add adaptive token sampling paper

add Table of Contents

README.md

@@ -1,5 +1,36 @@
 <img src="./images/vit.gif" width="500px"></img>
 
+## Table of Contents
+
+- [Vision Transformer - Pytorch](#vision-transformer---pytorch)
+- [Install](#install)
+- [Usage](#usage)
+- [Parameters](#parameters)
+- [Distillation](#distillation)
+- [Deep ViT](#deep-vit)
+- [CaiT](#cait)
+- [Token-to-Token ViT](#token-to-token-vit)
+- [CCT](#cct)
+- [Cross ViT](#cross-vit)
+- [PiT](#pit)
+- [LeViT](#levit)
+- [CvT](#cvt)
+- [Twins SVT](#twins-svt)
+- [CrossFormer](#crossformer)
+- [RegionViT](#regionvit)
+- [NesT](#nest)
+- [Masked Autoencoder](#masked-autoencoder)
+- [Simple Masked Image Modeling](#simple-masked-image-modeling)
+- [Masked Patch Prediction](#masked-patch-prediction)
+- [Dino](#dino)
+- [Accessing Attention](#accessing-attention)
+- [Research Ideas](#research-ideas)
+  * [Efficient Attention](#efficient-attention)
+  * [Combining with other Transformer improvements](#combining-with-other-transformer-improvements)
+- [FAQ](#faq)
+- [Resources](#resources)
+- [Citations](#citations)
+
 ## Vision Transformer - Pytorch
 
 Implementation of <a href="https://openreview.net/pdf?id=YicbFdNTTy">Vision Transformer</a>, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch. Significance is further explained in <a href="https://www.youtube.com/watch?v=TrdevFK_am4">Yannic Kilcher's</a> video. There's really not much to code here, but may as well lay it out for everyone so we expedite the attention revolution.
@@ -38,6 +69,7 @@ preds = v(img) # (1, 1000)
 ```
 
 ## Parameters
+
 - `image_size`: int.  
 Image size. If you have rectangular images, make sure your image size is the maximum of the width and height
 - `patch_size`: int.  
@@ -61,6 +93,7 @@ Dropout rate.
 Embedding dropout rate.
 - `pool`: string, either `cls` token pooling or `mean` pooling
 
+
 ## Distillation
 
 <img src="./images/distill.png" width="300px"></img>
@@ -93,7 +126,8 @@ distiller = DistillWrapper(
     student = v,
     teacher = teacher,
     temperature = 3,           # temperature of distillation
-    alpha = 0.5                # trade between main loss and distillation loss
+    alpha = 0.5,               # trade between main loss and distillation loss
+    hard = False               # whether to use soft or hard distillation
 )
 
 img = torch.randn(2, 3, 256, 256)
@@ -116,6 +150,7 @@ v = v.to_vit()
 type(v) # <class 'vit_pytorch.vit_pytorch.ViT'>
 ```
 
