.attention_pool = nn.Linear(self.embedding_dim, 1)
 
-        if positional_embedding != 'none':
-            if positional_embedding == 'learnable':
-                self.positional_emb = nn.Parameter(torch.zeros(1, sequence_length, embedding_dim),
-                                                   requires_grad=True)
-                nn.init.trunc_normal_(self.positional_emb, std=0.2)
-            else:
-                self.positional_emb = nn.Parameter(self.sinusoidal_embedding(sequence_length, embedding_dim),
-                                                   requires_grad=False)
-        else:
+        if positional_embedding == 'none':
             self.positional_emb = None
+        elif positional_embedding == 'learnable':
+            self.positional_emb = nn.Parameter(torch.zeros(1, sequence_length, embedding_dim),
+                                               requires_grad=True)
+            nn.init.trunc_normal_(self.positional_emb, std=0.2)
+        else:
+            self.positional_emb = nn.Parameter(sinusoidal_embedding(sequence_length, embedding_dim),
+                                               requires_grad=False)
 
         self.dropout = nn.Dropout(p=dropout_rate)
+
         dpr = [x.item() for x in torch.linspace(0, stochastic_depth_rate, num_layers)]
+
         self.blocks = nn.ModuleList([
             TransformerEncoderLayer(d_model=embedding_dim, nhead=num_heads,
                                     dim_feedforward=dim_feedforward, dropout=dropout_rate,
-                                    attention_dropout=attention_dropout, drop_path_rate=dpr[i])
-            for i in range(num_layers)])
+                                    attention_dropout=attention_dropout, drop_path_rate=layer_dpr)
+            for layer_dpr in dpr])
+
         self.norm = nn.LayerNorm(embedding_dim)
 
         self.fc = nn.Linear(embedding_dim, num_classes)
         self.apply(self.init_weight)
 
     def forward(self, x):
-        if self.positional_emb is None and x.size(1) < self.sequence_length:
+        b = x.shape[0]
+
+        if not exists(self.positional_emb) and x.size(1) < self.sequence_length:
             x = F.pad(x, (0, 0, 0, self.n_channels - x.size(1)), mode='constant', value=0)
 
         if not self.seq_pool:
-            cls_token = self.class_emb.expand(x.shape[0], -1, -1)
+            cls_token = repeat(self.class_emb, '1 1 d -> b 1 d', b = b)
             x = torch.cat((cls_token, x), dim=1)
 
-        if self.positional_emb is not None:
+        if exists(self.positional_emb):
             x += self.positional_emb
 
         x = self.dropout(x)
 
         for blk in self.blocks:
             x = blk(x)
+
         x = self.norm(x)
 
         if self.seq_pool:
-            x = torch.matmul(F.softmax(self.attention_pool(x), dim=1).transpose(-1, -2), x).squeeze(-2)
+            attn_weights = rearrange(self.attention_pool(x), 'b n 1 -> b n')
+            x = einsum('b n, b n d -> b d', attn_weights.softmax(dim = 1), x)
         else:
             x = x[:, 0]
 
-        x = self.fc(x)
-        return x
+        return self.fc(x)
 
     @staticmethod
     def init_weight(m):
         if isinstance(m, nn.Linear):
             nn.init.trunc_normal_(m.weight, std=.02)
-            if isinstance(m, nn.Linear) and m.bias is not None:
+            if isinstance(m, nn.Linear) and exists(m.bias):
                 nn.init.constant_(m.bias, 0)
         elif isinstance(m, nn.LayerNorm):
             nn.init.constant_(m.bias, 0)
             nn.init.constant_(m.weight, 1.0)
 
-    @staticmethod
-    def sinusoidal_embedding(n_channels, dim):
-        pe = torch.FloatTensor([[p / (10000 ** (2 * (i // 2) / dim)) for i in range(dim)]
-                                for p in range(n_channels)])
-        pe[:, 0::2] = torch.sin(pe[:, 0::2])
-        pe[:, 1::2] = torch.cos(pe[:, 1::2])
-        return pe.unsqueeze(0)
-
-
 # CCT Main model
+
 class CCT(nn.Module):
-    def __init__(self,
-                 img_size=224,
-                 embedding_dim=768,
-                 n_input_channels=3,
-                 n_conv_layers=1,
-                 kernel_size=7,
-                 stride=2,
-                 padding=3,
-                 pooling_kernel_size=3,
-                 pooling_stride=2,
-                 pooling_padding=1,
-                 *args, **kwargs):
-        super(CCT, self).__init__()
+    def __init__(
+        self,
+        img_size=224,
+        embedding_dim=768,
+        n_input_channels=3,
+        n_conv_layers=1,
+        kernel_size=7,
+        stride=2,
+        padding=3,
+        pooling_kernel_size=3,
+        pooling_stride=2,
+        pooling_padding=1,
+        *args, **kwargs
+    ):
+        super().__init__()
+        img_height, img_width = pair(img_size)
 
         self.tokenizer = Tokenizer(n_input_channels=n_input_channels,
                                    n_output_channels=embedding_dim,
@@ -324,8 +336,8 @@ class CCT(nn.Module):
 
         self.classifier = TransformerClassifier(
             sequence_length=self.tokenizer.sequence_length(n_channels=n_input_channels,
-                                                           height=img_size,
-                                                           width=img_size),
+                                                           height=img_height,
+                                                           width=img_width),
             embedding_dim=embedding_dim,
             seq_pool=True,
             dropout_rate=0.,
@@ -336,4 +348,3 @@ class CCT(nn.Module):
     def forward(self, x):
         x = self.tokenizer(x)
         return self.classifier(x)
-

vit_pytorch/cct_3d.py

@@ -0,0 +1,376 @@
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# CCT Models
+
+__all__ = ['cct_2', 'cct_4', 'cct_6', 'cct_7', 'cct_8', 'cct_14', 'cct_16']
+
+
+def cct_2(*args, **kwargs):
+    return _cct(num_layers=2, num_heads=2, mlp_ratio=1, embedding_dim=128,
+                *args, **kwargs)
+
+
+def cct_4(*args, **kwargs):
+    return _cct(num_layers=4, num_heads=2, mlp_ratio=1, embedding_dim=128,
+                *args, **kwargs)
+
+
+def cct_6(*args, **kwargs):
+    return _cct(num_layers=6, num_heads=4, mlp_ratio=2, embedding_dim=256,
+                *args, **kwargs)
+
+
+def cct_7(*args, **kwargs):
+    return _cct(num_layers=7, num_heads=4, mlp_ratio=2, embedding_dim=256,
+                *args, **kwargs)
+
+
+def cct_8(*args, **kwargs):
+    return _cct(num_layers=8, num_heads=4, mlp_ratio=2, embedding_dim=256,
+                *args, **kwargs)
+
+
+def cct_14(*args, **kwargs):
+    return _cct(num_layers=14, num_heads=6, mlp_ratio=3, embedding_dim=384,
+                *args, **kwargs)
+
+
+def cct_16(*args, **kwargs):
+    return _cct(num_layers=16, num_heads=6, mlp_ratio=3, embedding_dim=384,
+                *args, **kwargs)
+
+
+def _cct(num_layers, num_heads, mlp_ratio, embedding_dim,
+         kernel_size=3, stride=None, padding=None,
+         *args, **kwargs):
+    stride = default(stride, max(1, (kernel_size // 2) - 1))
+    padding = default(padding, max(1, (kernel_size // 2)))
+
+    return CCT(num_layers=num_layers,
+               num_heads=num_heads,
+               mlp_ratio=mlp_ratio,
+               embedding_dim=embedding_dim,
+               kernel_size=kernel_size,
+               stride=stride,
+               padding=padding,
+               *args, **kwargs)
+
+# positional
+
+def sinusoidal_embedding(n_channels, dim):
+    pe = torch.FloatTensor([[p / (10000 ** (2 * (i // 2) / dim)) for i in range(dim)]
+                            for p in range(n_channels)])
+    pe[:, 0::2] = torch.sin(pe[:, 0::2])
+    pe[:, 1::2] = torch.cos(pe[:, 1::2])
+    return rearrange(pe, '... -> 1 ...')
+
+# modules
+
+class Attention(nn.Module):
+    def __init__(self, dim, num_heads=8, attention_dropout=0.1, projection_dropout=0.1):
+        super().__init__()
+        self.heads = num_heads
+        head_dim = dim // self.heads
+        self.scale = head_dim ** -0.5
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=False)
+        self.attn_drop = nn.Dropout(attention_dropout)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(projection_dropout)
+
+    def forward(self, x):
+        B, N, C = x.shape
+
+        qkv = self.qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        q = q * self.scale
+
+        attn = einsum('b h i d, b h j d -> b h i j', q, k)
+        attn = attn.softmax(dim=-1)
+        attn = self.attn_drop(attn)
+
+        x = einsum('b h i j, b h j d -> b h i d', attn, v)
+        x = rearrange(x, 'b h n d -> b n (h d)')
+
+        return self.proj_drop(self.proj(x))
+
+
+class TransformerEncoderLayer(nn.Module):
+    """
+    Inspired by torch.nn.TransformerEncoderLayer and
+    rwightman's timm package.
+    """
+    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1,
+                 attention_dropout=0.1, drop_path_rate=0.1):
+        super().__init__()
+
+        self.pre_norm = nn.LayerNorm(d_model)
+        self.self_attn = Attention(dim=d_model, num_heads=nhead,
+                                   attention_dropout=attention_dropout, projection_dropout=dropout)
+
+        self.linear1  = nn.Linear(d_model, dim_feedforward)
+        self.dropout1 = nn.Dropout(dropout)
+        self.norm1    = nn.LayerNorm(d_model)
+        self.linear2  = nn.Linear(dim_feedforward, d_model)
+        self.dropout2 = nn.Dropout(dropout)
+
+        self.drop_path = DropPath(drop_path_rate)
+
+        self.activation = F.gelu
+
+    def forward(self, src, *args, **kwargs):
+        src = src + self.drop_path(self.self_attn(self.pre_norm(src)))
+        src = self.norm1(src)
+        src2 = self.linear2(self.dropout1(self.activation(self.linear1(src))))
+        src = src + self.drop_path(self.dropout2(src2))
+        return src
+
+class DropPath(nn.Module):
+    def __init__(self, drop_prob=None):
+        super().__init__()
+        self.drop_prob = float(drop_prob)
+
+    def forward(self, x):
+        batch, drop_prob, device, dtype = x.shape[0], self.drop_prob, x.device, x.dtype
+
+        if drop_prob <= 0. or not self.training:
+            return x
+
+        keep_prob = 1 - self.drop_prob
+        shape = (batch, *((1,) * (x.ndim - 1)))
+
+        keep_mask = torch.zeros(shape, device = device).float().uniform_(0, 1) < keep_prob
+        output = x.div(keep_prob) * keep_mask.float()
+        return output
+
+class Tokenizer(nn.Module):
+    def __init__(
+        self,
+        frame_kernel_size,
+        kernel_size,
+        stride,
+        padding,
+        frame_stride=1,
+        frame_pooling_stride=1,
+        frame_pooling_kernel_size=1,
+        pooling_kernel_size=3,
+        pooling_stride=2,
+        pooling_padding=1,
+        n_conv_layers=1,
+        n_input_channels=3,
+        n_output_channels=64,
+        in_planes=64,
+        activation=None,
+        max_pool=True,
+        conv_bias=False
+    ):
+        super().__init__()
+
+        n_filter_list = [n_input_channels] + \
+                        [in_planes for _ in range(n_conv_layers - 1)] + \
+                        [n_output_channels]
+
+        n_filter_list_pairs = zip(n_filter_list[:-1], n_filter_list[1:])
+
+        self.conv_layers = nn.Sequential(
+            *[nn.Sequential(
+                nn.Conv3d(chan_in, chan_out,
+                          kernel_size=(frame_kernel_size, kernel_size, kernel_size),
+                          stride=(frame_stride, stride, stride),
+                          padding=(frame_kernel_size // 2, padding, padding), bias=conv_bias),
+                nn.Identity() if not exists(activation) else activation(),
+                nn.MaxPool3d(kernel_size=(frame_pooling_kernel_size, pooling_kernel_size, pooling_kernel_size),
+                             stride=(frame_pooling_stride, pooling_stride, pooling_stride),
+                             padding=(frame_pooling_kernel_size // 2, pooling_padding, pooling_padding)) if max_pool else nn.Identity()
+            )
+                for chan_in, chan_out in n_filter_list_pairs
+            ])
+
+        self.apply(self.init_weight)
+
+    def sequence_length(self, n_channels=3, frames=8, height=224, width=224):
+        return self.forward(torch.zeros((1, n_channels, frames, height, width))).shape[1]
+
+    def forward(self, x):
+        x = self.conv_layers(x)
+        return rearrange(x, 'b c f h w -> b (f h w) c')
+
+    @staticmethod
+    def init_weight(m):
+        if isinstance(m, nn.Conv3d):
+            nn.init.kaiming_normal_(m.weight)
+
+
+class TransformerClassifier(nn.Module):
+    def __init__(
+        self,
+        seq_pool=True,
+        embedding_dim=768,
+        num_layers=12,
+        num_heads=12,
+        mlp_ratio=4.0,
+        num_classes=1000,
+        dropout_rate=0.1,
+        attention_dropout=0.1,
+        stochastic_depth_rate=0.1,
+        positional_embedding='sine',
+        sequence_length=None,
+        *args, **kwargs
+    ):
+        super().__init__()
+        assert positional_embedding in {'sine', 'learnable', 'none'}
+
+        dim_feedforward = int(embedding_dim * mlp_ratio)
+        self.embedding_dim = embedding_dim
+        self.sequence_length = sequence_length
+        self.seq_pool = seq_pool
+
+        assert exists(sequence_length) or positional_embedding == 'none', \
+            f"Positional embedding is set to {positional_embedding} and" \
+            f" the sequence length was not specified."
+
+        if not seq_pool:
+            sequence_length += 1
+            self.class_emb = nn.Parameter(torch.zeros(1, 1, self.embedding_dim))
+        else:
+            self.attention_pool = nn.Linear(self.embedding_dim, 1)
+
+        if positional_embedding == 'none':
+            self.positional_emb = None
+        elif positional_embedding == 'learnable':
+            self.positional_emb = nn.Parameter(torch.zeros(1, sequence_length, embedding_dim))
+            nn.init.trunc_normal_(self.positional_emb, std = 0.2)
+        else:
+            self.register_buffer('positional_emb', sinusoidal_embedding(sequence_length, embedding_dim))
+
+        self.dropout = nn.Dropout(p=dropout_rate)
+
+        dpr = [x.item() for x in torch.linspace(0, stochastic_depth_rate, num_layers)]
+
+        self.blocks = nn.ModuleList([
+            TransformerEncoderLayer(d_model=embedding_dim, nhead=num_heads,
+                                    dim_feedforward=dim_feedforward, dropout=dropout_rate,
+                                    attention_dropout=attention_dropout, drop_path_rate=layer_dpr)
+            for layer_dpr in dpr])
+
+        self.norm = nn.LayerNorm(embedding_dim)
+
+        self.fc = nn.Linear(embedding_dim, num_classes)
+        self.apply(self.init_weight)
+
+    @staticmethod
+    def init_weight(m):
+        if isinstance(m, nn.Linear):
+            nn.init.trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and exists(m.bias):
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+
+    def forward(self, x):
+        b = x.shape[0]
+
+        if not exists(self.positional_emb) and x.size(1) < self.sequence_length:
+            x = F.pad(x, (0, 0, 0, self.n_channels - x.size(1)), mode='constant', value=0)
+
+        if not self.seq_pool:
+            cls_token = repeat(self.class_emb, '1 1 d -> b 1 d', b = b)
+            x = torch.cat((cls_token, x), dim=1)
+
+        if exists(self.positional_emb):
+            x += self.positional_emb
+
+        x = self.dropout(x)
+
+        for blk in self.blocks:
+            x = blk(x)
+
+        x = self.norm(x)
+
+        if self.seq_pool:
+            attn_weights = rearrange(self.attention_pool(x), 'b n 1 -> b n')
+            x = einsum('b n, b n d -> b d', attn_weights.softmax(dim = 1), x)
+        else:
+            x = x[:, 0]
+
+        return self.fc(x)
+
+# CCT Main model
+
+class CCT(nn.Module):
+    def __init__(
+        self,
+        img_size=224,
+        num_frames=8,
+        embedding_dim=768,
+        n_input_channels=3,
+        n_conv_layers=1,
+        frame_stride=1,
+        frame_kernel_size=3,
+        frame_pooling_kernel_size=1,
+        frame_pooling_stride=1,
+        kernel_size=7,
+        stride=2,
+        padding=3,
+        pooling_kernel_size=3,
+        pooling_stride=2,
+        pooling_padding=1,
+        *args, **kwargs
+    ):
+        super().__init__()
+        img_height, img_width = pair(img_size)
+
+        self.tokenizer = Tokenizer(
+            n_input_channels=n_input_channels,
+            n_output_channels=embedding_dim,
+            frame_stride=frame_stride,
+            frame_kernel_size=frame_kernel_size,
+            frame_pooling_stride=frame_pooling_stride,
+            frame_pooling_kernel_size=frame_pooling_kernel_size,
+            kernel_size=kernel_size,
+            stride=stride,
+            padding=padding,
+            pooling_kernel_size=pooling_kernel_size,
+            pooling_stride=pooling_stride,
+            pooling_padding=pooling_padding,
+            max_pool=True,
+            activation=nn.ReLU,
+            n_conv_layers=n_conv_layers,
+            conv_bias=False
+        )
+
+        self.classifier = TransformerClassifier(
+            sequence_length=self.tokenizer.sequence_length(
+                n_channels=n_input_channels,
+                frames=num_frames,
+                height=img_height,
+                width=img_width
+            ),
+            embedding_dim=embedding_dim,
+            seq_pool=True,
+            dropout_rate=0.,
+            attention_dropout=0.1,
+            stochastic_depth=0.1,
+            *args, **kwargs
+        )
+
+    def forward(self, x):
+        x = self.tokenizer(x)
+        return self.classifier(x)

vit_pytorch/cross_vit.py

@@ -13,22 +13,13 @@ def exists(val):
 def default(val, d):
     return val if exists(val) else d
 