+
 ## Deep ViT
 
 This <a href="https://arxiv.org/abs/2103.11886">paper</a> notes that ViT struggles to attend at greater depths (past 12 layers), and suggests mixing the attention of each head post-softmax as a solution, dubbed Re-attention. The results line up with the <a href="https://github.com/lucidrains/x-transformers#talking-heads-attention">Talking Heads</a> paper from NLP.
@@ -143,6 +178,37 @@ img = torch.randn(1, 3, 256, 256)
 preds = v(img) # (1, 1000)
 ```
 
+## CaiT
+
+<a href="https://arxiv.org/abs/2103.17239">This paper</a> also notes difficulty in training vision transformers at greater depths and proposes two solutions. First it proposes to do per-channel multiplication of the output of the residual block. Second, it proposes to have the patches attend to one another, and only allow the CLS token to attend to the patches in the last few layers.
+
+They also add <a href="https://github.com/lucidrains/x-transformers#talking-heads-attention">Talking Heads</a>, noting improvements
+
+You can use this scheme as follows
+
+```python
+import torch
+from vit_pytorch.cait import CaiT
+
+v = CaiT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 12,             # depth of transformer for patch to patch attention only
+    cls_depth = 2,          # depth of cross attention of CLS tokens to patch
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1,
+    layer_dropout = 0.05    # randomly dropout 5% of the layers
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+```
+
 ## Token-to-Token ViT
 
 <img src="./images/t2t.png" width="400px"></img>
@@ -164,7 +230,407 @@ v = T2TViT(
 )
 
 img = torch.randn(1, 3, 224, 224)
-v(img) # (1, 1000)
+
+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
+by using convolutions instead of patching and performing sequence pooling. This
+allows for CCT to have high accuracy and a low number of parameters.
+
+You can use this with two methods
+```python
+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']
+        )
+```
+
+Alternatively you can use one of several pre-defined models `[2,4,6,7,8,14,16]`
+which pre-define the number of layers, number of attention heads, the mlp ratio,
+and the embedding dimension.
+
+```python
+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']  
+        )
+```
+<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>
+
+<a href="https://arxiv.org/abs/2103.14899">This paper</a> proposes to have two vision transformers processing the image at different scales, cross attending to one every so often. They show improvements on top of the base vision transformer.
+
+```python
+import torch
+from vit_pytorch.cross_vit import CrossViT
+
+v = CrossViT(
+    image_size = 256,
+    num_classes = 1000,
+    depth = 4,               # number of multi-scale encoding blocks
+    sm_dim = 192,            # high res dimension
+    sm_patch_size = 16,      # high res patch size (should be smaller than lg_patch_size)
+    sm_enc_depth = 2,        # high res depth
+    sm_enc_heads = 8,        # high res heads
+    sm_enc_mlp_dim = 2048,   # high res feedforward dimension
+    lg_dim = 384,            # low res dimension
+    lg_patch_size = 64,      # low res patch size
+    lg_enc_depth = 3,        # low res depth
+    lg_enc_heads = 8,        # low res heads
+    lg_enc_mlp_dim = 2048,   # low res feedforward dimensions
+    cross_attn_depth = 2,    # cross attention rounds
+    cross_attn_heads = 8,    # cross attention heads
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+pred = v(img) # (1, 1000)
+```
+
+## PiT
+
+<img src="./images/pit.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2103.16302">This paper</a> proposes to downsample the tokens through a pooling procedure using depth-wise convolutions.
+
+```python
+import torch
+from vit_pytorch.pit import PiT
+
+v = PiT(
+    image_size = 224,
+    patch_size = 14,
+    dim = 256,
+    num_classes = 1000,
+    depth = (3, 3, 3),     # list of depths, indicating the number of rounds of each stage before a downsample
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+# forward pass now returns predictions and the attention maps
+
+img = torch.randn(1, 3, 224, 224)
+
+preds = v(img) # (1, 1000)
+```
+
+## LeViT
+
+<img src="./images/levit.png" width="300px"></img>
+
+<a href="https://arxiv.org/abs/2104.01136">This paper</a> proposes a number of changes, including (1) convolutional embedding instead of patch-wise projection (2) downsampling in stages (3) extra non-linearity in attention (4) 2d relative positional biases instead of initial absolute positional bias (5) batchnorm in place of layernorm.
+
+<a href="https://github.com/facebookresearch/LeViT">Official repository</a>
+
+```python
+import torch
+from vit_pytorch.levit import LeViT
+
+levit = LeViT(
+    image_size = 224,
+    num_classes = 1000,
+    stages = 3,             # number of stages
+    dim = (256, 384, 512),  # dimensions at each stage
+    depth = 4,              # transformer of depth 4 at each stage
+    heads = (4, 6, 8),      # heads at each stage
+    mlp_mult = 2,
+    dropout = 0.1
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+levit(img) # (1, 1000)
+```
+
+## CvT
+
+<img src="./images/cvt.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2103.15808">This paper</a> proposes mixing convolutions and attention. Specifically, convolutions are used to embed and downsample the image / feature map in three stages. Depthwise-convoltion is also used to project the queries, keys, and values for attention.
+
+```python
+import torch
+from vit_pytorch.cvt import CvT
+
+v = CvT(
+    num_classes = 1000,
+    s1_emb_dim = 64,        # stage 1 - dimension
+    s1_emb_kernel = 7,      # stage 1 - conv kernel
+    s1_emb_stride = 4,      # stage 1 - conv stride
+    s1_proj_kernel = 3,     # stage 1 - attention ds-conv kernel size
+    s1_kv_proj_stride = 2,  # stage 1 - attention key / value projection stride
+    s1_heads = 1,           # stage 1 - heads
+    s1_depth = 1,           # stage 1 - depth
+    s1_mlp_mult = 4,        # stage 1 - feedforward expansion factor
+    s2_emb_dim = 192,       # stage 2 - (same as above)
+    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,       # stage 3 - (same as above)
+    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.
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = v(img) # (1, 1000)
+```
+
+## Twins SVT
+
+<img src="./images/twins_svt.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2104.13840">paper</a> proposes mixing local and global attention, along with position encoding generator (proposed in <a href="https://arxiv.org/abs/2102.10882">CPVT</a>) and global average pooling, to achieve the same results as <a href="https://arxiv.org/abs/2103.14030">Swin</a>, without the extra complexity of shifted windows, CLS tokens, nor positional embeddings.
+
+```python
+import torch
+from vit_pytorch.twins_svt import TwinsSVT
+
+model = TwinsSVT(
+    num_classes = 1000,       # number of output classes
+    s1_emb_dim = 64,          # stage 1 - patch embedding projected dimension
+    s1_patch_size = 4,        # stage 1 - patch size for patch embedding
+    s1_local_patch_size = 7,  # stage 1 - patch size for local attention
+    s1_global_k = 7,          # stage 1 - global attention key / value reduction factor, defaults to 7 as specified in paper
+    s1_depth = 1,             # stage 1 - number of transformer blocks (local attn -> ff -> global attn -> ff)
+    s2_emb_dim = 128,         # stage 2 (same as above)
+    s2_patch_size = 2,
+    s2_local_patch_size = 7,
+    s2_global_k = 7,
+    s2_depth = 1,
+    s3_emb_dim = 256,         # stage 3 (same as above)
+    s3_patch_size = 2,
+    s3_local_patch_size = 7,
+    s3_global_k = 7,
+    s3_depth = 5,
+    s4_emb_dim = 512,         # stage 4 (same as above)
+    s4_patch_size = 2,
+    s4_local_patch_size = 7,
+    s4_global_k = 7,
+    s4_depth = 4,
+    peg_kernel_size = 3,      # positional encoding generator kernel size
+    dropout = 0.              # dropout
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = model(img) # (1, 1000)
+```
+
+## RegionViT
+
+<img src="./images/regionvit.png" width="400px"></img>
+
+<img src="./images/regionvit2.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2106.02689">This paper</a> proposes to divide up the feature map into local regions, whereby the local tokens attend to each other. Each local region has its own regional token which then attends to all its local tokens, as well as other regional tokens.
+
+You can use it as follows
+
+```python
+import torch
+from vit_pytorch.regionvit import RegionViT
+
+model = RegionViT(
+    dim = (64, 128, 256, 512),      # tuple of size 4, indicating dimension at each stage
+    depth = (2, 2, 8, 2),           # depth of the region to local transformer at each stage
+    window_size = 7,                # window size, which should be either 7 or 14
+    num_classes = 1000,             # number of output classes
+    tokenize_local_3_conv = False,  # whether to use a 3 layer convolution to encode the local tokens from the image. the paper uses this for the smaller models, but uses only 1 conv (set to False) for the larger models
+    use_peg = False,                # whether to use positional generating module. they used this for object detection for a boost in performance
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = model(img) # (1, 1000)
+```
+
+## CrossFormer
+
+<img src="./images/crossformer.png" width="400px"></img>
+
+<img src="./images/crossformer2.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2108.00154">paper</a> beats PVT and Swin using alternating local and global attention. The global attention is done across the windowing dimension for reduced complexity, much like the scheme used for axial attention.
+
+They also have cross-scale embedding layer, which they shown to be a generic layer that can improve all vision transformers. Dynamic relative positional bias was also formulated to allow the net to generalize to images of greater resolution.
+
+```python
+import torch
+from vit_pytorch.crossformer import CrossFormer
+
+model = CrossFormer(
+    num_classes = 1000,                # number of output classes
+    dim = (64, 128, 256, 512),         # dimension at each stage
+    depth = (2, 2, 8, 2),              # depth of transformer at each stage
+    global_window_size = (8, 4, 2, 1), # global window sizes at each stage
+    local_window_size = 7,             # local window size (can be customized for each stage, but in paper, held constant at 7 for all stages)
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = model(img) # (1, 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.
+
+You can use it with the following code (ex. NesT-T)
+
+```python
+import torch
+from vit_pytorch.nest import NesT
+
+nest = NesT(
+    image_size = 224,
+    patch_size = 4,
+    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
+    num_classes = 1000
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = nest(img) # (1, 1000)
+```
+
+## Simple Masked Image Modeling
+
+<img src="./images/simmim.png" width="400px"/>
+
+This <a href="https://arxiv.org/abs/2111.09886">paper</a> proposes a simple masked image modeling (SimMIM) scheme, using only a linear projection off the masked tokens into pixel space followed by an L1 loss with the pixel values of the masked patches. Results are competitive with other more complicated approaches.
+
+You can use this as follows
+
+```python
+import torch
+from vit_pytorch import ViT
+from vit_pytorch.simmim import SimMIM
+
+v = ViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048
+)
+
+mim = SimMIM(
+    encoder = v,
+    masking_ratio = 0.5  # they found 50% to yield the best results
+)
+
+images = torch.randn(8, 3, 256, 256)
+
+loss = mim(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
+
+torch.save(v.state_dict(), './trained-vit.pt')
+```
+
+
+## Masked Autoencoder
+
+<img src="./images/mae.png" width="400px"/>
+
+A new <a href="https://arxiv.org/abs/2111.06377">Kaiming He paper</a> proposes a simple autoencoder scheme where the vision transformer attends to a set of unmasked patches, and a smaller decoder tries to reconstruct the masked pixel values.
+
+<a href="https://www.youtube.com/watch?v=LKixq2S2Pz8">DeepReader quick paper review</a>
+
+<a href="https://www.youtube.com/watch?v=Dp6iICL2dVI">AI Coffeebreak with Letitia</a>
+
+You can use it with the following code
+
+```python
+import torch
+from vit_pytorch import ViT, MAE
+
+v = ViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048
+)
+
+mae = MAE(
+    encoder = v,
+    masking_ratio = 0.75,   # the paper recommended 75% masked patches
+    decoder_dim = 512,      # paper showed good results with just 512
+    decoder_depth = 6       # anywhere from 1 to 8
+)
+
+images = torch.randn(8, 3, 256, 256)
+
+loss = mae(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')
 ```
 
 ## Masked Patch Prediction
@@ -200,7 +666,7 @@ mpp_trainer = MPP(
 opt = torch.optim.Adam(mpp_trainer.parameters(), lr=3e-4)
 
 def sample_unlabelled_images():
-    return torch.randn(20, 3, 256, 256)
+    return torch.FloatTensor(20, 3, 256, 256).uniform_(0., 1.)
 
 for _ in range(100):
     images = sample_unlabelled_images()
@@ -213,6 +679,93 @@ for _ in range(100):
 torch.save(model.state_dict(), './pretrained-net.pt')
 ```
 
+## Adaptive Token Sampling
+
+<img src="./images/ats.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2111.15667">paper</a> proposes to use the CLS attention scores, re-weighed by the norms of the value heads, as means to discard unimportant tokens at different layers.
+
+```python
+import torch
+from vit_pytorch.ats_vit import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 16,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    max_tokens_per_depth = (256, 128, 64, 32, 16, 8), # a tuple that denotes the maximum number of tokens that any given layer should have. if the layer has greater than this amount, it will undergo adaptive token sampling
+    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 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)
+```
+
+## Dino
+
+<img src="./images/dino.png" width="350px"></img>
+
+You can train `ViT` with the recent SOTA self-supervised learning technique, <a href="https://arxiv.org/abs/2104.14294">Dino</a>, with the following code.
+
+<a href="https://www.youtube.com/watch?v=h3ij3F3cPIk">Yannic Kilcher</a> video
+
+```python
+import torch
+from vit_pytorch import ViT, Dino
+
+model = ViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048
+)
+
+learner = Dino(
+    model,
+    image_size = 256,
+    hidden_layer = 'to_latent',        # 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.Adam(learner.parameters(), lr = 3e-4)
+
+def sample_unlabelled_images():
+    return torch.randn(20, 3, 256, 256)
+
+for _ in range(100):
+    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(model.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
@@ -256,56 +809,6 @@ v = v.eject()  # wrapper is discarded and original ViT instance is returned
 
 ## Research Ideas
 
-### Self Supervised Training
-
-You can train this with a near SOTA self-supervised learning technique, <a href="https://github.com/lucidrains/byol-pytorch">BYOL</a>, with the following code.
-
-(1)
-```bash
-$ pip install byol-pytorch
-```
-
-(2)
-```python
-import torch
-from vit_pytorch import ViT
-from byol_pytorch import BYOL
-
-model = ViT(
-    image_size = 256,
-    patch_size = 32,
-    num_classes = 1000,
-    dim = 1024,
-    depth = 6,
-    heads = 8,
-    mlp_dim = 2048
-)
-
-learner = BYOL(
-    model,
-    image_size = 256,
-    hidden_layer = 'to_latent'
-)
-
-opt = torch.optim.Adam(learner.parameters(), lr=3e-4)
-
-def sample_unlabelled_images():
-    return torch.randn(20, 3, 256, 256)
-
-for _ in range(100):
-    images = sample_unlabelled_images()
-    loss = learner(images)
-    opt.zero_grad()
-    loss.backward()
-    opt.step()
-    learner.update_moving_average() # update moving average of target encoder
-
-# save your improved network
-torch.save(model.state_dict(), './pretrained-net.pt')
-```
-
-A pytorch-lightning script is ready for you to use at the repository link above.
-
 ### Efficient Attention
 
 There may be some coming from computer vision who think attention still suffers from quadratic costs. Fortunately, we have a lot of new techniques that may help. This repository offers a way for you to plugin your own sparse attention transformer.
@@ -375,6 +878,58 @@ img = torch.randn(1, 3, 224, 224)
 v(img) # (1, 1000)
 ```
 