-# pre-layernorm
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 # feedforward
 
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -47,7 +38,10 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
         self.to_q = nn.Linear(dim, inner_dim, bias = False)
         self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
 
@@ -58,6 +52,7 @@ class Attention(nn.Module):
 
     def forward(self, x, context = None, kv_include_self = False):
         b, n, _, h = *x.shape, self.heads
+        x = self.norm(x)
         context = default(context, x)
 
         if kv_include_self:
@@ -69,6 +64,7 @@ class Attention(nn.Module):
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
@@ -83,8 +79,8 @@ class Transformer(nn.Module):
         self.norm = nn.LayerNorm(dim)
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
 
     def forward(self, x):
@@ -118,8 +114,8 @@ class CrossTransformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                ProjectInOut(sm_dim, lg_dim, PreNorm(lg_dim, Attention(lg_dim, heads = heads, dim_head = dim_head, dropout = dropout))),
-                ProjectInOut(lg_dim, sm_dim, PreNorm(sm_dim, Attention(sm_dim, heads = heads, dim_head = dim_head, dropout = dropout)))
+                ProjectInOut(sm_dim, lg_dim, Attention(lg_dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                ProjectInOut(lg_dim, sm_dim, Attention(sm_dim, heads = heads, dim_head = dim_head, dropout = dropout))
             ]))
 
     def forward(self, sm_tokens, lg_tokens):
@@ -183,7 +179,9 @@ class ImageEmbedder(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/crossformer.py

@@ -62,9 +62,9 @@ class LayerNorm(nn.Module):
         self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
 
     def forward(self, x):
-        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (std + self.eps) * self.g + self.b
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
 def FeedForward(dim, mult = 4, dropout = 0.):
     return nn.Sequential(
@@ -95,6 +95,9 @@ class Attention(nn.Module):
         self.window_size = window_size
 
         self.norm = LayerNorm(dim)
+
+        self.dropout = nn.Dropout(dropout)
+
         self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
         self.to_out = nn.Conv2d(inner_dim, dim, 1)
 
@@ -105,7 +108,7 @@ class Attention(nn.Module):
         # calculate and store indices for retrieving bias
 
         pos = torch.arange(window_size)
-        grid = torch.stack(torch.meshgrid(pos, pos))
+        grid = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
         grid = rearrange(grid, 'c i j -> (i j) c')
         rel_pos = grid[:, None] - grid[None, :]
         rel_pos += window_size - 1
@@ -141,7 +144,7 @@ class Attention(nn.Module):
         # add dynamic positional bias
 
         pos = torch.arange(-wsz, wsz + 1, device = device)
-        rel_pos = torch.stack(torch.meshgrid(pos, pos))
+        rel_pos = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
         rel_pos = rearrange(rel_pos, 'c i j -> (i j) c')
         biases = self.dpb(rel_pos.float())
         rel_pos_bias = biases[self.rel_pos_indices]
@@ -151,6 +154,7 @@ class Attention(nn.Module):
         # attend
 
         attn = sim.softmax(dim = -1)
+        attn = self.dropout(attn)
 
         # merge heads
 

vit_pytorch/cvt.py

@@ -30,23 +30,15 @@ class LayerNorm(nn.Module): # layernorm, but done in the channel dimension #1
         self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
 
     def forward(self, x):
-        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (std + self.eps) * self.g + self.b
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        x = self.norm(x)
-        return self.fn(x, **kwargs)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
 class FeedForward(nn.Module):
     def __init__(self, dim, mult = 4, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            LayerNorm(dim),
             nn.Conv2d(dim, dim * mult, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -75,7 +67,9 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
 
         self.to_q = DepthWiseConv2d(dim, inner_dim, proj_kernel, padding = padding, stride = 1, bias = False)
         self.to_kv = DepthWiseConv2d(dim, inner_dim * 2, proj_kernel, padding = padding, stride = kv_proj_stride, bias = False)
@@ -88,12 +82,15 @@ class Attention(nn.Module):
     def forward(self, x):
         shape = x.shape
         b, n, _, y, h = *shape, self.heads
+
+        x = self.norm(x)
         q, k, v = (self.to_q(x), *self.to_kv(x).chunk(2, dim = 1))
         q, k, v = map(lambda t: rearrange(t, 'b (h d) x y -> (b h) (x y) d', h = h), (q, k, v))
 
         dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b i j, b j d -> b i d', attn, v)
         out = rearrange(out, '(b h) (x y) d -> b (h d) x y', h = h, y = y)
@@ -105,8 +102,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, proj_kernel = proj_kernel, kv_proj_stride = kv_proj_stride, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout))
+                Attention(dim, proj_kernel = proj_kernel, kv_proj_stride = kv_proj_stride, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_mult, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:
@@ -162,12 +159,14 @@ class CvT(nn.Module):
 
             dim = config['emb_dim']
 
-        self.layers = nn.Sequential(
-            *layers,
+        self.layers = nn.Sequential(*layers)
+
+        self.to_logits = nn.Sequential(
             nn.AdaptiveAvgPool2d(1),
             Rearrange('... () () -> ...'),
             nn.Linear(dim, num_classes)
         )
 
     def forward(self, x):
-        return self.layers(x)
+        latents = self.layers(x)
+        return self.to_logits(latents)

vit_pytorch/deepvit.py

@@ -5,25 +5,11 @@ import torch.nn.functional as F
 from einops import rearrange, repeat
 from einops.layers.torch import Rearrange
 
-class Residual(nn.Module):
-    def __init__(self, fn):
-        super().__init__()
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(x, **kwargs) + x
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -40,8 +26,11 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
+        self.dropout = nn.Dropout(dropout)
+
         self.reattn_weights = nn.Parameter(torch.randn(heads, heads))
 
         self.reattn_norm = nn.Sequential(
@@ -57,6 +46,8 @@ class Attention(nn.Module):
 
     def forward(self, x):
         b, n, _, h = *x.shape, self.heads
+        x = self.norm(x)
+
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
 
@@ -64,6 +55,7 @@ class Attention(nn.Module):
 
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
         attn = dots.softmax(dim=-1)
+        attn = self.dropout(attn)
 
         # re-attention
 
@@ -83,13 +75,13 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                Residual(PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout))),
-                Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout)))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:
-            x = attn(x)
-            x = ff(x)
+            x = attn(x) + x
+            x = ff(x) + x
         return x
 
 class DeepViT(nn.Module):
@@ -102,7 +94,9 @@ class DeepViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/efficient.py

@@ -3,17 +3,23 @@ from torch import nn
 from einops import rearrange, repeat
 from einops.layers.torch import Rearrange
 
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
 class ViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, transformer, pool = 'cls', channels = 3):
         super().__init__()
-        assert image_size % patch_size == 0, 'image dimensions must be divisible by the patch size'
+        image_size_h, image_size_w = pair(image_size)
+        assert image_size_h % patch_size == 0 and image_size_w % patch_size == 0, 'image dimensions must be divisible by the patch size'
         assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
-        num_patches = (image_size // patch_size) ** 2
+        num_patches = (image_size_h // patch_size) * (image_size_w // patch_size)
         patch_dim = channels * patch_size ** 2
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/es_vit.py

@@ -0,0 +1,367 @@
+import copy
+import random
+from functools import wraps, partial
+
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+from torchvision import transforms as T
+
+from einops import rearrange, reduce, repeat
+
+# helper functions
+
+def exists(val):
+    return val is not None
+
+def default(val, default):
+    return val if exists(val) else default
+
+def singleton(cache_key):
+    def inner_fn(fn):
+        @wraps(fn)
+        def wrapper(self, *args, **kwargs):
+            instance = getattr(self, cache_key)
+            if instance is not None:
+                return instance
+
+            instance = fn(self, *args, **kwargs)
+            setattr(self, cache_key, instance)
+            return instance
+        return wrapper
+    return inner_fn
+
+def get_module_device(module):
+    return next(module.parameters()).device
+
+def set_requires_grad(model, val):
+    for p in model.parameters():
+        p.requires_grad = val
+
+# tensor related helpers
+
+def log(t, eps = 1e-20):
+    return torch.log(t + eps)
+
+# loss function # (algorithm 1 in the paper)
+
+def view_loss_fn(
+    teacher_logits,
+    student_logits,
+    teacher_temp,
+    student_temp,
+    centers,
+    eps = 1e-20
+):
+    teacher_logits = teacher_logits.detach()
+    student_probs = (student_logits / student_temp).softmax(dim = -1)
+    teacher_probs = ((teacher_logits - centers) / teacher_temp).softmax(dim = -1)
+    return - (teacher_probs * log(student_probs, eps)).sum(dim = -1).mean()
+
+def region_loss_fn(
+    teacher_logits,
+    student_logits,
+    teacher_latent,
+    student_latent,
+    teacher_temp,
+    student_temp,
+    centers,
+    eps = 1e-20
+):
+    teacher_logits = teacher_logits.detach()
+    student_probs = (student_logits / student_temp).softmax(dim = -1)
+    teacher_probs = ((teacher_logits - centers) / teacher_temp).softmax(dim = -1)
+
+    sim_matrix = einsum('b i d, b j d -> b i j', student_latent, teacher_latent)
+    sim_indices = sim_matrix.max(dim = -1).indices
+    sim_indices = repeat(sim_indices, 'b n -> b n k', k = teacher_probs.shape[-1])
+    max_sim_teacher_probs = teacher_probs.gather(1, sim_indices)
+
+    return - (max_sim_teacher_probs * log(student_probs, eps)).sum(dim = -1).mean()
+
+# augmentation utils
+
+class RandomApply(nn.Module):
+    def __init__(self, fn, p):
+        super().__init__()
+        self.fn = fn
+        self.p = p
+
+    def forward(self, x):
+        if random.random() > self.p:
+            return x
+        return self.fn(x)
+
+# exponential moving average
+
+class EMA():
+    def __init__(self, beta):
+        super().__init__()
+        self.beta = beta
+
+    def update_average(self, old, new):
+        if old is None:
+            return new
+        return old * self.beta + (1 - self.beta) * new
+
+def update_moving_average(ema_updater, ma_model, current_model):
+    for current_params, ma_params in zip(current_model.parameters(), ma_model.parameters()):
+        old_weight, up_weight = ma_params.data, current_params.data
+        ma_params.data = ema_updater.update_average(old_weight, up_weight)
+
+# MLP class for projector and predictor
+
+class L2Norm(nn.Module):
+    def forward(self, x, eps = 1e-6):
+        return F.normalize(x, dim = 1, eps = eps)
+
+class MLP(nn.Module):
+    def __init__(self, dim, dim_out, num_layers, hidden_size = 256):
+        super().__init__()
+
+        layers = []
+        dims = (dim, *((hidden_size,) * (num_layers - 1)))
+
+        for ind, (layer_dim_in, layer_dim_out) in enumerate(zip(dims[:-1], dims[1:])):
+            is_last = ind == (len(dims) - 1)
+
+            layers.extend([
+                nn.Linear(layer_dim_in, layer_dim_out),
+                nn.GELU() if not is_last else nn.Identity()
+            ])
+
+        self.net = nn.Sequential(
+            *layers,
+            L2Norm(),
+            nn.Linear(hidden_size, dim_out)
+        )
+
+    def forward(self, x):
+        return self.net(x)
+
+# a wrapper class for the base neural network
+# will manage the interception of the hidden layer output
+# and pipe it into the projecter and predictor nets
+
+class NetWrapper(nn.Module):
+    def __init__(self, net, output_dim, projection_hidden_size, projection_num_layers, layer = -2):
+        super().__init__()
+        self.net = net
+        self.layer = layer
+
+        self.view_projector = None
+        self.region_projector = None
+        self.projection_hidden_size = projection_hidden_size
+        self.projection_num_layers = projection_num_layers
+        self.output_dim = output_dim
+
+        self.hidden = {}
+        self.hook_registered = False
+
+    def _find_layer(self):
+        if type(self.layer) == str:
+            modules = dict([*self.net.named_modules()])
+            return modules.get(self.layer, None)
+        elif type(self.layer) == int:
+            children = [*self.net.children()]
+            return children[self.layer]
+        return None
+
+    def _hook(self, _, input, output):
+        device = input[0].device
+        self.hidden[device] = output
+
+    def _register_hook(self):
+        layer = self._find_layer()
+        assert layer is not None, f'hidden layer ({self.layer}) not found'
+        handle = layer.register_forward_hook(self._hook)
+        self.hook_registered = True
+
+    @singleton('view_projector')
+    def _get_view_projector(self, hidden):
+        dim = hidden.shape[1]
+        projector = MLP(dim, self.output_dim, self.projection_num_layers, self.projection_hidden_size)
+        return projector.to(hidden)
+
+    @singleton('region_projector')
+    def _get_region_projector(self, hidden):
+        dim = hidden.shape[1]
+        projector = MLP(dim, self.output_dim, self.projection_num_layers, self.projection_hidden_size)
+        return projector.to(hidden)
+
+    def get_embedding(self, x):
+        if self.layer == -1:
+            return self.net(x)
+
+        if not self.hook_registered:
+            self._register_hook()
+
+        self.hidden.clear()
+        _ = self.net(x)
+        hidden = self.hidden[x.device]
+        self.hidden.clear()
+
+        assert hidden is not None, f'hidden layer {self.layer} never emitted an output'
+        return hidden
+
+    def forward(self, x, return_projection = True):
+        region_latents = self.get_embedding(x)
+        global_latent = reduce(region_latents, 'b c h w -> b c', 'mean')
+
+        if not return_projection:
+            return global_latent, region_latents
+
+        view_projector = self._get_view_projector(global_latent)
+        region_projector = self._get_region_projector(region_latents)
+
+        region_latents = rearrange(region_latents, 'b c h w -> b (h w) c')
+
+        return view_projector(global_latent), region_projector(region_latents), region_latents
+
+# main class
+
+class EsViTTrainer(nn.Module):
+    def __init__(
+        self,
+        net,
+        image_size,
+        hidden_layer = -2,
+        projection_hidden_size = 256,
+        num_classes_K = 65336,
+        projection_layers = 4,
+        student_temp = 0.9,
+        teacher_temp = 0.04,
+        local_upper_crop_scale = 0.4,
+        global_lower_crop_scale = 0.5,
+        moving_average_decay = 0.9,
+        center_moving_average_decay = 0.9,
+        augment_fn = None,
+        augment_fn2 = None
+    ):
+        super().__init__()
+        self.net = net
+
+        # default BYOL augmentation
+
+        DEFAULT_AUG = torch.nn.Sequential(
+            RandomApply(
+                T.ColorJitter(0.8, 0.8, 0.8, 0.2),
+                p = 0.3
+            ),
+            T.RandomGrayscale(p=0.2),
+            T.RandomHorizontalFlip(),
+            RandomApply(
+                T.GaussianBlur((3, 3), (1.0, 2.0)),
+                p = 0.2
+            ),
+            T.Normalize(
+                mean=torch.tensor([0.485, 0.456, 0.406]),
+                std=torch.tensor([0.229, 0.224, 0.225])),
+        )
+
+        self.augment1 = default(augment_fn, DEFAULT_AUG)
+        self.augment2 = default(augment_fn2, DEFAULT_AUG)
+
+        # local and global crops
+
+        self.local_crop = T.RandomResizedCrop((image_size, image_size), scale = (0.05, local_upper_crop_scale))
+        self.global_crop = T.RandomResizedCrop((image_size, image_size), scale = (global_lower_crop_scale, 1.))
+
+        self.student_encoder = NetWrapper(net, num_classes_K, projection_hidden_size, projection_layers, layer = hidden_layer)
+
+        self.teacher_encoder = None
+        self.teacher_ema_updater = EMA(moving_average_decay)
+
+        self.register_buffer('teacher_view_centers', torch.zeros(1, num_classes_K))
+        self.register_buffer('last_teacher_view_centers',  torch.zeros(1, num_classes_K))
+
+        self.register_buffer('teacher_region_centers', torch.zeros(1, num_classes_K))
+        self.register_buffer('last_teacher_region_centers',  torch.zeros(1, num_classes_K))
+
+        self.teacher_centering_ema_updater = EMA(center_moving_average_decay)
+
+        self.student_temp = student_temp
+        self.teacher_temp = teacher_temp
+
+        # get device of network and make wrapper same device
+        device = get_module_device(net)
+        self.to(device)
+
+        # send a mock image tensor to instantiate singleton parameters
+        self.forward(torch.randn(2, 3, image_size, image_size, device=device))
+
+    @singleton('teacher_encoder')
+    def _get_teacher_encoder(self):
+        teacher_encoder = copy.deepcopy(self.student_encoder)
+        set_requires_grad(teacher_encoder, False)
+        return teacher_encoder
+
+    def reset_moving_average(self):
+        del self.teacher_encoder
+        self.teacher_encoder = None
+
+    def update_moving_average(self):
+        assert self.teacher_encoder is not None, 'target encoder has not been created yet'
+        update_moving_average(self.teacher_ema_updater, self.teacher_encoder, self.student_encoder)
+
+        new_teacher_view_centers = self.teacher_centering_ema_updater.update_average(self.teacher_view_centers, self.last_teacher_view_centers)
+        self.teacher_view_centers.copy_(new_teacher_view_centers)
+
+        new_teacher_region_centers = self.teacher_centering_ema_updater.update_average(self.teacher_region_centers, self.last_teacher_region_centers)
+        self.teacher_region_centers.copy_(new_teacher_region_centers)
+
+    def forward(
+        self,
+        x,
+        return_embedding = False,
+        return_projection = True,
+        student_temp = None,
+        teacher_temp = None
+    ):
+        if return_embedding:
+            return self.student_encoder(x, return_projection = return_projection)
+
+        image_one, image_two = self.augment1(x), self.augment2(x)
+
+        local_image_one, local_image_two   = self.local_crop(image_one),  self.local_crop(image_two)
+        global_image_one, global_image_two = self.global_crop(image_one), self.global_crop(image_two)
+
+        student_view_proj_one, student_region_proj_one, student_latent_one = self.student_encoder(local_image_one)
+        student_view_proj_two, student_region_proj_two, student_latent_two = self.student_encoder(local_image_two)
+
+        with torch.no_grad():
+            teacher_encoder = self._get_teacher_encoder()
+            teacher_view_proj_one, teacher_region_proj_one, teacher_latent_one = teacher_encoder(global_image_one)
+            teacher_view_proj_two, teacher_region_proj_two, teacher_latent_two = teacher_encoder(global_image_two)
+
+        view_loss_fn_ = partial(
+            view_loss_fn,
+            student_temp = default(student_temp, self.student_temp),
+            teacher_temp = default(teacher_temp, self.teacher_temp),
+            centers = self.teacher_view_centers
+        )
+
+        region_loss_fn_ = partial(
+            region_loss_fn,
+            student_temp = default(student_temp, self.student_temp),
+            teacher_temp = default(teacher_temp, self.teacher_temp),
+            centers = self.teacher_region_centers
+        )
+
+        # calculate view-level loss
+
+        teacher_view_logits_avg = torch.cat((teacher_view_proj_one, teacher_view_proj_two)).mean(dim = 0)
+        self.last_teacher_view_centers.copy_(teacher_view_logits_avg)
+
+        teacher_region_logits_avg = torch.cat((teacher_region_proj_one, teacher_region_proj_two)).mean(dim = (0, 1))
+        self.last_teacher_region_centers.copy_(teacher_region_logits_avg)
+
+        view_loss = (view_loss_fn_(teacher_view_proj_one, student_view_proj_two) \
+                   + view_loss_fn_(teacher_view_proj_two, student_view_proj_one)) / 2
+
+        # calculate region-level loss
+
+        region_loss = (region_loss_fn_(teacher_region_proj_one, student_region_proj_two, teacher_latent_one, student_latent_two) \
+                     + region_loss_fn_(teacher_region_proj_two, student_region_proj_one, teacher_latent_two, student_latent_one)) / 2
+
+        return (view_loss + region_loss) / 2

vit_pytorch/extractor.py

@@ -4,13 +4,27 @@ from torch import nn
 def exists(val):
     return val is not None
 
+def identity(t):
+    return t
+
+def clone_and_detach(t):
+    return t.clone().detach()
+
+def apply_tuple_or_single(fn, val):
+    if isinstance(val, tuple):
+        return tuple(map(fn, val))
+    return fn(val)
+
 class Extractor(nn.Module):
     def __init__(
         self,
         vit,
         device = None,
+        layer = None,
         layer_name = 'transformer',
-        return_embeddings_only = False
+        layer_save_input = False,
+        return_embeddings_only = False,
+        detach = True
     ):
         super().__init__()
         self.vit = vit
@@ -22,15 +36,24 @@ class Extractor(nn.Module):
         self.ejected = False
         self.device = device
 
+        self.layer = layer
         self.layer_name = layer_name
+        self.layer_save_input = layer_save_input # whether to save input or output of layer
         self.return_embeddings_only = return_embeddings_only
 
-    def _hook(self, _, input, output):
-        self.latents = output.clone().detach()
+        self.detach_fn = clone_and_detach if detach else identity
+
+    def _hook(self, _, inputs, output):
+        layer_output = inputs if self.layer_save_input else output
+        self.latents = apply_tuple_or_single(self.detach_fn, layer_output)
 
     def _register_hook(self):
-        assert hasattr(self.vit, self.layer_name), 'layer whose output to take as embedding not found in vision transformer'
-        layer = getattr(self.vit, self.layer_name)
+        if not exists(self.layer):
+            assert hasattr(self.vit, self.layer_name), 'layer whose output to take as embedding not found in vision transformer'
+            layer = getattr(self.vit, self.layer_name)
+        else:
+            layer = self.layer
+
         handle = layer.register_forward_hook(self._hook)
         self.hooks.append(handle)
         self.hook_registered = True
@@ -59,7 +82,7 @@ class Extractor(nn.Module):
         pred = self.vit(img)
 
         target_device = self.device if exists(self.device) else img.device
-        latents = self.latents.to(target_device)
+        latents = apply_tuple_or_single(lambda t: t.to(target_device), self.latents)
 
         if return_embeddings_only or self.return_embeddings_only:
             return latents

vit_pytorch/learnable_memory_vit.py

@@ -0,0 +1,218 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# controlling freezing of layers
+
+def set_module_requires_grad_(module, requires_grad):
+    for param in module.parameters():
+        param.requires_grad = requires_grad
+
+def freeze_all_layers_(module):
+    set_module_requires_grad_(module, False)
+
+def unfreeze_all_layers_(module):
+    set_module_requires_grad_(module, True)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_q = nn.Linear(dim, inner_dim, bias = False)
+        self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, attn_mask = None, memories = None):
+        x = self.norm(x)
+
+        x_kv = x # input for key / values projection
+
+        if exists(memories):
+            # add memories to key / values if it is passed in
+            memories = repeat(memories, 'n d -> b n d', b = x.shape[0]) if memories.ndim == 2 else memories
+            x_kv = torch.cat((x_kv, memories), dim = 1)
+
+        qkv = (self.to_q(x), *self.to_kv(x_kv).chunk(2, dim = -1))
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        if exists(attn_mask):
+            dots = dots.masked_fill(~attn_mask, -torch.finfo(dots.dtype).max)
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+
+    def forward(self, x, attn_mask = None, memories = None):
+        for ind, (attn, ff) in enumerate(self.layers):
+            layer_memories = memories[ind] if exists(memories) else None
+
+            x = attn(x, attn_mask = attn_mask, memories = layer_memories) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def img_to_tokens(self, img):
+        x = self.to_patch_embedding(img)
+
+        cls_tokens = repeat(self.cls_token, '1 n d -> b n d', b = x.shape[0])
+        x = torch.cat((cls_tokens, x), dim = 1)
+
+        x += self.pos_embedding
+        x = self.dropout(x)
+        return x
+
+    def forward(self, img):
+        x = self.img_to_tokens(img)        
+
+        x = self.transformer(x)
+
+        cls_tokens = x[:, 0]
+        return self.mlp_head(cls_tokens)
+
+# adapter with learnable memories per layer, memory CLS token, and learnable adapter head
+
+class Adapter(nn.Module):
+    def __init__(
+        self,
+        *,
+        vit,
+        num_memories_per_layer = 10,
+        num_classes = 2,   
+    ):
+        super().__init__()
+        assert isinstance(vit, ViT)
+
+        # extract some model variables needed
+
+        dim = vit.cls_token.shape[-1]
+        layers = len(vit.transformer.layers)
+        num_patches = vit.pos_embedding.shape[-2]
+
+        self.vit = vit
+
+        # freeze ViT backbone - only memories will be finetuned
+
+        freeze_all_layers_(vit)
+
+        # learnable parameters
+
+        self.memory_cls_token = nn.Parameter(torch.randn(dim))
+        self.memories_per_layer = nn.Parameter(torch.randn(layers, num_memories_per_layer, dim))
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+        # specialized attention mask to preserve the output of the original ViT
+        # it allows the memory CLS token to attend to all other tokens (and the learnable memory layer tokens), but not vice versa        
+
+        attn_mask = torch.ones((num_patches, num_patches), dtype = torch.bool)
+        attn_mask = F.pad(attn_mask, (1, num_memories_per_layer), value = False)  # main tokens cannot attend to learnable memories per layer
+        attn_mask = F.pad(attn_mask, (0, 0, 1, 0), value = True)                  # memory CLS token can attend to everything
+        self.register_buffer('attn_mask', attn_mask)
+
+    def forward(self, img):
+        b = img.shape[0]
+
+        tokens = self.vit.img_to_tokens(img)
+
+        # add task specific memory tokens
+
+        memory_cls_tokens = repeat(self.memory_cls_token, 'd -> b 1 d', b = b)
+        tokens = torch.cat((memory_cls_tokens, tokens), dim = 1)        
+
+        # pass memories along with image tokens through transformer for attending
+
+        out = self.vit.transformer(tokens, memories = self.memories_per_layer, attn_mask = self.attn_mask)
+
+        # extract memory CLS tokens
+
+        memory_cls_tokens = out[:, 0]
+
+        # pass through task specific adapter head
+
+        return self.mlp_head(memory_cls_tokens)

vit_pytorch/levit.py

@@ -52,6 +52,7 @@ class Attention(nn.Module):
         self.to_v = nn.Sequential(nn.Conv2d(dim, inner_dim_value, 1, bias = False), nn.BatchNorm2d(inner_dim_value))
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
 
         out_batch_norm = nn.BatchNorm2d(dim_out)
         nn.init.zeros_(out_batch_norm.weight)
@@ -70,8 +71,8 @@ class Attention(nn.Module):
         q_range = torch.arange(0, fmap_size, step = (2 if downsample else 1))
         k_range = torch.arange(fmap_size)
 
-        q_pos = torch.stack(torch.meshgrid(q_range, q_range), dim = -1)
-        k_pos = torch.stack(torch.meshgrid(k_range, k_range), dim = -1)
+        q_pos = torch.stack(torch.meshgrid(q_range, q_range, indexing = 'ij'), dim = -1)
+        k_pos = torch.stack(torch.meshgrid(k_range, k_range, indexing = 'ij'), dim = -1)
 
         q_pos, k_pos = map(lambda t: rearrange(t, 'i j c -> (i j) c'), (q_pos, k_pos))
         rel_pos = (q_pos[:, None, ...] - k_pos[None, :, ...]).abs()
@@ -100,6 +101,7 @@ class Attention(nn.Module):
         dots = self.apply_pos_bias(dots)
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h (x y) d -> b (h d) x y', h = h, y = y)

vit_pytorch/local_vit.py

@@ -26,16 +26,6 @@ class ExcludeCLS(nn.Module):
         x = self.fn(x, **kwargs)
         return torch.cat((cls_token, x), dim = 1)
 
-# prenorm
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 # feed forward related classes
 
 class DepthWiseConv2d(nn.Module):
@@ -52,6 +42,7 @@ class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Conv2d(dim, hidden_dim, 1),
             nn.Hardswish(),
             DepthWiseConv2d(hidden_dim, hidden_dim, 3, padding = 1),
@@ -77,7 +68,9 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.to_out = nn.Sequential(
@@ -87,12 +80,15 @@ class Attention(nn.Module):
 
     def forward(self, x):
         b, n, _, h = *x.shape, self.heads
+
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
 
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
@@ -104,8 +100,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                Residual(PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout))),
-                ExcludeCLS(Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))))
+                Residual(Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                ExcludeCLS(Residual(FeedForward(dim, mlp_dim, dropout = dropout)))
             ]))
     def forward(self, x):
         for attn, ff in self.layers:
@@ -124,7 +120,9 @@ class LocalViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/mae.py

@@ -24,11 +24,14 @@ class MAE(nn.Module):
 
         self.encoder = encoder
         num_patches, encoder_dim = encoder.pos_embedding.shape[-2:]
-        self.to_patch, self.patch_to_emb = encoder.to_patch_embedding[:2]
-        pixel_values_per_patch = self.patch_to_emb.weight.shape[-1]
+
+        self.to_patch = encoder.to_patch_embedding[0]
+        self.patch_to_emb = nn.Sequential(*encoder.to_patch_embedding[1:])
+
+        pixel_values_per_patch = encoder.to_patch_embedding[2].weight.shape[-1]
 
         # decoder parameters
-
+        self.decoder_dim = decoder_dim
         self.enc_to_dec = nn.Linear(encoder_dim, decoder_dim) if encoder_dim != decoder_dim else nn.Identity()
         self.mask_token = nn.Parameter(torch.randn(decoder_dim))
         self.decoder = Transformer(dim = decoder_dim, depth = decoder_depth, heads = decoder_heads, dim_head = decoder_dim_head, mlp_dim = decoder_dim * 4)
@@ -46,7 +49,10 @@ class MAE(nn.Module):
         # patch to encoder tokens and add positions
 
         tokens = self.patch_to_emb(patches)
-        tokens = tokens + self.encoder.pos_embedding[:, 1:(num_patches + 1)]
+        if self.encoder.pool == "cls":
+            tokens += self.encoder.pos_embedding[:, 1:(num_patches + 1)]
+        elif self.encoder.pool == "mean":
+            tokens += self.encoder.pos_embedding.to(device, dtype=tokens.dtype) 
 
         # calculate of patches needed to be masked, and get random indices, dividing it up for mask vs unmasked
 
@@ -71,19 +77,25 @@ class MAE(nn.Module):
 
         decoder_tokens = self.enc_to_dec(encoded_tokens)
 
+        # reapply decoder position embedding to unmasked tokens
+
+        unmasked_decoder_tokens = decoder_tokens + self.decoder_pos_emb(unmasked_indices)
+
         # repeat mask tokens for number of masked, and add the positions using the masked indices derived above
 
         mask_tokens = repeat(self.mask_token, 'd -> b n d', b = batch, n = num_masked)
         mask_tokens = mask_tokens + self.decoder_pos_emb(masked_indices)
 
         # concat the masked tokens to the decoder tokens and attend with decoder
-
-        decoder_tokens = torch.cat((mask_tokens, decoder_tokens), dim = 1)
+        
+        decoder_tokens = torch.zeros(batch, num_patches, self.decoder_dim, device=device)
+        decoder_tokens[batch_range, unmasked_indices] = unmasked_decoder_tokens
+        decoder_tokens[batch_range, masked_indices] = mask_tokens
         decoded_tokens = self.decoder(decoder_tokens)
 
         # splice out the mask tokens and project to pixel values
 
-        mask_tokens = decoded_tokens[:, :num_masked]
+        mask_tokens = decoded_tokens[batch_range, masked_indices]
         pred_pixel_values = self.to_pixels(mask_tokens)
 