+## FAQ
+
+- How do I pass in non-square images?
+
+You can already pass in non-square images - you just have to make sure your height and width is less than or equal to the `image_size`, and both divisible by the `patch_size`
+
+ex.
+
+```python
+import torch
+from vit_pytorch import ViT
+
+v = ViT(
+    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
+)
+
+img = torch.randn(1, 3, 256, 128) # <-- not a square
+
+preds = v(img) # (1, 1000)
+```
+
+- How do I pass in non-square patches?
+
+```python
+import torch
+from vit_pytorch import ViT
+
+v = ViT(
+    num_classes = 1000,
+    image_size = (256, 128),  # image size is a tuple of (height, width)
+    patch_size = (32, 16),    # patch size is a tuple of (height, width)
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 128)
+
+preds = v(img)
+```
+
 ## Resources
 
 Coming from computer vision and new to transformers? Here are some resources that greatly accelerated my learning.
@@ -387,6 +942,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 
 
 ## Citations
+```bibtex
+@article{hassani2021escaping,
+    title   = {Escaping the Big Data Paradigm with Compact Transformers},
+    author  = {Ali Hassani and Steven Walton and Nikhil Shah and Abulikemu Abuduweili and Jiachen Li and Humphrey Shi},
+    year    = 2021,
+    url     = {https://arxiv.org/abs/2104.05704},
+    eprint  = {2104.05704},
+    archiveprefix = {arXiv},
+    primaryclass = {cs.CV}
+}
+```
 
 ```bibtex
 @misc{dosovitskiy2020image,
@@ -412,10 +978,10 @@ Coming from computer vision and new to transformers? Here are some resources tha
 
 ```bibtex
 @misc{yuan2021tokenstotoken,
-    title     = {Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet},
-    author    = {Li Yuan and Yunpeng Chen and Tao Wang and Weihao Yu and Yujun Shi and Francis EH Tay and Jiashi Feng and Shuicheng Yan},
-    year      = {2021},
-    eprint    = {2101.11986},
+    title   = {Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet},
+    author  = {Li Yuan and Yunpeng Chen and Tao Wang and Weihao Yu and Yujun Shi and Francis EH Tay and Jiashi Feng and Shuicheng Yan},
+    year    = {2021},
+    eprint  = {2101.11986},
     archivePrefix = {arXiv},
     primaryClass = {cs.CV}
 }
@@ -432,6 +998,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{touvron2021going,
+    title   = {Going deeper with Image Transformers}, 
+    author  = {Hugo Touvron and Matthieu Cord and Alexandre Sablayrolles and Gabriel Synnaeve and Hervé Jégou},
+    year    = {2021},
+    eprint  = {2103.17239},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{chen2021crossvit,
     title   = {CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification},
@@ -454,6 +1031,138 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{heo2021rethinking,
+    title   = {Rethinking Spatial Dimensions of Vision Transformers}, 
+    author  = {Byeongho Heo and Sangdoo Yun and Dongyoon Han and Sanghyuk Chun and Junsuk Choe and Seong Joon Oh},
+    year    = {2021},
+    eprint  = {2103.16302},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{graham2021levit,
+    title   = {LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference},
+    author  = {Ben Graham and Alaaeldin El-Nouby and Hugo Touvron and Pierre Stock and Armand Joulin and Hervé Jégou and Matthijs Douze},
+    year    = {2021},
+    eprint  = {2104.01136},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{li2021localvit,
+    title   = {LocalViT: Bringing Locality to Vision Transformers},
+    author  = {Yawei Li and Kai Zhang and Jiezhang Cao and Radu Timofte and Luc Van Gool},
+    year    = {2021},
+    eprint  = {2104.05707},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{chu2021twins,
+    title   = {Twins: Revisiting Spatial Attention Design in Vision Transformers},
+    author  = {Xiangxiang Chu and Zhi Tian and Yuqing Wang and Bo Zhang and Haibing Ren and Xiaolin Wei and Huaxia Xia and Chunhua Shen},
+    year    = {2021},
+    eprint  = {2104.13840},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{su2021roformer,
+    title   = {RoFormer: Enhanced Transformer with Rotary Position Embedding}, 
+    author  = {Jianlin Su and Yu Lu and Shengfeng Pan and Bo Wen and Yunfeng Liu},
+    year    = {2021},
+    eprint  = {2104.09864},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CL}
+}
+```
+
+```bibtex
+@misc{zhang2021aggregating,
+    title   = {Aggregating Nested Transformers},
+    author  = {Zizhao Zhang and Han Zhang and Long Zhao and Ting Chen and Tomas Pfister},
+    year    = {2021},
+    eprint  = {2105.12723},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{chen2021regionvit,
+    title   = {RegionViT: Regional-to-Local Attention for Vision Transformers}, 
+    author  = {Chun-Fu Chen and Rameswar Panda and Quanfu Fan},
+    year    = {2021},
+    eprint  = {2106.02689},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{wang2021crossformer,
+    title   = {CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention}, 
+    author  = {Wenxiao Wang and Lu Yao and Long Chen and Binbin Lin and Deng Cai and Xiaofei He and Wei Liu},
+    year    = {2021},
+    eprint  = {2108.00154},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{caron2021emerging,
+    title   = {Emerging Properties in Self-Supervised Vision Transformers},
+    author  = {Mathilde Caron and Hugo Touvron and Ishan Misra and Hervé Jégou and Julien Mairal and Piotr Bojanowski and Armand Joulin},
+    year    = {2021},
+    eprint  = {2104.14294},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{he2021masked,
+    title   = {Masked Autoencoders Are Scalable Vision Learners}, 
+    author  = {Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Dollár and Ross Girshick},
+    year    = {2021},
+    eprint  = {2111.06377},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{xie2021simmim,
+    title   = {SimMIM: A Simple Framework for Masked Image Modeling}, 
+    author  = {Zhenda Xie and Zheng Zhang and Yue Cao and Yutong Lin and Jianmin Bao and Zhuliang Yao and Qi Dai and Han Hu},
+    year    = {2021},
+    eprint  = {2111.09886},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{fayyaz2021ats,
+    title   = {ATS: Adaptive Token Sampling For Efficient Vision Transformers},
+    author  = {Mohsen Fayyaz and Soroush Abbasi Kouhpayegani and Farnoush Rezaei Jafari and Eric Sommerlade and Hamid Reza Vaezi Joze and Hamed Pirsiavash and Juergen Gall},
+    year    = {2021},
+    eprint  = {2111.15667},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{vaswani2017attention,
     title   = {Attention Is All You Need},