         # calculate reconstruction loss

vit_pytorch/max_vit.py

@@ -0,0 +1,291 @@
+from functools import partial
+
+import torch
+from torch import nn, einsum
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+class Residual(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.fn = fn
+
+    def forward(self, x):
+        return self.fn(x) + x
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mult = 4, dropout = 0.):
+        super().__init__()
+        inner_dim = int(dim * mult)
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, inner_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# MBConv
+
+class SqueezeExcitation(nn.Module):
+    def __init__(self, dim, shrinkage_rate = 0.25):
+        super().__init__()
+        hidden_dim = int(dim * shrinkage_rate)
+
+        self.gate = nn.Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(dim, hidden_dim, bias = False),
+            nn.SiLU(),
+            nn.Linear(hidden_dim, dim, bias = False),
+            nn.Sigmoid(),
+            Rearrange('b c -> b c 1 1')
+        )
+
+    def forward(self, x):
+        return x * self.gate(x)
+
+
+class MBConvResidual(nn.Module):
+    def __init__(self, fn, dropout = 0.):
+        super().__init__()
+        self.fn = fn
+        self.dropsample = Dropsample(dropout)
+
+    def forward(self, x):
+        out = self.fn(x)
+        out = self.dropsample(out)
+        return out + x
+
+class Dropsample(nn.Module):
+    def __init__(self, prob = 0):
+        super().__init__()
+        self.prob = prob
+  
+    def forward(self, x):
+        device = x.device
+
+        if self.prob == 0. or (not self.training):
+            return x
+
+        keep_mask = torch.FloatTensor((x.shape[0], 1, 1, 1), device = device).uniform_() > self.prob
+        return x * keep_mask / (1 - self.prob)
+
+def MBConv(
+    dim_in,
+    dim_out,
+    *,
+    downsample,
+    expansion_rate = 4,
+    shrinkage_rate = 0.25,
+    dropout = 0.
+):
+    hidden_dim = int(expansion_rate * dim_out)
+    stride = 2 if downsample else 1
+
+    net = nn.Sequential(
+        nn.Conv2d(dim_in, hidden_dim, 1),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        nn.Conv2d(hidden_dim, hidden_dim, 3, stride = stride, padding = 1, groups = hidden_dim),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        SqueezeExcitation(hidden_dim, shrinkage_rate = shrinkage_rate),
+        nn.Conv2d(hidden_dim, dim_out, 1),
+        nn.BatchNorm2d(dim_out)
+    )
+
+    if dim_in == dim_out and not downsample:
+        net = MBConvResidual(net, dropout = dropout)
+
+    return net
+
+# attention related classes
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        dim_head = 32,
+        dropout = 0.,
+        window_size = 7
+    ):
+        super().__init__()
+        assert (dim % dim_head) == 0, 'dimension should be divisible by dimension per head'
+
+        self.heads = dim // dim_head
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.to_qkv = nn.Linear(dim, dim * 3, bias = False)
+
+        self.attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_out = nn.Sequential(
+            nn.Linear(dim, dim, bias = False),
+            nn.Dropout(dropout)
+        )
+
+        # relative positional bias
+
+        self.rel_pos_bias = nn.Embedding((2 * window_size - 1) ** 2, self.heads)
+
+        pos = torch.arange(window_size)
+        grid = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
+        grid = rearrange(grid, 'c i j -> (i j) c')
+        rel_pos = rearrange(grid, 'i ... -> i 1 ...') - rearrange(grid, 'j ... -> 1 j ...')
+        rel_pos += window_size - 1
+        rel_pos_indices = (rel_pos * torch.tensor([2 * window_size - 1, 1])).sum(dim = -1)
+
+        self.register_buffer('rel_pos_indices', rel_pos_indices, persistent = False)
+
+    def forward(self, x):
+        batch, height, width, window_height, window_width, _, device, h = *x.shape, x.device, self.heads
+
+        x = self.norm(x)
+
+        # flatten
+
+        x = rearrange(x, 'b x y w1 w2 d -> (b x y) (w1 w2) d')
+
+        # project for queries, keys, values
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = -1)
+
+        # split heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), (q, k, v))
+
+        # scale
+
+        q = q * self.scale
+
+        # sim
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add positional bias
+
+        bias = self.rel_pos_bias(self.rel_pos_indices)
+        sim = sim + rearrange(bias, 'i j h -> h i j')
+
+        # attention
+
+        attn = self.attend(sim)
+
+        # aggregate
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+
+        # merge heads
+
+        out = rearrange(out, 'b h (w1 w2) d -> b w1 w2 (h d)', w1 = window_height, w2 = window_width)
+
+        # combine heads out
+
+        out = self.to_out(out)
+        return rearrange(out, '(b x y) ... -> b x y ...', x = height, y = width)
+
+class MaxViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        dim_head = 32,
+        dim_conv_stem = None,
+        window_size = 7,
+        mbconv_expansion_rate = 4,
+        mbconv_shrinkage_rate = 0.25,
+        dropout = 0.1,
+        channels = 3
+    ):
+        super().__init__()
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+
+        # convolutional stem
+
+        dim_conv_stem = default(dim_conv_stem, dim)
+
+        self.conv_stem = nn.Sequential(
+            nn.Conv2d(channels, dim_conv_stem, 3, stride = 2, padding = 1),
+            nn.Conv2d(dim_conv_stem, dim_conv_stem, 3, padding = 1)
+        )
+
+        # variables
+
+        num_stages = len(depth)
+
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+        dims = (dim_conv_stem, *dims)
+        dim_pairs = tuple(zip(dims[:-1], dims[1:]))
+
+        self.layers = nn.ModuleList([])
+
+        # shorthand for window size for efficient block - grid like attention
+
+        w = window_size
+
+        # iterate through stages
+
+        for ind, ((layer_dim_in, layer_dim), layer_depth) in enumerate(zip(dim_pairs, depth)):
+            for stage_ind in range(layer_depth):
+                is_first = stage_ind == 0
+                stage_dim_in = layer_dim_in if is_first else layer_dim
+
+                block = nn.Sequential(
+                    MBConv(
+                        stage_dim_in,
+                        layer_dim,
+                        downsample = is_first,
+                        expansion_rate = mbconv_expansion_rate,
+                        shrinkage_rate = mbconv_shrinkage_rate
+                    ),
+                    Rearrange('b d (x w1) (y w2) -> b x y w1 w2 d', w1 = w, w2 = w),  # block-like attention
+                    Residual(layer_dim, Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = w)),
+                    Residual(layer_dim, FeedForward(dim = layer_dim, dropout = dropout)),
+                    Rearrange('b x y w1 w2 d -> b d (x w1) (y w2)'),
+
+                    Rearrange('b d (w1 x) (w2 y) -> b x y w1 w2 d', w1 = w, w2 = w),  # grid-like attention
+                    Residual(layer_dim, Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = w)),
+                    Residual(layer_dim, FeedForward(dim = layer_dim, dropout = dropout)),
+                    Rearrange('b x y w1 w2 d -> b d (w1 x) (w2 y)'),
+                )
+
+                self.layers.append(block)
+
+        # mlp head out
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, x):
+        x = self.conv_stem(x)
+
+        for stage in self.layers:
+            x = stage(x)
+
+        return self.mlp_head(x)

vit_pytorch/max_vit_with_registers.py

@@ -0,0 +1,339 @@
+from functools import partial
+
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+from torch.nn import Module, ModuleList, Sequential
+
+from einops import rearrange, repeat, reduce, pack, unpack
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def pack_one(x, pattern):
+    return pack([x], pattern)
+
+def unpack_one(x, ps, pattern):
+    return unpack(x, ps, pattern)[0]
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+def FeedForward(dim, mult = 4, dropout = 0.):
+    inner_dim = int(dim * mult)
+    return Sequential(
+        nn.LayerNorm(dim),
+        nn.Linear(dim, inner_dim),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Linear(inner_dim, dim),
+        nn.Dropout(dropout)
+    )
+
+# MBConv
+
+class SqueezeExcitation(Module):
+    def __init__(self, dim, shrinkage_rate = 0.25):
+        super().__init__()
+        hidden_dim = int(dim * shrinkage_rate)
+
+        self.gate = Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(dim, hidden_dim, bias = False),
+            nn.SiLU(),
+            nn.Linear(hidden_dim, dim, bias = False),
+            nn.Sigmoid(),
+            Rearrange('b c -> b c 1 1')
+        )
+
+    def forward(self, x):
+        return x * self.gate(x)
+
+class MBConvResidual(Module):
+    def __init__(self, fn, dropout = 0.):
+        super().__init__()
+        self.fn = fn
+        self.dropsample = Dropsample(dropout)
+
+    def forward(self, x):
+        out = self.fn(x)
+        out = self.dropsample(out)
+        return out + x
+
+class Dropsample(Module):
+    def __init__(self, prob = 0):
+        super().__init__()
+        self.prob = prob
+  
+    def forward(self, x):
+        device = x.device
+
+        if self.prob == 0. or (not self.training):
+            return x
+
+        keep_mask = torch.FloatTensor((x.shape[0], 1, 1, 1), device = device).uniform_() > self.prob
+        return x * keep_mask / (1 - self.prob)
+
+def MBConv(
+    dim_in,
+    dim_out,
+    *,
+    downsample,
+    expansion_rate = 4,
+    shrinkage_rate = 0.25,
+    dropout = 0.
+):
+    hidden_dim = int(expansion_rate * dim_out)
+    stride = 2 if downsample else 1
+
+    net = Sequential(
+        nn.Conv2d(dim_in, hidden_dim, 1),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        nn.Conv2d(hidden_dim, hidden_dim, 3, stride = stride, padding = 1, groups = hidden_dim),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        SqueezeExcitation(hidden_dim, shrinkage_rate = shrinkage_rate),
+        nn.Conv2d(hidden_dim, dim_out, 1),
+        nn.BatchNorm2d(dim_out)
+    )
+
+    if dim_in == dim_out and not downsample:
+        net = MBConvResidual(net, dropout = dropout)
+
+    return net
+
+# attention related classes
+
+class Attention(Module):
+    def __init__(
+        self,
+        dim,
+        dim_head = 32,
+        dropout = 0.,
+        window_size = 7
+    ):
+        super().__init__()
+        assert (dim % dim_head) == 0, 'dimension should be divisible by dimension per head'
+
+        self.heads = dim // dim_head
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.to_qkv = nn.Linear(dim, dim * 3, bias = False)
+
+        self.attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_out = nn.Sequential(
+            nn.Linear(dim, dim, bias = False),
+            nn.Dropout(dropout)
+        )
+
+        # relative positional bias
+
+        self.rel_pos_bias = nn.Embedding((2 * window_size - 1) ** 2, self.heads)
+
+        pos = torch.arange(window_size)
+        grid = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
+        grid = rearrange(grid, 'c i j -> (i j) c')
+        rel_pos = rearrange(grid, 'i ... -> i 1 ...') - rearrange(grid, 'j ... -> 1 j ...')
+        rel_pos += window_size - 1
+        rel_pos_indices = (rel_pos * torch.tensor([2 * window_size - 1, 1])).sum(dim = -1)
+
+        self.register_buffer('rel_pos_indices', rel_pos_indices, persistent = False)
+
+    def forward(self, x):
+        device, h = x.device, self.heads
+
+        x = self.norm(x)
+
+        # project for queries, keys, values
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = -1)
+
+        # split heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), (q, k, v))
+
+        # scale
+
+        q = q * self.scale
+
+        # sim
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add positional bias
+
+        bias = self.rel_pos_bias(self.rel_pos_indices)
+        bias = rearrange(bias, 'i j h -> h i j')
+
+        num_registers = sim.shape[-1] - bias.shape[-1]
+        bias = F.pad(bias, (num_registers, 0, num_registers, 0), value = 0.)
+
+        sim = sim + bias
+
+        # attention
+
+        attn = self.attend(sim)
+
+        # aggregate
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+
+        # combine heads out
+
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class MaxViT(Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        dim_head = 32,
+        dim_conv_stem = None,
+        window_size = 7,
+        mbconv_expansion_rate = 4,
+        mbconv_shrinkage_rate = 0.25,
+        dropout = 0.1,
+        channels = 3,
+        num_register_tokens = 4
+    ):
+        super().__init__()
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+
+        # convolutional stem
+
+        dim_conv_stem = default(dim_conv_stem, dim)
+
+        self.conv_stem = Sequential(
+            nn.Conv2d(channels, dim_conv_stem, 3, stride = 2, padding = 1),
+            nn.Conv2d(dim_conv_stem, dim_conv_stem, 3, padding = 1)
+        )
+
+        # variables
+
+        num_stages = len(depth)
+
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+        dims = (dim_conv_stem, *dims)
+        dim_pairs = tuple(zip(dims[:-1], dims[1:]))
+
+        self.layers = nn.ModuleList([])
+
+        # window size
+
+        self.window_size = window_size
+
+        self.register_tokens = nn.ParameterList([])
+
+        # iterate through stages
+
+        for ind, ((layer_dim_in, layer_dim), layer_depth) in enumerate(zip(dim_pairs, depth)):
+            for stage_ind in range(layer_depth):
+                is_first = stage_ind == 0
+                stage_dim_in = layer_dim_in if is_first else layer_dim
+
+                conv = MBConv(
+                    stage_dim_in,
+                    layer_dim,
+                    downsample = is_first,
+                    expansion_rate = mbconv_expansion_rate,
+                    shrinkage_rate = mbconv_shrinkage_rate
+                )
+
+                block_attn = Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = window_size)
+                block_ff = FeedForward(dim = layer_dim, dropout = dropout)
+
+                grid_attn = Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = window_size)
+                grid_ff = FeedForward(dim = layer_dim, dropout = dropout)
+
+                register_tokens = nn.Parameter(torch.randn(num_register_tokens, layer_dim))
+
+                self.layers.append(ModuleList([
+                    conv,
+                    ModuleList([block_attn, block_ff]),
+                    ModuleList([grid_attn, grid_ff])
+                ]))
+
+                self.register_tokens.append(register_tokens)
+
+        # mlp head out
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, x):
+        b, w = x.shape[0], self.window_size
+
+        x = self.conv_stem(x)
+
+        for (conv, (block_attn, block_ff), (grid_attn, grid_ff)), register_tokens in zip(self.layers, self.register_tokens):
+            x = conv(x)
+
+            # block-like attention
+
+            x = rearrange(x, 'b d (x w1) (y w2) -> b x y w1 w2 d', w1 = w, w2 = w)
+
+            # prepare register tokens
+
+            r = repeat(register_tokens, 'n d -> b x y n d', b = b, x = x.shape[1],y = x.shape[2])
+            r, register_batch_ps = pack_one(r, '* n d')
+
+            x, window_ps = pack_one(x, 'b x y * d')
+            x, batch_ps  = pack_one(x, '* n d')
+            x, register_ps = pack([r, x], 'b * d')
+
+            x = block_attn(x) + x
+            x = block_ff(x) + x
+
+            r, x = unpack(x, register_ps, 'b * d')
+
+            x = unpack_one(x, batch_ps, '* n d')
+            x = unpack_one(x, window_ps, 'b x y * d')
+            x = rearrange(x, 'b x y w1 w2 d -> b d (x w1) (y w2)')
+
+            r = unpack_one(r, register_batch_ps, '* n d')
+
+            # grid-like attention
+
+            x = rearrange(x, 'b d (w1 x) (w2 y) -> b x y w1 w2 d', w1 = w, w2 = w)
+
+            # prepare register tokens
+
+            r = reduce(r, 'b x y n d -> b n d', 'mean')
+            r = repeat(r, 'b n d -> b x y n d', x = x.shape[1], y = x.shape[2])
+            r, register_batch_ps = pack_one(r, '* n d')
+
+            x, window_ps = pack_one(x, 'b x y * d')
+            x, batch_ps  = pack_one(x, '* n d')
+            x, register_ps = pack([r, x], 'b * d')
+
+            x = grid_attn(x) + x
+
+            r, x = unpack(x, register_ps, 'b * d')
+
+            x = grid_ff(x) + x
+
+            x = unpack_one(x, batch_ps, '* n d')
+            x = unpack_one(x, window_ps, 'b x y * d')
+            x = rearrange(x, 'b x y w1 w2 d -> b d (w1 x) (w2 y)')
+
+        return self.mlp_head(x)

vit_pytorch/mobile_vit.py

@@ -1,53 +1,32 @@
-"""
-An implementation of MobileViT Model as defined in:
-MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
-Arxiv: https://arxiv.org/abs/2110.02178
-Origin Code: https://github.com/murufeng/awesome_lightweight_networks
-"""
-
 import torch
 import torch.nn as nn
 
 from einops import rearrange
 from einops.layers.torch import Reduce
 
-def _make_divisible(v, divisor, min_value=None):
-    if min_value is None:
-        min_value = divisor
-    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
-    if new_v < 0.9 * v:
-        new_v += divisor
-    return new_v
-
-
-def conv_bn_relu(inp, oup, kernel, stride=1):
-    return nn.Sequential(
-        nn.Conv2d(inp, oup, kernel_size=kernel, stride=stride, padding=1, bias=False),
-        nn.BatchNorm2d(oup),
-        nn.ReLU6(inplace=True)
-    )
-
+# helpers
 
 def conv_1x1_bn(inp, oup):
     return nn.Sequential(
         nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
         nn.BatchNorm2d(oup),
-        nn.ReLU6(inplace=True)
+        nn.SiLU()
     )
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
+def conv_nxn_bn(inp, oup, kernel_size=3, stride=1):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, kernel_size, stride, 1, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.SiLU()
+    )
 
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
+# classes
 
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout=0.):
         super().__init__()
-        self.ffn = nn.Sequential(
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.SiLU(),
             nn.Dropout(dropout),
@@ -56,8 +35,7 @@ class FeedForward(nn.Module):
         )
 
     def forward(self, x):
-        return self.ffn(x)
-
+        return self.net(x)
 
 class Attention(nn.Module):
     def __init__(self, dim, heads=8, dim_head=64, dropout=0.):
@@ -66,7 +44,10 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim=-1)
+        self.dropout = nn.Dropout(dropout)
+
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias=False)
 
         self.to_out = nn.Sequential(
@@ -75,24 +56,33 @@ class Attention(nn.Module):
         )
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim=-1)
+
         q, k, v = map(lambda t: rearrange(t, 'b p n (h d) -> b p h n d', h=self.heads), qkv)
 
         dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
         attn = self.attend(dots)
+        attn = self.dropout(attn)
+
         out = torch.matmul(attn, v)
         out = rearrange(out, 'b p h n d -> b p n (h d)')
         return self.to_out(out)
 