examples/cats_and_dogs.ipynb

@@ -364,9 +364,8 @@
     "\n",
     "val_transforms = transforms.Compose(\n",
     "    [\n",
-    "        transforms.Resize((224, 224)),\n",
-    "        transforms.RandomResizedCrop(224),\n",
-    "        transforms.RandomHorizontalFlip(),\n",
+    "        transforms.Resize(256),\n",
+    "        transforms.CenterCrop(224),\n",
     "        transforms.ToTensor(),\n",
     "    ]\n",
     ")\n",
@@ -374,9 +373,8 @@
     "\n",
     "test_transforms = transforms.Compose(\n",
     "    [\n",
-    "        transforms.Resize((224, 224)),\n",
-    "        transforms.RandomResizedCrop(224),\n",
-    "        transforms.RandomHorizontalFlip(),\n",
+    "        transforms.Resize(256),\n",
+    "        transforms.CenterCrop(224),\n",
     "        transforms.ToTensor(),\n",
     "    ]\n",
     ")\n"
@@ -6250,4 +6248,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 1
-}
+}

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.12.0',
+  version = '0.24.3',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',
@@ -15,8 +15,9 @@ setup(
     'image recognition'
   ],
   install_requires=[
+    'einops>=0.3',
     'torch>=1.6',
-    'einops>=0.3'
+    'torchvision'
   ],
   classifiers=[
     'Development Status :: 4 - Beta',

vit_pytorch/__init__.py

@@ -1 +1,3 @@
 from vit_pytorch.vit import ViT
+from vit_pytorch.mae import MAE
+from vit_pytorch.dino import Dino