-
 class Transformer(nn.Module):
-    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+    """Transformer block described in ViT.
+    Paper: https://arxiv.org/abs/2010.11929
+    Based on: https://github.com/lucidrains/vit-pytorch
+    """
+
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout=0.):
         super().__init__()
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads, dim_head, dropout),
+                FeedForward(dim, mlp_dim, dropout)
             ]))
 
     def forward(self, x):
@@ -102,17 +92,24 @@ class Transformer(nn.Module):
         return x
 
 class MV2Block(nn.Module):
-    def __init__(self, inp, oup, stride=1, expand_ratio=4):
-        super(MV2Block, self).__init__()
+    """MV2 block described in MobileNetV2.
+    Paper: https://arxiv.org/pdf/1801.04381
+    Based on: https://github.com/tonylins/pytorch-mobilenet-v2
+    """
+
+    def __init__(self, inp, oup, stride=1, expansion=4):
+        super().__init__()
+        self.stride = stride
         assert stride in [1, 2]
 
-        hidden_dim = round(inp * expand_ratio)
-        self.identity = stride == 1 and inp == oup
+        hidden_dim = int(inp * expansion)
+        self.use_res_connect = self.stride == 1 and inp == oup
 
-        if expand_ratio == 1:
+        if expansion == 1:
             self.conv = nn.Sequential(
                 # dw
-                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride,
+                          1, groups=hidden_dim, bias=False),
                 nn.BatchNorm2d(hidden_dim),
                 nn.SiLU(),
                 # pw-linear
@@ -126,7 +123,8 @@ class MV2Block(nn.Module):
                 nn.BatchNorm2d(hidden_dim),
                 nn.SiLU(),
                 # dw
-                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride,
+                          1, groups=hidden_dim, bias=False),
                 nn.BatchNorm2d(hidden_dim),
                 nn.SiLU(),
                 # pw-linear
@@ -136,8 +134,7 @@ class MV2Block(nn.Module):
 
     def forward(self, x):
         out = self.conv(x)
-
-        if self.identity:
+        if self.use_res_connect:
             out = out + x
         return out
 
@@ -146,13 +143,13 @@ class MobileViTBlock(nn.Module):
         super().__init__()
         self.ph, self.pw = patch_size
 
-        self.conv1 = conv_bn_relu(channel, channel, kernel_size)
+        self.conv1 = conv_nxn_bn(channel, channel, kernel_size)
         self.conv2 = conv_1x1_bn(channel, dim)
 
-        self.transformer = Transformer(dim, depth, 1, 32, mlp_dim, dropout)
+        self.transformer = Transformer(dim, depth, 4, 8, mlp_dim, dropout)
 
         self.conv3 = conv_1x1_bn(dim, channel)
-        self.conv4 = conv_bn_relu(2 * channel, channel, kernel_size)
+        self.conv4 = conv_nxn_bn(2 * channel, channel, kernel_size)
 
     def forward(self, x):
         y = x.clone()
@@ -164,8 +161,8 @@ class MobileViTBlock(nn.Module):
         # Global representations
         _, _, h, w = x.shape
         x = rearrange(x, 'b d (h ph) (w pw) -> b (ph pw) (h w) d', ph=self.ph, pw=self.pw)
-        x = self.transformer(x)
-        x = rearrange(x, 'b (ph pw) (h w) d -> b d (h ph) (w pw)', h=h // self.ph, w=w // self.pw, ph=self.ph, pw=self.pw)
+        x = self.transformer(x)        
+        x = rearrange(x, 'b (ph pw) (h w) d -> b d (h ph) (w pw)', h=h//self.ph, w=w//self.pw, ph=self.ph, pw=self.pw)
 
         # Fusion
         x = self.conv3(x)
@@ -173,18 +170,22 @@ class MobileViTBlock(nn.Module):
         x = self.conv4(x)
         return x
 
-
 class MobileViT(nn.Module):
+    """MobileViT.
+    Paper: https://arxiv.org/abs/2110.02178
+    Based on: https://github.com/chinhsuanwu/mobilevit-pytorch
+    """
+
     def __init__(
         self,
         image_size,
         dims,
         channels,
         num_classes,
-        expansion = 4,
-        kernel_size = 3,
-        patch_size = (2, 2),
-        depths = (2, 4, 3)
+        expansion=4,
+        kernel_size=3,
+        patch_size=(2, 2),
+        depths=(2, 4, 3)
     ):
         super().__init__()
         assert len(dims) == 3, 'dims must be a tuple of 3'
@@ -196,28 +197,31 @@ class MobileViT(nn.Module):
 
         init_dim, *_, last_dim = channels
 
-        self.conv1 = conv_bn_relu(3, init_dim, kernel=3, stride=2)
+        self.conv1 = conv_nxn_bn(3, init_dim, stride=2)
 
         self.stem = nn.ModuleList([])
         self.stem.append(MV2Block(channels[0], channels[1], 1, expansion))
         self.stem.append(MV2Block(channels[1], channels[2], 2, expansion))
         self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
         self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
-    
+
         self.trunk = nn.ModuleList([])
         self.trunk.append(nn.ModuleList([
             MV2Block(channels[3], channels[4], 2, expansion),
-            MobileViTBlock(dims[0], depths[0], channels[5], kernel_size, patch_size, int(dims[0] * 2))
+            MobileViTBlock(dims[0], depths[0], channels[5],
+                           kernel_size, patch_size, int(dims[0] * 2))
         ]))
 
         self.trunk.append(nn.ModuleList([
             MV2Block(channels[5], channels[6], 2, expansion),
-            MobileViTBlock(dims[1], depths[1], channels[7], kernel_size, patch_size, int(dims[1] * 4))
+            MobileViTBlock(dims[1], depths[1], channels[7],
+                           kernel_size, patch_size, int(dims[1] * 4))
         ]))
 
         self.trunk.append(nn.ModuleList([
             MV2Block(channels[7], channels[8], 2, expansion),
-            MobileViTBlock(dims[2], depths[2], channels[9], kernel_size, patch_size, int(dims[2] * 4))
+            MobileViTBlock(dims[2], depths[2], channels[9],
+                           kernel_size, patch_size, int(dims[2] * 4))
         ]))
 
         self.to_logits = nn.Sequential(

vit_pytorch/mp3.py

@@ -0,0 +1,186 @@
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# positional embedding
+
+def posemb_sincos_2d(patches, temperature = 10000, dtype = torch.float32):
+    _, h, w, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    y, x = torch.meshgrid(torch.arange(h, device = device), torch.arange(w, device = device), indexing = 'ij')
+    assert (dim % 4) == 0, 'feature dimension must be multiple of 4 for sincos emb'
+    omega = torch.arange(dim // 4, device = device) / (dim // 4 - 1)
+    omega = 1. / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :]
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim = 1)
+    return pe.type(dtype)
+
+# feedforward
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# (cross)attention
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.norm = nn.LayerNorm(dim)
+
+        self.to_q = nn.Linear(dim, inner_dim, bias = False)
+        self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, context = None):
+        b, n, _, h = *x.shape, self.heads
+
+        x = self.norm(x)
+
+        context = self.norm(context) if exists(context) else x
+
+        qkv = (self.to_q(x), *self.to_kv(context).chunk(2, dim = -1))
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
+
+        dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+    def forward(self, x, context = None):
+        for attn, ff in self.layers:
+            x = attn(x, context = context) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, num_classes, image_size, patch_size, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.dim = dim
+        self.num_patches = num_patches
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b h w (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        *_, h, w, dtype = *img.shape, img.dtype
+
+        x = self.to_patch_embedding(img)
+        pe = posemb_sincos_2d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)
+
+# Masked Position Prediction Pre-Training
+
+class MP3(nn.Module):
+    def __init__(self, vit: ViT, masking_ratio):
+        super().__init__()
+        self.vit = vit
+
+        assert masking_ratio > 0 and masking_ratio < 1, 'masking ratio must be kept between 0 and 1'
+        self.masking_ratio = masking_ratio
+
+        dim = vit.dim
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, vit.num_patches)
+        )
+
+    def forward(self, img):
+        device = img.device
+        tokens = self.vit.to_patch_embedding(img)
+        tokens = rearrange(tokens, 'b ... d -> b (...) d')
+
+        batch, num_patches, *_ = tokens.shape
+
+        # Masking
+        num_masked = int(self.masking_ratio * num_patches)
+        rand_indices = torch.rand(batch, num_patches, device = device).argsort(dim = -1)
+        masked_indices, unmasked_indices = rand_indices[:, :num_masked], rand_indices[:, num_masked:]
+
+        batch_range = torch.arange(batch, device = device)[:, None]
+        tokens_unmasked = tokens[batch_range, unmasked_indices]
+
+        attended_tokens = self.vit.transformer(tokens, tokens_unmasked)
+        logits = rearrange(self.mlp_head(attended_tokens), 'b n d -> (b n) d')
+        
+        # Define labels
+        labels = repeat(torch.arange(num_patches, device = device), 'n -> (b n)', b = batch)
+        loss = F.cross_entropy(logits, labels)
+
+        return loss

vit_pytorch/mpp.py

@@ -96,6 +96,9 @@ class MPP(nn.Module):
         self.loss = MPPLoss(patch_size, channels, output_channel_bits,
                             max_pixel_val, mean, std)
 
+        # extract patching function
+        self.patch_to_emb = nn.Sequential(transformer.to_patch_embedding[1:])
+
         # output transformation
         self.to_bits = nn.Linear(dim, 2**(output_channel_bits * channels))
 
@@ -151,7 +154,7 @@ class MPP(nn.Module):
         masked_input[bool_mask_replace] = self.mask_token
 
         # linear embedding of patches
-        masked_input = transformer.to_patch_embedding[-1](masked_input)
+        masked_input = self.patch_to_emb(masked_input)
 
         # add cls token to input sequence
         b, n, _ = masked_input.shape

vit_pytorch/na_vit.py

@@ -0,0 +1,389 @@
+from functools import partial
+from typing import List, Union
+
+import torch
+import torch.nn.functional as F
+from torch import nn, Tensor
+from torch.nn.utils.rnn import pad_sequence as orig_pad_sequence
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def always(val):
+    return lambda *args: val
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def divisible_by(numer, denom):
+    return (numer % denom) == 0
+
+# auto grouping images
+
+def group_images_by_max_seq_len(
+    images: List[Tensor],
+    patch_size: int,
+    calc_token_dropout = None,
+    max_seq_len = 2048
+
+) -> List[List[Tensor]]:
+
+    calc_token_dropout = default(calc_token_dropout, always(0.))
+
+    groups = []
+    group = []
+    seq_len = 0
+
+    if isinstance(calc_token_dropout, (float, int)):
+        calc_token_dropout = always(calc_token_dropout)
+
+    for image in images:
+        assert isinstance(image, Tensor)
+
+        image_dims = image.shape[-2:]
+        ph, pw = map(lambda t: t // patch_size, image_dims)
+
+        image_seq_len = (ph * pw)
+        image_seq_len = int(image_seq_len * (1 - calc_token_dropout(*image_dims)))
+
+        assert image_seq_len <= max_seq_len, f'image with dimensions {image_dims} exceeds maximum sequence length'
+
+        if (seq_len + image_seq_len) > max_seq_len:
+            groups.append(group)
+            group = []
+            seq_len = 0
+
+        group.append(image)
+        seq_len += image_seq_len
+
+    if len(group) > 0:
+        groups.append(group)
+
+    return groups
+
+# normalization
+# they use layernorm without bias, something that pytorch does not offer
+
+class LayerNorm(nn.Module):
+    def __init__(self, dim):
+        super().__init__()
+        self.gamma = nn.Parameter(torch.ones(dim))
+        self.register_buffer('beta', torch.zeros(dim))
+
+    def forward(self, x):
+        return F.layer_norm(x, x.shape[-1:], self.gamma, self.beta)
+
+# they use a query-key normalization that is equivalent to rms norm (no mean-centering, learned gamma), from vit 22B paper
+
+class RMSNorm(nn.Module):
+    def __init__(self, heads, dim):
+        super().__init__()
+        self.scale = dim ** 0.5
+        self.gamma = nn.Parameter(torch.ones(heads, 1, dim))
+
+    def forward(self, x):
+        normed = F.normalize(x, dim = -1)
+        return normed * self.scale * self.gamma
+
+# feedforward
+
+def FeedForward(dim, hidden_dim, dropout = 0.):
+    return nn.Sequential(
+        LayerNorm(dim),
+        nn.Linear(dim, hidden_dim),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Linear(hidden_dim, dim),
+        nn.Dropout(dropout)
+    )
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.norm = LayerNorm(dim)
+
+        self.q_norm = RMSNorm(heads, dim_head)
+        self.k_norm = RMSNorm(heads, dim_head)
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_q = nn.Linear(dim, inner_dim, bias = False)
+        self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim, bias = False),
+            nn.Dropout(dropout)
+        )
+
+    def forward(
+        self,
+        x,
+        context = None,
+        mask = None,
+        attn_mask = None
+    ):
+        x = self.norm(x)
+        kv_input = default(context, x)
+
+        qkv = (self.to_q(x), *self.to_kv(kv_input).chunk(2, dim = -1))
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        q = self.q_norm(q)
+        k = self.k_norm(k)
+
+        dots = torch.matmul(q, k.transpose(-1, -2))
+
+        if exists(mask):
+            mask = rearrange(mask, 'b j -> b 1 1 j')
+            dots = dots.masked_fill(~mask, -torch.finfo(dots.dtype).max)
+
+        if exists(attn_mask):
+            dots = dots.masked_fill(~attn_mask, -torch.finfo(dots.dtype).max)
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+
+        self.norm = LayerNorm(dim)
+
+    def forward(
+        self,
+        x,
+        mask = None,
+        attn_mask = None
+    ):
+        for attn, ff in self.layers:
+            x = attn(x, mask = mask, attn_mask = attn_mask) + x
+            x = ff(x) + x
+
+        return self.norm(x)
+
+class NaViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., token_dropout_prob = None):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+
+        # what percent of tokens to dropout
+        # if int or float given, then assume constant dropout prob
+        # otherwise accept a callback that in turn calculates dropout prob from height and width
+
+        self.calc_token_dropout = None
+
+        if callable(token_dropout_prob):
+            self.calc_token_dropout = token_dropout_prob
+
+        elif isinstance(token_dropout_prob, (float, int)):
+            assert 0. < token_dropout_prob < 1.
+            token_dropout_prob = float(token_dropout_prob)
+            self.calc_token_dropout = lambda height, width: token_dropout_prob
+
+        # calculate patching related stuff
+
+        assert divisible_by(image_height, patch_size) and divisible_by(image_width, patch_size), 'Image dimensions must be divisible by the patch size.'
+
+        patch_height_dim, patch_width_dim = (image_height // patch_size), (image_width // patch_size)
+        patch_dim = channels * (patch_size ** 2)
+
+        self.channels = channels
+        self.patch_size = patch_size
+
+        self.to_patch_embedding = nn.Sequential(
+            LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            LayerNorm(dim),
+        )
+
+        self.pos_embed_height = nn.Parameter(torch.randn(patch_height_dim, dim))
+        self.pos_embed_width = nn.Parameter(torch.randn(patch_width_dim, dim))
+
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        # final attention pooling queries
+
+        self.attn_pool_queries = nn.Parameter(torch.randn(dim))
+        self.attn_pool = Attention(dim = dim, dim_head = dim_head, heads = heads)
+
+        # output to logits
+
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            LayerNorm(dim),
+            nn.Linear(dim, num_classes, bias = False)
+        )
+
+    @property
+    def device(self):
+        return next(self.parameters()).device
+
+    def forward(
+        self,
+        batched_images: Union[List[Tensor], List[List[Tensor]]], # assume different resolution images already grouped correctly
+        group_images = False,
+        group_max_seq_len = 2048
+    ):
+        p, c, device, has_token_dropout = self.patch_size, self.channels, self.device, exists(self.calc_token_dropout)
+
+        arange = partial(torch.arange, device = device)
+        pad_sequence = partial(orig_pad_sequence, batch_first = True)
+
+        # auto pack if specified
+
+        if group_images:
+            batched_images = group_images_by_max_seq_len(
+                batched_images,
+                patch_size = self.patch_size,
+                calc_token_dropout = self.calc_token_dropout,
+                max_seq_len = group_max_seq_len
+            )
+
+        # process images into variable lengthed sequences with attention mask
+
+        num_images = []
+        batched_sequences = []
+        batched_positions = []
+        batched_image_ids = []
+
+        for images in batched_images:
+            num_images.append(len(images))
+
+            sequences = []
+            positions = []
+            image_ids = torch.empty((0,), device = device, dtype = torch.long)
+
+            for image_id, image in enumerate(images):
+                assert image.ndim ==3 and image.shape[0] == c
+                image_dims = image.shape[-2:]
+                assert all([divisible_by(dim, p) for dim in image_dims]), f'height and width {image_dims} of images must be divisible by patch size {p}'
+
+                ph, pw = map(lambda dim: dim // p, image_dims)
+
+                pos = torch.stack(torch.meshgrid((
+                    arange(ph),
+                    arange(pw)
+                ), indexing = 'ij'), dim = -1)
+
+                pos = rearrange(pos, 'h w c -> (h w) c')
+                seq = rearrange(image, 'c (h p1) (w p2) -> (h w) (c p1 p2)', p1 = p, p2 = p)
+
+                seq_len = seq.shape[-2]
+
+                if has_token_dropout:
+                    token_dropout = self.calc_token_dropout(*image_dims)
+                    num_keep = max(1, int(seq_len * (1 - token_dropout)))
+                    keep_indices = torch.randn((seq_len,), device = device).topk(num_keep, dim = -1).indices
+
+                    seq = seq[keep_indices]
+                    pos = pos[keep_indices]
+
+                image_ids = F.pad(image_ids, (0, seq.shape[-2]), value = image_id)
+                sequences.append(seq)
+                positions.append(pos)
+
+            batched_image_ids.append(image_ids)
+            batched_sequences.append(torch.cat(sequences, dim = 0))
+            batched_positions.append(torch.cat(positions, dim = 0))
+
+        # derive key padding mask
+
+        lengths = torch.tensor([seq.shape[-2] for seq in batched_sequences], device = device, dtype = torch.long)
+        max_length = arange(lengths.amax().item())
+        key_pad_mask = rearrange(lengths, 'b -> b 1') <= rearrange(max_length, 'n -> 1 n')
+
+        # derive attention mask, and combine with key padding mask from above
+
+        batched_image_ids = pad_sequence(batched_image_ids)
+        attn_mask = rearrange(batched_image_ids, 'b i -> b 1 i 1') == rearrange(batched_image_ids, 'b j -> b 1 1 j')
+        attn_mask = attn_mask & rearrange(key_pad_mask, 'b j -> b 1 1 j')
+
+        # combine patched images as well as the patched width / height positions for 2d positional embedding
+
+        patches = pad_sequence(batched_sequences)
+        patch_positions = pad_sequence(batched_positions)
+
+        # need to know how many images for final attention pooling
+
+        num_images = torch.tensor(num_images, device = device, dtype = torch.long)        
+
+        # to patches
+
+        x = self.to_patch_embedding(patches)        
+
+        # factorized 2d absolute positional embedding
+
+        h_indices, w_indices = patch_positions.unbind(dim = -1)
+
+        h_pos = self.pos_embed_height[h_indices]
+        w_pos = self.pos_embed_width[w_indices]
+
+        x = x + h_pos + w_pos
+
+        # embed dropout
+
+        x = self.dropout(x)
+
+        # attention
+
+        x = self.transformer(x, attn_mask = attn_mask)
+
+        # do attention pooling at the end
+
+        max_queries = num_images.amax().item()
+
+        queries = repeat(self.attn_pool_queries, 'd -> b n d', n = max_queries, b = x.shape[0])
+
+        # attention pool mask
+
+        image_id_arange = arange(max_queries)
+
+        attn_pool_mask = rearrange(image_id_arange, 'i -> i 1') == rearrange(batched_image_ids, 'b j -> b 1 j')
+
+        attn_pool_mask = attn_pool_mask & rearrange(key_pad_mask, 'b j -> b 1 j')
+
+        attn_pool_mask = rearrange(attn_pool_mask, 'b i j -> b 1 i j')
+
+        # attention pool
+
+        x = self.attn_pool(queries, context = x, attn_mask = attn_pool_mask) + queries
+
+        x = rearrange(x, 'b n d -> (b n) d')
+
+        # each batch element may not have same amount of images
+
+        is_images = image_id_arange < rearrange(num_images, 'b -> b 1')
+        is_images = rearrange(is_images, 'b n -> (b n)')
+
+        x = x[is_images]
+
+        # project out to logits
+
+        x = self.to_latent(x)
+
+        return self.mlp_head(x)