vit_pytorch/ats_vit.py

@@ -0,0 +1,262 @@
+import torch
+import torch.nn.functional as F
+from torch.nn.utils.rnn import pad_sequence
+from torch import nn, einsum
+
+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)
+
+# adaptive token sampling functions and classes
+
+def log(t, eps = 1e-6):
+    return torch.log(t + eps)
+
+def sample_gumbel(shape, device, dtype, eps = 1e-6):
+    u = torch.empty(shape, device = device, dtype = dtype).uniform_(0, 1)
+    return -log(-log(u, eps), eps)
+
+def batched_index_select(values, indices, dim = 1):
+    value_dims = values.shape[(dim + 1):]
+    values_shape, indices_shape = map(lambda t: list(t.shape), (values, indices))
+    indices = indices[(..., *((None,) * len(value_dims)))]
+    indices = indices.expand(*((-1,) * len(indices_shape)), *value_dims)
+    value_expand_len = len(indices_shape) - (dim + 1)
+    values = values[(*((slice(None),) * dim), *((None,) * value_expand_len), ...)]
+
+    value_expand_shape = [-1] * len(values.shape)
+    expand_slice = slice(dim, (dim + value_expand_len))
+    value_expand_shape[expand_slice] = indices.shape[expand_slice]
+    values = values.expand(*value_expand_shape)
+
+    dim += value_expand_len
+    return values.gather(dim, indices)
+
+class AdaptiveTokenSampling(nn.Module):
+    def __init__(self, output_num_tokens, eps = 1e-6):
+        super().__init__()
+        self.eps = eps
+        self.output_num_tokens = output_num_tokens
+
+    def forward(self, attn, value, mask):
+        heads, output_num_tokens, eps, device, dtype = attn.shape[1], self.output_num_tokens, self.eps, attn.device, attn.dtype
+
+        # first get the attention values for CLS token to all other tokens
+
+        cls_attn = attn[..., 0, 1:]
+
+        # calculate the norms of the values, for weighting the scores, as described in the paper
+
+        value_norms = value[..., 1:, :].norm(dim = -1)
+
+        # weigh the attention scores by the norm of the values, sum across all heads
+
+        cls_attn = einsum('b h n, b h n -> b n', cls_attn, value_norms)
+
+        # normalize to 1
+
+        normed_cls_attn = cls_attn / (cls_attn.sum(dim = -1, keepdim = True) + eps)
+
+        # instead of using inverse transform sampling, going to invert the softmax and use gumbel-max sampling instead
+
+        pseudo_logits = log(normed_cls_attn)
+
+        # mask out pseudo logits for gumbel-max sampling
+
+        mask_without_cls = mask[:, 1:]
+        mask_value = -torch.finfo(attn.dtype).max / 2
+        pseudo_logits = pseudo_logits.masked_fill(~mask_without_cls, mask_value)
+
+        # expand k times, k being the adaptive sampling number
+
+        pseudo_logits = repeat(pseudo_logits, 'b n -> b k n', k = output_num_tokens)
+        pseudo_logits = pseudo_logits + sample_gumbel(pseudo_logits.shape, device = device, dtype = dtype)
+
+        # gumble-max and add one to reserve 0 for padding / mask
+
+        sampled_token_ids = pseudo_logits.argmax(dim = -1) + 1
+
+        # calculate unique using torch.unique and then pad the sequence from the right
+
+        unique_sampled_token_ids_list = [torch.unique(t, sorted = True) for t in torch.unbind(sampled_token_ids)]
+        unique_sampled_token_ids = pad_sequence(unique_sampled_token_ids_list, batch_first = True)
+
+        # calculate the new mask, based on the padding
+
+        new_mask = unique_sampled_token_ids != 0
+
+        # CLS token never gets masked out (gets a value of True)
+
+        new_mask = F.pad(new_mask, (1, 0), value = True)
+
+        # prepend a 0 token id to keep the CLS attention scores
+
+        unique_sampled_token_ids = F.pad(unique_sampled_token_ids, (1, 0), value = 0)
+        expanded_unique_sampled_token_ids = repeat(unique_sampled_token_ids, 'b n -> b h n', h = heads)
+
+        # gather the new attention scores
+
+        new_attn = batched_index_select(attn, expanded_unique_sampled_token_ids, dim = 2)
+
+        # return the sampled attention scores, new mask (denoting padding), as well as the sampled token indices (for the residual)
+        return new_attn, new_mask, unique_sampled_token_ids
+
+# 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.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., output_num_tokens = None):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.output_num_tokens = output_num_tokens
+        self.ats = AdaptiveTokenSampling(output_num_tokens) if exists(output_num_tokens) else None
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, *, mask):
+        num_tokens = x.shape[1]
+
+        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
+
+        if exists(mask):
+            dots_mask = rearrange(mask, 'b i -> b 1 i 1') * rearrange(mask, 'b j -> b 1 1 j')
+            mask_value = -torch.finfo(dots.dtype).max
+            dots = dots.masked_fill(~dots_mask, mask_value)
+
+        attn = self.attend(dots)
+
+        sampled_token_ids = None
+
+        # if adaptive token sampling is enabled
+        # and number of tokens is greater than the number of output tokens
+        if exists(self.output_num_tokens) and (num_tokens - 1) > self.output_num_tokens:
+            attn, mask, sampled_token_ids = self.ats(attn, v, mask = mask)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+
+        return self.to_out(out), mask, sampled_token_ids
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, max_tokens_per_depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        assert len(max_tokens_per_depth) == depth, 'max_tokens_per_depth must be a tuple of length that is equal to the depth of the transformer'
+        assert sorted(max_tokens_per_depth, reverse = True) == list(max_tokens_per_depth), 'max_tokens_per_depth must be in decreasing order'
+        assert min(max_tokens_per_depth) > 0, 'max_tokens_per_depth must have at least 1 token at any layer'
+
+        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))
+            ]))
+
+    def forward(self, x):
+        b, n, device = *x.shape[:2], x.device
+
+        # use mask to keep track of the paddings when sampling tokens
+        # as the duplicates (when sampling) are just removed, as mentioned in the paper
+        mask = torch.ones((b, n), device = device, dtype = torch.bool)
+
+        token_ids = torch.arange(n, device = device)
+        token_ids = repeat(token_ids, 'n -> b n', b = b)
+
+        for attn, ff in self.layers:
+            attn_out, mask, sampled_token_ids = attn(x, mask = mask)
+
+            # when token sampling, one needs to then gather the residual tokens with the sampled token ids
+            if exists(sampled_token_ids):
+                x = batched_index_select(x, sampled_token_ids, dim = 1)
+                token_ids = batched_index_select(token_ids, sampled_token_ids, dim = 1)
+
+            x = x + attn_out
+
+            x = ff(x) + x
+
+        return x, token_ids
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, max_tokens_per_depth, heads, mlp_dim, 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.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, max_tokens_per_depth, heads, dim_head, mlp_dim, dropout)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img, return_sampled_token_ids = False):
+        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, token_ids = self.transformer(x)
+
+        logits = self.mlp_head(x[:, 0])
+
+        if return_sampled_token_ids:
+            # remove CLS token and decrement by 1 to make -1 the padding
+            token_ids = token_ids[:, 1:] - 1
+            return logits, token_ids
+
+        return logits

vit_pytorch/cait.py

@@ -0,0 +1,177 @@
+from random import randrange
+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 dropout_layers(layers, dropout):
+    if dropout == 0:
+        return layers
+
+    num_layers = len(layers)
+    to_drop = torch.zeros(num_layers).uniform_(0., 1.) < dropout
+
+    # make sure at least one layer makes it
+    if all(to_drop):
+        rand_index = randrange(num_layers)
+        to_drop[rand_index] = False
+
+    layers = [layer for (layer, drop) in zip(layers, to_drop) if not drop]
+    return layers
+
+# classes
+
+class LayerScale(nn.Module):
+    def __init__(self, dim, fn, depth):
+        super().__init__()
+        if depth <= 18:  # epsilon detailed in section 2 of paper
+            init_eps = 0.1
+        elif depth > 18 and depth <= 24:
+            init_eps = 1e-5
+        else:
+            init_eps = 1e-6
+
+        scale = torch.zeros(1, 1, dim).fill_(init_eps)
+        self.scale = nn.Parameter(scale)
+        self.fn = fn
+    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.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.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.mix_heads_pre_attn = nn.Parameter(torch.randn(heads, heads))
+        self.mix_heads_post_attn = nn.Parameter(torch.randn(heads, heads))
+
+        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
+
+        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))
+        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
+
+        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 = 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)
+        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., layer_dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        self.layer_dropout = layer_dropout
+
+        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)
+            ]))
+    def forward(self, x, context = None):
+        layers = dropout_layers(self.layers, dropout = self.layer_dropout)
+
+        for attn, ff in layers:
+            x = attn(x, context = context) + x
+            x = ff(x) + x
+        return x
+
+class CaiT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        patch_size,
+        num_classes,
+        dim,
+        depth,
+        cls_depth,
+        heads,
+        mlp_dim,
+        dim_head = 64,
+        dropout = 0.,
+        emb_dropout = 0.,
+        layer_dropout = 0.
+    ):
+        super().__init__()
+        assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
+        num_patches = (image_size // patch_size) ** 2
+        patch_dim = 3 * 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.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.patch_transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout, layer_dropout)
+        self.cls_transformer = Transformer(dim, cls_depth, heads, dim_head, mlp_dim, dropout, layer_dropout)
+
+        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[:, :n]
+        x = self.dropout(x)
+
+        x = self.patch_transformer(x)
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = self.cls_transformer(cls_tokens, context = x)
+
+        return self.mlp_head(x[:, 0])