vit_pytorch/nest.py

@@ -20,23 +20,15 @@ class LayerNorm(nn.Module):
         self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
 
     def forward(self, x):
-        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (std + self.eps) * self.g + self.b
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = LayerNorm(dim)
-        self.fn = fn
-
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
 class FeedForward(nn.Module):
     def __init__(self, dim, mlp_mult = 4, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            LayerNorm(dim),
             nn.Conv2d(dim, dim * mlp_mult, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -54,7 +46,9 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
 
         self.to_out = nn.Sequential(
@@ -65,12 +59,15 @@ class Attention(nn.Module):
     def forward(self, x):
         b, c, h, w, heads = *x.shape, self.heads
 
+        x = self.norm(x)
+
         qkv = self.to_qkv(x).chunk(3, dim = 1)
         q, k, v = map(lambda t: rearrange(t, 'b (h d) x y -> b h (x y) d', h = heads), qkv)
 
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h (x y) d -> b (h d) x y', x = h, y = w)
@@ -91,8 +88,8 @@ class Transformer(nn.Module):
 
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout))
+                Attention(dim, heads = heads, dropout = dropout),
+                FeedForward(dim, mlp_mult, dropout = dropout)
             ]))
     def forward(self, x):
         *_, h, w = x.shape
@@ -129,19 +126,22 @@ class NesT(nn.Module):
         fmap_size = image_size // patch_size
         blocks = 2 ** (num_hierarchies - 1)
 
-        seq_len = (fmap_size // blocks) ** 2   # sequence length is held constant across heirarchy
+        seq_len = (fmap_size // blocks) ** 2   # sequence length is held constant across hierarchy
         hierarchies = list(reversed(range(num_hierarchies)))
-        mults = [2 ** i for i in hierarchies]
+        mults = [2 ** i for i in reversed(hierarchies)]
 
         layer_heads = list(map(lambda t: t * heads, mults))
         layer_dims = list(map(lambda t: t * dim, mults))
+        last_dim = layer_dims[-1]
 
         layer_dims = [*layer_dims, layer_dims[-1]]
         dim_pairs = zip(layer_dims[:-1], layer_dims[1:])
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (p1 p2 c) h w', p1 = patch_size, p2 = patch_size),
+            LayerNorm(patch_dim),
             nn.Conv2d(patch_dim, layer_dims[0], 1),
+            LayerNorm(layer_dims[0])
         )
 
         block_repeats = cast_tuple(block_repeats, num_hierarchies)
@@ -157,10 +157,11 @@ class NesT(nn.Module):
                 Aggregate(dim_in, dim_out) if not is_last else nn.Identity()
             ]))
 
+
         self.mlp_head = nn.Sequential(
-            LayerNorm(dim),
+            LayerNorm(last_dim),
             Reduce('b c h w -> b c', 'mean'),
-            nn.Linear(dim, num_classes)
+            nn.Linear(last_dim, num_classes)
         )
 
     def forward(self, img):

vit_pytorch/parallel_vit.py

@@ -0,0 +1,135 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class Parallel(nn.Module):
+    def __init__(self, *fns):
+        super().__init__()
+        self.fns = nn.ModuleList(fns)
+
+    def forward(self, x):
+        return sum([fn(x) for fn in self.fns])
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        x = self.norm(x)
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, num_parallel_branches = 2, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        attn_block = lambda: Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)
+        ff_block = lambda: FeedForward(dim, mlp_dim, dropout = dropout)
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Parallel(*[attn_block() for _ in range(num_parallel_branches)]),
+                Parallel(*[ff_block() for _ in range(num_parallel_branches)]),
+            ]))
+
+    def forward(self, x):
+        for attns, ffs in self.layers:
+            x = attns(x) + x
+            x = ffs(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', num_parallel_branches = 2, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, num_parallel_branches, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/pit.py

@@ -17,18 +17,11 @@ def conv_output_size(image_size, kernel_size, stride, padding = 0):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -47,7 +40,9 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.to_out = nn.Sequential(
@@ -57,12 +52,15 @@ class Attention(nn.Module):
 
     def forward(self, x):
         b, n, _, h = *x.shape, self.heads
+
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
 
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
@@ -74,8 +72,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:

vit_pytorch/recorder.py

@@ -55,5 +55,5 @@ class Recorder(nn.Module):
         target_device = self.device if self.device is not None else img.device
         recordings = tuple(map(lambda t: t.to(target_device), self.recordings))
 
-        attns = torch.stack(recordings, dim = 1)
+        attns = torch.stack(recordings, dim = 1) if len(recordings) > 0 else None
         return pred, attns

vit_pytorch/regionvit.py

@@ -61,8 +61,13 @@ class Attention(nn.Module):
         inner_dim = dim_head * heads
 
         self.norm = nn.LayerNorm(dim)
+        self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
-        self.to_out = nn.Linear(inner_dim, dim)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
 
     def forward(self, x, rel_pos_bias = None):
         h = self.heads
@@ -86,6 +91,7 @@ class Attention(nn.Module):
             sim = sim + rel_pos_bias
 
         attn = sim.softmax(dim = -1)
+        attn = self.dropout(attn)
 
         # merge heads
 
@@ -132,7 +138,7 @@ class R2LTransformer(nn.Module):
         h_range = torch.arange(window_size_h, device = device)
         w_range = torch.arange(window_size_w, device = device)
 
-        grid_x, grid_y = torch.meshgrid(h_range, w_range)
+        grid_x, grid_y = torch.meshgrid(h_range, w_range, indexing = 'ij')
         grid = torch.stack((grid_x, grid_y))
         grid = rearrange(grid, 'c h w -> c (h w)')
         grid = (grid[:, :, None] - grid[:, None, :]) + (self.window_size - 1)

vit_pytorch/rvt.py

@@ -55,14 +55,6 @@ class DepthWiseConv2d(nn.Module):
 
 # helper classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class SpatialConv(nn.Module):
     def __init__(self, dim_in, dim_out, kernel, bias = False):
         super().__init__()
@@ -86,6 +78,7 @@ class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0., use_glu = True):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim * 2 if use_glu else hidden_dim),
             GEGLU() if use_glu else nn.GELU(),
             nn.Dropout(dropout),
@@ -103,7 +96,9 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
 
         self.use_ds_conv = use_ds_conv
 
@@ -120,6 +115,9 @@ class Attention(nn.Module):
         b, n, _, h = *x.shape, self.heads
 
         to_q_kwargs = {'fmap_dims': fmap_dims} if self.use_ds_conv else {}
+
+        x = self.norm(x)
+
         q = self.to_q(x, **to_q_kwargs)
 
         qkv = (q, *self.to_kv(x).chunk(2, dim = -1))
@@ -148,6 +146,7 @@ class Attention(nn.Module):
         dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b i j, b j d -> b i d', attn, v)
         out = rearrange(out, '(b h) n d -> b n (h d)', h = h)
@@ -160,8 +159,8 @@ class Transformer(nn.Module):
         self.pos_emb = AxialRotaryEmbedding(dim_head, max_freq = image_size)
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout, use_rotary = use_rotary, use_ds_conv = use_ds_conv)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout, use_glu = use_glu))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout, use_rotary = use_rotary, use_ds_conv = use_ds_conv),
+                FeedForward(dim, mlp_dim, dropout = dropout, use_glu = use_glu)
             ]))
     def forward(self, x, fmap_dims):
         pos_emb = self.pos_emb(x[:, 1:])

vit_pytorch/scalable_vit.py

@@ -0,0 +1,304 @@
+from functools import partial
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+class ChanLayerNorm(nn.Module):
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
+
+class Downsample(nn.Module):
+    def __init__(self, dim_in, dim_out):
+        super().__init__()
+        self.conv = nn.Conv2d(dim_in, dim_out, 3, stride = 2, padding = 1)
+
+    def forward(self, x):
+        return self.conv(x)
+
+class PEG(nn.Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        self.proj = nn.Conv2d(dim, dim, kernel_size = kernel_size, padding = kernel_size // 2, groups = dim, stride = 1)
+
+    def forward(self, x):
+        return self.proj(x) + x
+
+# feedforward
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, expansion_factor = 4, dropout = 0.):
+        super().__init__()
+        inner_dim = dim * expansion_factor
+        self.net = nn.Sequential(
+            ChanLayerNorm(dim),
+            nn.Conv2d(dim, inner_dim, 1),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# attention
+
+class ScalableSelfAttention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        heads = 8,
+        dim_key = 32,
+        dim_value = 32,
+        dropout = 0.,
+        reduction_factor = 1
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_key ** -0.5
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.norm = ChanLayerNorm(dim)
+        self.to_q = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
+        self.to_k = nn.Conv2d(dim, dim_key * heads, reduction_factor, stride = reduction_factor, bias = False)
+        self.to_v = nn.Conv2d(dim, dim_value * heads, reduction_factor, stride = reduction_factor, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(dim_value * heads, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        height, width, heads = *x.shape[-2:], self.heads
+
+        x = self.norm(x)
+
+        q, k, v = self.to_q(x), self.to_k(x), self.to_v(x)
+
+        # split out heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) ... -> b h (...) d', h = heads), (q, k, v))
+
+        # similarity
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        # attention
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        # aggregate values
+
+        out = torch.matmul(attn, v)
+
+        # merge back heads
+
+        out = rearrange(out, 'b h (x y) d -> b (h d) x y', x = height, y = width)
+        return self.to_out(out)
+
+class InteractiveWindowedSelfAttention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        window_size,
+        heads = 8,
+        dim_key = 32,
+        dim_value = 32,
+        dropout = 0.
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_key ** -0.5
+        self.window_size = window_size
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.norm = ChanLayerNorm(dim)
+        self.local_interactive_module = nn.Conv2d(dim_value * heads, dim_value * heads, 3, padding = 1)
+
+        self.to_q = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
+        self.to_k = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
+        self.to_v = nn.Conv2d(dim, dim_value * heads, 1, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(dim_value * heads, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        height, width, heads, wsz = *x.shape[-2:], self.heads, self.window_size
+
+        x = self.norm(x)
+
+        wsz_h, wsz_w = default(wsz, height), default(wsz, width)
+        assert (height % wsz_h) == 0 and (width % wsz_w) == 0, f'height ({height}) or width ({width}) of feature map is not divisible by the window size ({wsz_h}, {wsz_w})'
+
+        q, k, v = self.to_q(x), self.to_k(x), self.to_v(x)
+
+        # get output of LIM
+
+        local_out = self.local_interactive_module(v)
+
+        # divide into window (and split out heads) for efficient self attention
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) (x w1) (y w2) -> (b x y) h (w1 w2) d', h = heads, w1 = wsz_h, w2 = wsz_w), (q, k, v))
+
+        # similarity
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        # attention
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        # aggregate values
+
+        out = torch.matmul(attn, v)
+
+        # reshape the windows back to full feature map (and merge heads)
+
+        out = rearrange(out, '(b x y) h (w1 w2) d -> b (h d) (x w1) (y w2)', x = height // wsz_h, y = width // wsz_w, w1 = wsz_h, w2 = wsz_w)
+
+        # add LIM output 
+
+        out = out + local_out
+
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        depth,
+        heads = 8,
+        ff_expansion_factor = 4,
+        dropout = 0.,
+        ssa_dim_key = 32,
+        ssa_dim_value = 32,
+        ssa_reduction_factor = 1,
+        iwsa_dim_key = 32,
+        iwsa_dim_value = 32,
+        iwsa_window_size = None,
+        norm_output = True
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for ind in range(depth):
+            is_first = ind == 0
+
+            self.layers.append(nn.ModuleList([
+                ScalableSelfAttention(dim, heads = heads, dim_key = ssa_dim_key, dim_value = ssa_dim_value, reduction_factor = ssa_reduction_factor, dropout = dropout),
+                FeedForward(dim, expansion_factor = ff_expansion_factor, dropout = dropout),
+                PEG(dim) if is_first else None,
+                FeedForward(dim, expansion_factor = ff_expansion_factor, dropout = dropout),
+                InteractiveWindowedSelfAttention(dim, heads = heads, dim_key = iwsa_dim_key, dim_value = iwsa_dim_value, window_size = iwsa_window_size, dropout = dropout)
+            ]))
+
+        self.norm = ChanLayerNorm(dim) if norm_output else nn.Identity()
+
+    def forward(self, x):
+        for ssa, ff1, peg, iwsa, ff2 in self.layers:
+            x = ssa(x) + x
+            x = ff1(x) + x
+
+            if exists(peg):
+                x = peg(x)
+
+            x = iwsa(x) + x
+            x = ff2(x) + x
+
+        return self.norm(x)
+
+class ScalableViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        heads,
+        reduction_factor,
+        window_size = None,
+        iwsa_dim_key = 32,
+        iwsa_dim_value = 32,
+        ssa_dim_key = 32,
+        ssa_dim_value = 32,
+        ff_expansion_factor = 4,
+        channels = 3,
+        dropout = 0.
+    ):
+        super().__init__()
+        self.to_patches = nn.Conv2d(channels, dim, 7, stride = 4, padding = 3)
+
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+
+        num_stages = len(depth)
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+
+        hyperparams_per_stage = [
+            heads,
+            ssa_dim_key,
+            ssa_dim_value,
+            reduction_factor,
+            iwsa_dim_key,
+            iwsa_dim_value,
+            window_size,
+        ]
+
+        hyperparams_per_stage = list(map(partial(cast_tuple, length = num_stages), hyperparams_per_stage))
+        assert all(tuple(map(lambda arr: len(arr) == num_stages, hyperparams_per_stage)))
+
+        self.layers = nn.ModuleList([])
+
+        for ind, (layer_dim, layer_depth, layer_heads, layer_ssa_dim_key, layer_ssa_dim_value, layer_ssa_reduction_factor, layer_iwsa_dim_key, layer_iwsa_dim_value, layer_window_size) in enumerate(zip(dims, depth, *hyperparams_per_stage)):
+            is_last = ind == (num_stages - 1)
+
+            self.layers.append(nn.ModuleList([
+                Transformer(dim = layer_dim, depth = layer_depth, heads = layer_heads, ff_expansion_factor = ff_expansion_factor, dropout = dropout, ssa_dim_key = layer_ssa_dim_key, ssa_dim_value = layer_ssa_dim_value, ssa_reduction_factor = layer_ssa_reduction_factor, iwsa_dim_key = layer_iwsa_dim_key, iwsa_dim_value = layer_iwsa_dim_value, iwsa_window_size = layer_window_size, norm_output = not is_last),
+                Downsample(layer_dim, layer_dim * 2) if not is_last else None
+            ]))
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patches(img)
+
+        for transformer, downsample in self.layers:
+            x = transformer(x)
+
+            if exists(downsample):
+                x = downsample(x)
+
+        return self.mlp_head(x)

vit_pytorch/sep_vit.py

@@ -0,0 +1,290 @@
+from functools import partial
+
+import torch
+from torch import nn, einsum
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+class ChanLayerNorm(nn.Module):
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
+
+class OverlappingPatchEmbed(nn.Module):
+    def __init__(self, dim_in, dim_out, stride = 2):
+        super().__init__()
+        kernel_size = stride * 2 - 1
+        padding = kernel_size // 2
+        self.conv = nn.Conv2d(dim_in, dim_out, kernel_size, stride = stride, padding = padding)
+
+    def forward(self, x):
+        return self.conv(x)
+
+class PEG(nn.Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        self.proj = nn.Conv2d(dim, dim, kernel_size = kernel_size, padding = kernel_size // 2, groups = dim, stride = 1)
+
+    def forward(self, x):
+        return self.proj(x) + x
+
+# feedforward
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mult = 4, dropout = 0.):
+        super().__init__()
+        inner_dim = int(dim * mult)
+        self.net = nn.Sequential(
+            ChanLayerNorm(dim),
+            nn.Conv2d(dim, inner_dim, 1),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# attention
+
+class DSSA(nn.Module):
+    def __init__(
+        self,
+        dim,
+        heads = 8,
+        dim_head = 32,
+        dropout = 0.,
+        window_size = 7
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.window_size = window_size
+        inner_dim = dim_head * heads
+
+        self.norm = ChanLayerNorm(dim)
+
+        self.attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_qkv = nn.Conv1d(dim, inner_dim * 3, 1, bias = False)
+
+        # window tokens
+
+        self.window_tokens = nn.Parameter(torch.randn(dim))
+
+        # prenorm and non-linearity for window tokens
+        # then projection to queries and keys for window tokens
+
+        self.window_tokens_to_qk = nn.Sequential(
+            nn.LayerNorm(dim_head),
+            nn.GELU(),
+            Rearrange('b h n c -> b (h c) n'),
+            nn.Conv1d(inner_dim, inner_dim * 2, 1),
+            Rearrange('b (h c) n -> b h n c', h = heads),
+        )
+
+        # window attention
+
+        self.window_attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        """
+        einstein notation
+
+        b - batch
+        c - channels
+        w1 - window size (height)
+        w2 - also window size (width)
+        i - sequence dimension (source)
+        j - sequence dimension (target dimension to be reduced)
+        h - heads
+        x - height of feature map divided by window size
+        y - width of feature map divided by window size
+        """
+
+        batch, height, width, heads, wsz = x.shape[0], *x.shape[-2:], self.heads, self.window_size
+        assert (height % wsz) == 0 and (width % wsz) == 0, f'height {height} and width {width} must be divisible by window size {wsz}'
+        num_windows = (height // wsz) * (width // wsz)
+
+        x = self.norm(x)
+
+        # fold in windows for "depthwise" attention - not sure why it is named depthwise when it is just "windowed" attention
+
+        x = rearrange(x, 'b c (h w1) (w w2) -> (b h w) c (w1 w2)', w1 = wsz, w2 = wsz)
+
+        # add windowing tokens
+
+        w = repeat(self.window_tokens, 'c -> b c 1', b = x.shape[0])
+        x = torch.cat((w, x), dim = -1)
+
+        # project for queries, keys, value
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = 1)
+
+        # split out heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) ... -> b h (...) d', h = heads), (q, k, v))
+
+        # scale
+
+        q = q * self.scale
+
+        # similarity
+
+        dots = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # attention
+
+        attn = self.attend(dots)
+
+        # aggregate values
+
+        out = torch.matmul(attn, v)
+
+        # split out windowed tokens
+
+        window_tokens, windowed_fmaps = out[:, :, 0], out[:, :, 1:]
+
+        # early return if there is only 1 window
+
+        if num_windows == 1:
+            fmap = rearrange(windowed_fmaps, '(b x y) h (w1 w2) d -> b (h d) (x w1) (y w2)', x = height // wsz, y = width // wsz, w1 = wsz, w2 = wsz)
+            return self.to_out(fmap)
+
+        # carry out the pointwise attention, the main novelty in the paper
+
+        window_tokens = rearrange(window_tokens, '(b x y) h d -> b h (x y) d', x = height // wsz, y = width // wsz)
+        windowed_fmaps = rearrange(windowed_fmaps, '(b x y) h n d -> b h (x y) n d', x = height // wsz, y = width // wsz)
+
+        # windowed queries and keys (preceded by prenorm activation)
+
+        w_q, w_k = self.window_tokens_to_qk(window_tokens).chunk(2, dim = -1)
+
+        # scale
+
+        w_q = w_q * self.scale
+
+        # similarities
+
+        w_dots = einsum('b h i d, b h j d -> b h i j', w_q, w_k)
+
+        w_attn = self.window_attend(w_dots)
+
+        # aggregate the feature maps from the "depthwise" attention step (the most interesting part of the paper, one i haven't seen before)
+
+        aggregated_windowed_fmap = einsum('b h i j, b h j w d -> b h i w d', w_attn, windowed_fmaps)
+
+        # fold back the windows and then combine heads for aggregation
+
+        fmap = rearrange(aggregated_windowed_fmap, 'b h (x y) (w1 w2) d -> b (h d) (x w1) (y w2)', x = height // wsz, y = width // wsz, w1 = wsz, w2 = wsz)
+        return self.to_out(fmap)
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        depth,
+        dim_head = 32,
+        heads = 8,
+        ff_mult = 4,
+        dropout = 0.,
+        norm_output = True
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        for ind in range(depth):
+            self.layers.append(nn.ModuleList([
+                DSSA(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mult = ff_mult, dropout = dropout),
+            ]))
+
+        self.norm = ChanLayerNorm(dim) if norm_output else nn.Identity()
+
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+
+        return self.norm(x)
+
+class SepViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        heads,
+        window_size = 7,
+        dim_head = 32,
+        ff_mult = 4,
+        channels = 3,
+        dropout = 0.
+    ):
+        super().__init__()
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+
+        num_stages = len(depth)
+
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+        dims = (channels, *dims)
+        dim_pairs = tuple(zip(dims[:-1], dims[1:]))
+
+        strides = (4, *((2,) * (num_stages - 1)))
+
+        hyperparams_per_stage = [heads, window_size]
+        hyperparams_per_stage = list(map(partial(cast_tuple, length = num_stages), hyperparams_per_stage))
+        assert all(tuple(map(lambda arr: len(arr) == num_stages, hyperparams_per_stage)))
+
+        self.layers = nn.ModuleList([])
+
+        for ind, ((layer_dim_in, layer_dim), layer_depth, layer_stride, layer_heads, layer_window_size) in enumerate(zip(dim_pairs, depth, strides, *hyperparams_per_stage)):
+            is_last = ind == (num_stages - 1)
+
+            self.layers.append(nn.ModuleList([
+                OverlappingPatchEmbed(layer_dim_in, layer_dim, stride = layer_stride),
+                PEG(layer_dim),
+                Transformer(dim = layer_dim, depth = layer_depth, heads = layer_heads, ff_mult = ff_mult, dropout = dropout, norm_output = not is_last),
+            ]))
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, x):
+
+        for ope, peg, transformer in self.layers:
+            x = ope(x)
+            x = peg(x)
+            x = transformer(x)
+
+        return self.mlp_head(x)

vit_pytorch/simmim.py

@@ -18,8 +18,11 @@ class SimMIM(nn.Module):
 
         self.encoder = encoder
         num_patches, encoder_dim = encoder.pos_embedding.shape[-2:]
-        self.to_patch, self.patch_to_emb = encoder.to_patch_embedding[:2]
-        pixel_values_per_patch = self.patch_to_emb.weight.shape[-1]
+
+        self.to_patch = encoder.to_patch_embedding[0]
+        self.patch_to_emb = nn.Sequential(*encoder.to_patch_embedding[1:])
+
+        pixel_values_per_patch = encoder.to_patch_embedding[2].weight.shape[-1]
 
         # simple linear head
 

vit_pytorch/simple_flash_attn_vit.py

@@ -0,0 +1,176 @@
+from collections import namedtuple
+from packaging import version
+
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# constants
+
+Config = namedtuple('FlashAttentionConfig', ['enable_flash', 'enable_math', 'enable_mem_efficient'])
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_2d(patches, temperature = 10000, dtype = torch.float32):
+    _, h, w, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    y, x = torch.meshgrid(torch.arange(h, device = device), torch.arange(w, device = device), indexing = 'ij')
+    assert (dim % 4) == 0, 'feature dimension must be multiple of 4 for sincos emb'
+    omega = torch.arange(dim // 4, device = device) / (dim // 4 - 1)
+    omega = 1. / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :] 
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim = 1)
+    return pe.type(dtype)
+
+# main class
+
+class Attend(nn.Module):
+    def __init__(self, use_flash = False):
+        super().__init__()
+        self.use_flash = use_flash
+        assert not (use_flash and version.parse(torch.__version__) < version.parse('2.0.0')), 'in order to use flash attention, you must be using pytorch 2.0 or above'
+
+        # determine efficient attention configs for cuda and cpu
+
+        self.cpu_config = Config(True, True, True)
+        self.cuda_config = None
+
+        if not torch.cuda.is_available() or not use_flash:
+            return
+
+        device_properties = torch.cuda.get_device_properties(torch.device('cuda'))
+
+        if device_properties.major == 8 and device_properties.minor == 0:
+            self.cuda_config = Config(True, False, False)
+        else:
+            self.cuda_config = Config(False, True, True)
+
+    def flash_attn(self, q, k, v):
+        config = self.cuda_config if q.is_cuda else self.cpu_config
+
+        # flash attention - https://arxiv.org/abs/2205.14135
+        
+        with torch.backends.cuda.sdp_kernel(**config._asdict()):
+            out = F.scaled_dot_product_attention(q, k, v)
+
+        return out
+
+    def forward(self, q, k, v):
+        n, device, scale = q.shape[-2], q.device, q.shape[-1] ** -0.5
+
+        if self.use_flash:
+            return self.flash_attn(q, k, v)
+
+        # similarity
+
+        sim = einsum("b h i d, b j d -> b h i j", q, k) * scale
+
+        # attention
+
+        attn = sim.softmax(dim=-1)
+
+        # aggregate values
+
+        out = einsum("b h i j, b j d -> b h i d", attn, v)
+
+        return out
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, use_flash = True):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = Attend(use_flash = use_flash)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        out = self.attend(q, k, v)
+
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, use_flash):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, use_flash = use_flash),
+                FeedForward(dim, mlp_dim)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, use_flash = True):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b h w (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, use_flash)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        *_, h, w, dtype = *img.shape, img.dtype
+
+        x = self.to_patch_embedding(img)
+        pe = posemb_sincos_2d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/simple_vit.py

@@ -0,0 +1,120 @@
+import torch
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_2d(h, w, dim, temperature: int = 10000, dtype = torch.float32):
+    y, x = torch.meshgrid(torch.arange(h), torch.arange(w), indexing="ij")
+    assert (dim % 4) == 0, "feature dimension must be multiple of 4 for sincos emb"
+    omega = torch.arange(dim // 4) / (dim // 4 - 1)
+    omega = 1.0 / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :]
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim=1)
+    return pe.type(dtype)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head),
+                FeedForward(dim, mlp_dim)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return self.norm(x)
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange("b c (h p1) (w p2) -> b (h w) (p1 p2 c)", p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.pos_embedding = posemb_sincos_2d(
+            h = image_height // patch_height,
+            w = image_width // patch_width,
+            dim = dim,
+        ) 
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.pool = "mean"
+        self.to_latent = nn.Identity()
+
+        self.linear_head = nn.Linear(dim, num_classes)
+
+    def forward(self, img):
+        device = img.device
+
+        x = self.to_patch_embedding(img)
+        x += self.pos_embedding.to(device, dtype=x.dtype)
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/simple_vit_1d.py

@@ -0,0 +1,125 @@
+import torch
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def posemb_sincos_1d(patches, temperature = 10000, dtype = torch.float32):
+    _, n, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    n = torch.arange(n, device = device)
+    assert (dim % 2) == 0, 'feature dimension must be multiple of 2 for sincos emb'
+    omega = torch.arange(dim // 2, device = device) / (dim // 2 - 1)
+    omega = 1. / (temperature ** omega)
+
+    n = n.flatten()[:, None] * omega[None, :]
+    pe = torch.cat((n.sin(), n.cos()), dim = 1)
+    return pe.type(dtype)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head),
+                FeedForward(dim, mlp_dim)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return self.norm(x)
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, seq_len, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
+        super().__init__()
+
+        assert seq_len % patch_size == 0
+
+        num_patches = seq_len // patch_size
+        patch_dim = channels * patch_size
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (n p) -> b n (p c)', p = patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Linear(dim, num_classes)
+
+    def forward(self, series):
+        *_, n, dtype = *series.shape, series.dtype
+
+        x = self.to_patch_embedding(series)
+        pe = posemb_sincos_1d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)
+
+if __name__ == '__main__':
+
+    v = SimpleViT(
+        seq_len = 256,
+        patch_size = 16,
+        num_classes = 1000,
+        dim = 1024,
+        depth = 6,
+        heads = 8,
+        mlp_dim = 2048
+    )
+
+    time_series = torch.randn(4, 3, 256)
+    logits = v(time_series) # (4, 1000)

vit_pytorch/simple_vit_3d.py

@@ -0,0 +1,128 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_3d(patches, temperature = 10000, dtype = torch.float32):
+    _, f, h, w, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    z, y, x = torch.meshgrid(
+        torch.arange(f, device = device),
+        torch.arange(h, device = device),
+        torch.arange(w, device = device),
+    indexing = 'ij')
+
+    fourier_dim = dim // 6
+
+    omega = torch.arange(fourier_dim, device = device) / (fourier_dim - 1)
+    omega = 1. / (temperature ** omega)
+
+    z = z.flatten()[:, None] * omega[None, :]
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :] 
+
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos(), z.sin(), z.cos()), dim = 1)
+
+    pe = F.pad(pe, (0, dim - (fourier_dim * 6))) # pad if feature dimension not cleanly divisible by 6
+    return pe.type(dtype)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head),
+                FeedForward(dim, mlp_dim)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return self.norm(x)
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(image_patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        assert frames % frame_patch_size == 0, 'Frames must be divisible by the frame patch size'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width) * (frames // frame_patch_size)
+        patch_dim = channels * patch_height * patch_width * frame_patch_size
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f h w (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Linear(dim, num_classes)
+
+    def forward(self, video):
+        *_, h, w, dtype = *video.shape, video.dtype
+
+        x = self.to_patch_embedding(video)
+        pe = posemb_sincos_3d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/simple_vit_with_patch_dropout.py

@@ -0,0 +1,141 @@
+import torch
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_2d(patches, temperature = 10000, dtype = torch.float32):
+    _, h, w, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    y, x = torch.meshgrid(torch.arange(h, device = device), torch.arange(w, device = device), indexing = 'ij')
+    assert (dim % 4) == 0, 'feature dimension must be multiple of 4 for sincos emb'
+    omega = torch.arange(dim // 4, device = device) / (dim // 4 - 1)
+    omega = 1. / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :] 
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim = 1)
+    return pe.type(dtype)
+
+# patch dropout
+
+class PatchDropout(nn.Module):
+    def __init__(self, prob):
+        super().__init__()
+        assert 0 <= prob < 1.
+        self.prob = prob
+
+    def forward(self, x):
+        if not self.training or self.prob == 0.:
+            return x
+
+        b, n, _, device = *x.shape, x.device
+
+        batch_indices = torch.arange(b, device = device)
+        batch_indices = rearrange(batch_indices, '... -> ... 1')
+        num_patches_keep = max(1, int(n * (1 - self.prob)))
+        patch_indices_keep = torch.randn(b, n, device = device).topk(num_patches_keep, dim = -1).indices
+
+        return x[batch_indices, patch_indices_keep]
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head),
+                FeedForward(dim, mlp_dim)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return self.norm(x)
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, patch_dropout = 0.5):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b h w (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.patch_dropout = PatchDropout(patch_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Linear(dim, num_classes)
+
+    def forward(self, img):
+        *_, h, w, dtype = *img.shape, img.dtype
+
+        x = self.to_patch_embedding(img)
+        pe = posemb_sincos_2d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.patch_dropout(x)
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/simple_vit_with_qk_norm.py