vit_pytorch/cct.py

@@ -0,0 +1,339 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+# Pre-defined 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 = 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))
+    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)
+
+
+# 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.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).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
+        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
+
+
+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(TransformerEncoderLayer, self).__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) if drop_path_rate > 0 else nn.Identity()
+
+        self.activation = F.gelu
+
+    def forward(self, src: torch.Tensor, *args, **kwargs) -> torch.Tensor:
+        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
+
+    def forward(self, x):
+        return drop_path(x, self.drop_prob, self.training)
+
+
+class Tokenizer(nn.Module):
+    def __init__(self,
+                 kernel_size, stride, padding,
+                 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(Tokenizer, self).__init__()
+
+        n_filter_list = [n_input_channels] + \
+                        [in_planes for _ in range(n_conv_layers - 1)] + \
+                        [n_output_channels]
+
+        self.conv_layers = nn.Sequential(
+            *[nn.Sequential(
+                nn.Conv2d(n_filter_list[i], n_filter_list[i + 1],
+                          kernel_size=(kernel_size, kernel_size),
+                          stride=(stride, stride),
+                          padding=(padding, padding), bias=conv_bias),
+                nn.Identity() if activation is None 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)
+            ])
+
+        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)
+
+    @staticmethod
+    def init_weight(m):
+        if isinstance(m, nn.Conv2d):
+            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__()
+        positional_embedding = positional_embedding if \
+            positional_embedding in ['sine', 'learnable', 'none'] else 'sine'
+        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', \
+            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)
+        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:
+            self.positional_emb = None
+
+        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)])
+        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:
+            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)
+            x = torch.cat((cls_token, x), dim=1)
+
+        if self.positional_emb is not None:
+            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)
+        else:
+            x = x[:, 0]
+
+        x = self.fc(x)
+        return 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:
+                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__()
+
+        self.tokenizer = Tokenizer(n_input_channels=n_input_channels,
+                                   n_output_channels=embedding_dim,
+                                   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,
+                                                           height=img_size,
+                                                           width=img_size),
+            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/crossformer.py