@@ -0,0 +1,141 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_2d(h, w, dim, temperature: int = 10000, dtype = torch.float32):
+    y, x = torch.meshgrid(torch.arange(h), torch.arange(w), indexing="ij")
+    assert (dim % 4) == 0, "feature dimension must be multiple of 4 for sincos emb"
+    omega = torch.arange(dim // 4) / (dim // 4 - 1)
+    omega = 1.0 / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :]
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim=1)
+    return pe.type(dtype)
+
+# they use a query-key normalization that is equivalent to rms norm (no mean-centering, learned gamma), from vit 22B paper
+
+# in latest tweet, seem to claim more stable training at higher learning rates
+# unsure if this has taken off within Brain, or it has some hidden drawback
+
+class RMSNorm(nn.Module):
+    def __init__(self, heads, dim):
+        super().__init__()
+        self.scale = dim ** 0.5
+        self.gamma = nn.Parameter(torch.ones(heads, 1, dim) / self.scale)
+
+    def forward(self, x):
+        normed = F.normalize(x, dim = -1)
+        return normed * self.scale * self.gamma
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.q_norm = RMSNorm(heads, dim_head)
+        self.k_norm = RMSNorm(heads, dim_head)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        q = self.q_norm(q)
+        k = self.k_norm(k)
+
+        dots = torch.matmul(q, k.transpose(-1, -2))
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head),
+                FeedForward(dim, mlp_dim)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return self.norm(x)
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange("b c (h p1) (w p2) -> b (h w) (p1 p2 c)", p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.pos_embedding = posemb_sincos_2d(
+            h = image_height // patch_height,
+            w = image_width // patch_width,
+            dim = dim,
+        ) 
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.pool = "mean"
+        self.to_latent = nn.Identity()
+
+        self.linear_head = nn.LayerNorm(dim)
+
+    def forward(self, img):
+        device = img.device
+
+        x = self.to_patch_embedding(img)
+        x += self.pos_embedding.to(device, dtype=x.dtype)
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/simple_vit_with_register_tokens.py

@@ -0,0 +1,134 @@
+"""
+    Vision Transformers Need Registers
+    https://arxiv.org/abs/2309.16588
+"""
+
+import torch
+from torch import nn
+
+from einops import rearrange, repeat, pack, unpack
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_2d(h, w, dim, temperature: int = 10000, dtype = torch.float32):
+    y, x = torch.meshgrid(torch.arange(h), torch.arange(w), indexing="ij")
+    assert (dim % 4) == 0, "feature dimension must be multiple of 4 for sincos emb"
+    omega = torch.arange(dim // 4) / (dim // 4 - 1)
+    omega = 1.0 / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :]
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim=1)
+    return pe.type(dtype)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head),
+                FeedForward(dim, mlp_dim)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return self.norm(x)
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, num_register_tokens = 4, channels = 3, dim_head = 64):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange("b c (h p1) (w p2) -> b (h w) (p1 p2 c)", p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.register_tokens = nn.Parameter(torch.randn(num_register_tokens, dim))
+
+        self.pos_embedding = posemb_sincos_2d(
+            h = image_height // patch_height,
+            w = image_width // patch_width,
+            dim = dim,
+        ) 
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.pool = "mean"
+        self.to_latent = nn.Identity()
+
+        self.linear_head = nn.Linear(dim, num_classes)
+
+    def forward(self, img):
+        batch, device = img.shape[0], img.device
+
+        x = self.to_patch_embedding(img)
+        x += self.pos_embedding.to(device, dtype=x.dtype)
+
+        r = repeat(self.register_tokens, 'n d -> b n d', b = batch)
+
+        x, ps = pack([x, r], 'b * d')
+
+        x = self.transformer(x)
+
+        x, _ = unpack(x, ps, 'b * d')
+
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/twins_svt.py

@@ -38,24 +38,15 @@ class LayerNorm(nn.Module):
         self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
 
     def forward(self, x):
-        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (std + self.eps) * self.g + self.b
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = LayerNorm(dim)
-        self.fn = fn
-
-    def forward(self, x, **kwargs):
-        x = self.norm(x)
-        return self.fn(x, **kwargs)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
 class FeedForward(nn.Module):
     def __init__(self, dim, mult = 4, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            LayerNorm(dim),
             nn.Conv2d(dim, dim * mult, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -71,7 +62,12 @@ class PatchEmbedding(nn.Module):
         self.dim = dim
         self.dim_out = dim_out
         self.patch_size = patch_size
-        self.proj = nn.Conv2d(patch_size ** 2 * dim, dim_out, 1)
+
+        self.proj = nn.Sequential(
+            LayerNorm(patch_size ** 2 * dim),
+            nn.Conv2d(patch_size ** 2 * dim, dim_out, 1),
+            LayerNorm(dim_out)
+        )
 
     def forward(self, fmap):
         p = self.patch_size
@@ -94,6 +90,7 @@ class LocalAttention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
         self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
         self.to_kv = nn.Conv2d(dim, inner_dim * 2, 1, bias = False)
 
@@ -103,6 +100,8 @@ class LocalAttention(nn.Module):
         )
 
     def forward(self, fmap):
+        fmap = self.norm(fmap)
+
         shape, p = fmap.shape, self.patch_size
         b, n, x, y, h = *shape, self.heads
         x, y = map(lambda t: t // p, (x, y))
@@ -127,15 +126,21 @@ class GlobalAttention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
+
         self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
         self.to_kv = nn.Conv2d(dim, inner_dim * 2, k, stride = k, bias = False)
 
+        self.dropout = nn.Dropout(dropout)
+
         self.to_out = nn.Sequential(
             nn.Conv2d(inner_dim, dim, 1),
             nn.Dropout(dropout)
         )
 
     def forward(self, x):
+        x = self.norm(x)
+
         shape = x.shape
         b, n, _, y, h = *shape, self.heads
         q, k, v = (self.to_q(x), *self.to_kv(x).chunk(2, dim = 1))
@@ -145,6 +150,7 @@ class GlobalAttention(nn.Module):
         dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
 
         attn = dots.softmax(dim = -1)
+        attn = self.dropout(attn)
 
         out = einsum('b i j, b j d -> b i d', attn, v)
         out = rearrange(out, '(b h) (x y) d -> b (h d) x y', h = h, y = y)
@@ -156,10 +162,10 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                Residual(PreNorm(dim, LocalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, patch_size = local_patch_size))) if has_local else nn.Identity(),
-                Residual(PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout))) if has_local else nn.Identity(),
-                Residual(PreNorm(dim, GlobalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, k = global_k))),
-                Residual(PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout)))
+                Residual(LocalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, patch_size = local_patch_size)) if has_local else nn.Identity(),
+                Residual(FeedForward(dim, mlp_mult, dropout = dropout)) if has_local else nn.Identity(),
+                Residual(GlobalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, k = global_k)),
+                Residual(FeedForward(dim, mlp_mult, dropout = dropout))
             ]))
     def forward(self, x):
         for local_attn, ff1, global_attn, ff2 in self.layers:

vit_pytorch/vit.py

@@ -11,24 +11,18 @@ def pair(t):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
             nn.Linear(hidden_dim, dim),
             nn.Dropout(dropout)
         )
+
     def forward(self, x):
         return self.net(x)
 
@@ -41,7 +35,11 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
+
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.to_out = nn.Sequential(
@@ -50,12 +48,15 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
+
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
         dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = torch.matmul(attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
@@ -64,17 +65,20 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
+
     def forward(self, x):
         for attn, ff in self.layers:
             x = attn(x) + x
             x = ff(x) + x
-        return x
+
+        return self.norm(x)
 
 class ViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
@@ -90,7 +94,9 @@ class ViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
@@ -102,16 +108,13 @@ class ViT(nn.Module):
         self.pool = pool
         self.to_latent = nn.Identity()
 
-        self.mlp_head = nn.Sequential(
-            nn.LayerNorm(dim),
-            nn.Linear(dim, num_classes)
-        )
+        self.mlp_head = nn.Linear(dim, num_classes)
 
     def forward(self, img):
         x = self.to_patch_embedding(img)
         b, n, _ = x.shape
 
-        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        cls_tokens = repeat(self.cls_token, '1 1 d -> b 1 d', b = b)
         x = torch.cat((cls_tokens, x), dim=1)
         x += self.pos_embedding[:, :(n + 1)]
         x = self.dropout(x)

vit_pytorch/vit_1d.py

@@ -0,0 +1,130 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat, pack, unpack
+from einops.layers.torch import Rearrange
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Layernorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        x = self.norm(x)
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, seq_len, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        assert (seq_len % patch_size) == 0
+
+        num_patches = seq_len // patch_size
+        patch_dim = channels * patch_size
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (n p) -> b n (p c)', p = patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, series):
+        x = self.to_patch_embedding(series)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, 'd -> b d', b = b)
+
+        x, ps = pack([cls_tokens, x], 'b * d')
+
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        cls_tokens, _ = unpack(x, ps, 'b * d')
+
+        return self.mlp_head(cls_tokens)
+
+if __name__ == '__main__':
+
+    v = ViT(
+        seq_len = 256,
+        patch_size = 16,
+        num_classes = 1000,
+        dim = 1024,
+        depth = 6,
+        heads = 8,
+        mlp_dim = 2048,
+        dropout = 0.1,
+        emb_dropout = 0.1
+    )
+
+    time_series = torch.randn(4, 3, 256)
+    logits = v(time_series) # (4, 1000)

vit_pytorch/vit_3d.py

@@ -0,0 +1,126 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        x = self.norm(x)
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(image_patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        assert frames % frame_patch_size == 0, 'Frames must be divisible by frame patch size'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width) * (frames // frame_patch_size)
+        patch_dim = channels * patch_height * patch_width * frame_patch_size
+
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (f pf) (h p1) (w p2) -> b (f h w) (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, video):
+        x = self.to_patch_embedding(video)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '1 1 d -> b 1 d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/vit_for_small_dataset.py

@@ -0,0 +1,140 @@
+from math import sqrt
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class LSA(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.temperature = nn.Parameter(torch.log(torch.tensor(dim_head ** -0.5)))
+
+        self.norm = nn.LayerNorm(dim)
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        x = self.norm(x)
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.temperature.exp()
+
+        mask = torch.eye(dots.shape[-1], device = dots.device, dtype = torch.bool)
+        mask_value = -torch.finfo(dots.dtype).max
+        dots = dots.masked_fill(mask, mask_value)
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                LSA(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class SPT(nn.Module):
+    def __init__(self, *, dim, patch_size, channels = 3):
+        super().__init__()
+        patch_dim = patch_size * patch_size * 5 * channels
+
+        self.to_patch_tokens = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim)
+        )
+
+    def forward(self, x):
+        shifts = ((1, -1, 0, 0), (-1, 1, 0, 0), (0, 0, 1, -1), (0, 0, -1, 1))
+        shifted_x = list(map(lambda shift: F.pad(x, shift), shifts))
+        x_with_shifts = torch.cat((x, *shifted_x), dim = 1)
+        return self.to_patch_tokens(x_with_shifts)
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = SPT(dim = dim, patch_size = patch_size, channels = channels)
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/vit_with_patch_dropout.py

@@ -0,0 +1,147 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class PatchDropout(nn.Module):
+    def __init__(self, prob):
+        super().__init__()
+        assert 0 <= prob < 1.
+        self.prob = prob
+
+    def forward(self, x):
+        if not self.training or self.prob == 0.:
+            return x
+
+        b, n, _, device = *x.shape, x.device
+
+        batch_indices = torch.arange(b, device = device)
+        batch_indices = rearrange(batch_indices, '... -> ... 1')
+        num_patches_keep = max(1, int(n * (1 - self.prob)))
+        patch_indices_keep = torch.randn(b, n, device = device).topk(num_patches_keep, dim = -1).indices
+
+        return x[batch_indices, patch_indices_keep]
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        x = self.norm(x)
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., patch_dropout = 0.25):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(num_patches, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+
+        self.patch_dropout = PatchDropout(patch_dropout)
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        x += self.pos_embedding
+
+        x = self.patch_dropout(x)
+
+        cls_tokens = repeat(self.cls_token, '1 1 d -> b 1 d', b = b)
+
+        x = torch.cat((cls_tokens, x), dim=1)
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/vit_with_patch_merger.py

@@ -0,0 +1,144 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val ,d):
+    return val if exists(val) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# patch merger class
+
+class PatchMerger(nn.Module):
+    def __init__(self, dim, num_tokens_out):
+        super().__init__()
+        self.scale = dim ** -0.5
+        self.norm = nn.LayerNorm(dim)
+        self.queries = nn.Parameter(torch.randn(num_tokens_out, dim))
+
+    def forward(self, x):
+        x = self.norm(x)
+        sim = torch.matmul(self.queries, x.transpose(-1, -2)) * self.scale
+        attn = sim.softmax(dim = -1)
+        return torch.matmul(attn, x)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        x = self.norm(x)
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0., patch_merge_layer = None, patch_merge_num_tokens = 8):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+
+        self.patch_merge_layer_index = default(patch_merge_layer, depth // 2) - 1 # default to mid-way through transformer, as shown in paper
+        self.patch_merger = PatchMerger(dim = dim, num_tokens_out = patch_merge_num_tokens)
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+    def forward(self, x):
+        for index, (attn, ff) in enumerate(self.layers):
+            x = attn(x) + x
+            x = ff(x) + x
+
+            if index == self.patch_merge_layer_index:
+                x = self.patch_merger(x)
+
+        return self.norm(x)
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, patch_merge_layer = None, patch_merge_num_tokens = 8, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout, patch_merge_layer, patch_merge_num_tokens)
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b n d -> b d', 'mean'),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        x += self.pos_embedding[:, :n]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        return self.mlp_head(x)

vit_pytorch/vivit.py

@@ -0,0 +1,178 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat, reduce
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        x = self.norm(x)
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return self.norm(x)
+
+class ViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        image_patch_size,
+        frames,
+        frame_patch_size,
+        num_classes,
+        dim,
+        spatial_depth,
+        temporal_depth,
+        heads,
+        mlp_dim,
+        pool = 'cls',
+        channels = 3,
+        dim_head = 64,
+        dropout = 0.,
+        emb_dropout = 0.
+    ):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(image_patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        assert frames % frame_patch_size == 0, 'Frames must be divisible by frame patch size'
+
+        num_image_patches = (image_height // patch_height) * (image_width // patch_width)
+        num_frame_patches = (frames // frame_patch_size)
+
+        patch_dim = channels * patch_height * patch_width * frame_patch_size
+
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.global_average_pool = pool == 'mean'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f (h w) (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_frame_patches, num_image_patches, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.spatial_cls_token = nn.Parameter(torch.randn(1, 1, dim)) if not self.global_average_pool else None
+        self.temporal_cls_token = nn.Parameter(torch.randn(1, 1, dim)) if not self.global_average_pool else None
+
+        self.spatial_transformer = Transformer(dim, spatial_depth, heads, dim_head, mlp_dim, dropout)
+        self.temporal_transformer = Transformer(dim, temporal_depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Linear(dim, num_classes)
+
+    def forward(self, video):
+        x = self.to_patch_embedding(video)
+        b, f, n, _ = x.shape
+
+        x = x + self.pos_embedding[:, :f, :n]
+
+        if exists(self.spatial_cls_token):
+            spatial_cls_tokens = repeat(self.spatial_cls_token, '1 1 d -> b f 1 d', b = b, f = f)
+            x = torch.cat((spatial_cls_tokens, x), dim = 2)
+
+        x = self.dropout(x)
+
+        x = rearrange(x, 'b f n d -> (b f) n d')
+
+        # attend across space
+
+        x = self.spatial_transformer(x)
+
+        x = rearrange(x, '(b f) n d -> b f n d', b = b)
+
+        # excise out the spatial cls tokens or average pool for temporal attention
+
+        x = x[:, :, 0] if not self.global_average_pool else reduce(x, 'b f n d -> b f d', 'mean')
+
+        # append temporal CLS tokens
+
+        if exists(self.temporal_cls_token):
+            temporal_cls_tokens = repeat(self.temporal_cls_token, '1 1 d-> b 1 d', b = b)
+
+            x = torch.cat((temporal_cls_tokens, x), dim = 1)
+
+        # attend across time
+
+        x = self.temporal_transformer(x)
+
+        # excise out temporal cls token or average pool
+
+        x = x[:, 0] if not self.global_average_pool else reduce(x, 'b f d -> b d', 'mean')
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)