@@ -0,0 +1,263 @@
+import torch
+from torch import nn, einsum
+from einops import rearrange
+from einops.layers.torch import Rearrange, Reduce
+import torch.nn.functional as F
+
+# helpers
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# cross embed layer
+
+class CrossEmbedLayer(nn.Module):
+    def __init__(
+        self,
+        dim_in,
+        dim_out,
+        kernel_sizes,
+        stride = 2
+    ):
+        super().__init__()
+        kernel_sizes = sorted(kernel_sizes)
+        num_scales = len(kernel_sizes)
+
+        # calculate the dimension at each scale
+        dim_scales = [int(dim_out / (2 ** i)) for i in range(1, num_scales)]
+        dim_scales = [*dim_scales, dim_out - sum(dim_scales)]
+
+        self.convs = nn.ModuleList([])
+        for kernel, dim_scale in zip(kernel_sizes, dim_scales):
+            self.convs.append(nn.Conv2d(dim_in, dim_scale, kernel, stride = stride, padding = (kernel - stride) // 2))
+
+    def forward(self, x):
+        fmaps = tuple(map(lambda conv: conv(x), self.convs))
+        return torch.cat(fmaps, dim = 1)
+
+# dynamic positional bias
+
+def DynamicPositionBias(dim):
+    return nn.Sequential(
+        nn.Linear(2, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, 1),
+        Rearrange('... () -> ...')
+    )
+
+# transformer classes
+
+class LayerNorm(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):
+        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (std + self.eps) * self.g + self.b
+
+def FeedForward(dim, mult = 4, dropout = 0.):
+    return nn.Sequential(
+        LayerNorm(dim),
+        nn.Conv2d(dim, dim * mult, 1),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Conv2d(dim * mult, dim, 1)
+    )
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        attn_type,
+        window_size,
+        dim_head = 32,
+        dropout = 0.
+    ):
+        super().__init__()
+        assert attn_type in {'short', 'long'}, 'attention type must be one of local or distant'
+        heads = dim // dim_head
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        inner_dim = dim_head * heads
+
+        self.attn_type = attn_type
+        self.window_size = window_size
+
+        self.norm = LayerNorm(dim)
+        self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
+        self.to_out = nn.Conv2d(inner_dim, dim, 1)
+
+        # positions
+
+        self.dpb = DynamicPositionBias(dim // 4)
+
+        # calculate and store indices for retrieving bias
+
+        pos = torch.arange(window_size)
+        grid = torch.stack(torch.meshgrid(pos, pos))
+        grid = rearrange(grid, 'c i j -> (i j) c')
+        rel_pos = grid[:, None] - grid[None, :]
+        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):
+        *_, height, width, heads, wsz, device = *x.shape, self.heads, self.window_size, x.device
+
+        # prenorm
+
+        x = self.norm(x)
+
+        # rearrange for short or long distance attention
+
+        if self.attn_type == 'short':
+            x = rearrange(x, 'b d (h s1) (w s2) -> (b h w) d s1 s2', s1 = wsz, s2 = wsz)
+        elif self.attn_type == 'long':
+            x = rearrange(x, 'b d (l1 h) (l2 w) -> (b h w) d l1 l2', l1 = wsz, l2 = wsz)
+
+        # 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 (h d) x y -> b h (x y) d', h = heads), (q, k, v))
+        q = q * self.scale
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add dynamic positional bias
+
+        pos = torch.arange(-wsz, wsz + 1, device = device)
+        rel_pos = torch.stack(torch.meshgrid(pos, pos))
+        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]
+
+        sim = sim + rel_pos_bias
+
+        # attend
+
+        attn = sim.softmax(dim = -1)
+
+        # merge heads
+
+        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 = wsz, y = wsz)
+        out = self.to_out(out)
+
+        # rearrange back for long or short distance attention
+
+        if self.attn_type == 'short':
+            out = rearrange(out, '(b h w) d s1 s2 -> b d (h s1) (w s2)', h = height // wsz, w = width // wsz)
+        elif self.attn_type == 'long':
+            out = rearrange(out, '(b h w) d l1 l2 -> b d (l1 h) (l2 w)', h = height // wsz, w = width // wsz)
+
+        return out
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        *,
+        local_window_size,
+        global_window_size,
+        depth = 4,
+        dim_head = 32,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, attn_type = 'short', window_size = local_window_size, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout),
+                Attention(dim, attn_type = 'long', window_size = global_window_size, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout)
+            ]))
+
+    def forward(self, x):
+        for short_attn, short_ff, long_attn, long_ff in self.layers:
+            x = short_attn(x) + x
+            x = short_ff(x) + x
+            x = long_attn(x) + x
+            x = long_ff(x) + x
+
+        return x
+
+# classes
+
+class CrossFormer(nn.Module):
+    def __init__(
+        self,
+        *,
+        dim = (64, 128, 256, 512),
+        depth = (2, 2, 8, 2),
+        global_window_size = (8, 4, 2, 1),
+        local_window_size = 7,
+        cross_embed_kernel_sizes = ((4, 8, 16, 32), (2, 4), (2, 4), (2, 4)),
+        cross_embed_strides = (4, 2, 2, 2),
+        num_classes = 1000,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+        channels = 3
+    ):
+        super().__init__()
+
+        dim = cast_tuple(dim, 4)
+        depth = cast_tuple(depth, 4)
+        global_window_size = cast_tuple(global_window_size, 4)
+        local_window_size = cast_tuple(local_window_size, 4)
+        cross_embed_kernel_sizes = cast_tuple(cross_embed_kernel_sizes, 4)
+        cross_embed_strides = cast_tuple(cross_embed_strides, 4)
+
+        assert len(dim) == 4
+        assert len(depth) == 4
+        assert len(global_window_size) == 4
+        assert len(local_window_size) == 4
+        assert len(cross_embed_kernel_sizes) == 4
+        assert len(cross_embed_strides) == 4
+
+        # dimensions
+
+        last_dim = dim[-1]
+        dims = [channels, *dim]
+        dim_in_and_out = tuple(zip(dims[:-1], dims[1:]))
+
+        # layers
+
+        self.layers = nn.ModuleList([])
+
+        for (dim_in, dim_out), layers, global_wsz, local_wsz, cel_kernel_sizes, cel_stride in zip(dim_in_and_out, depth, global_window_size, local_window_size, cross_embed_kernel_sizes, cross_embed_strides):
+            self.layers.append(nn.ModuleList([
+                CrossEmbedLayer(dim_in, dim_out, cel_kernel_sizes, stride = cel_stride),
+                Transformer(dim_out, local_window_size = local_wsz, global_window_size = global_wsz, depth = layers, attn_dropout = attn_dropout, ff_dropout = ff_dropout)
+            ]))
+
+        # final logits
+
+        self.to_logits = nn.Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(last_dim, num_classes)
+        )
+
+    def forward(self, x):
+        for cel, transformer in self.layers:
+            x = cel(x)
+            x = transformer(x)
+
+        return self.to_logits(x)

vit_pytorch/cvt.py

@@ -22,15 +22,25 @@ def group_by_key_prefix_and_remove_prefix(prefix, d):
 
 # classes
 
+class LayerNorm(nn.Module): # layernorm, but done in the channel dimension #1
+    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):
+        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        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 = nn.LayerNorm(dim)
+        self.norm = LayerNorm(dim)
         self.fn = fn
     def forward(self, x, **kwargs):
-        x = rearrange(x, 'b c h w -> b h w c')
         x = self.norm(x)
-        x = rearrange(x, 'b h w c -> b c h w')
         return self.fn(x, **kwargs)
 
 class FeedForward(nn.Module):
@@ -67,8 +77,8 @@ class Attention(nn.Module):
 
         self.attend = nn.Softmax(dim = -1)
 
-        self.to_q = DepthWiseConv2d(dim, inner_dim, 3, padding = padding, stride = 1, bias = False)
-        self.to_kv = DepthWiseConv2d(dim, inner_dim * 2, 3, padding = padding, stride = kv_proj_stride, bias = False)
+        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)
 
         self.to_out = nn.Sequential(
             nn.Conv2d(inner_dim, dim, 1),
@@ -130,7 +140,7 @@ class CvT(nn.Module):
         s3_emb_stride = 2,
         s3_proj_kernel = 3,
         s3_kv_proj_stride = 2,
-        s3_heads = 4,
+        s3_heads = 6,
         s3_depth = 10,
         s3_mlp_mult = 4,
         dropout = 0.
@@ -146,6 +156,7 @@ class CvT(nn.Module):
 
             layers.append(nn.Sequential(
                 nn.Conv2d(dim, config['emb_dim'], kernel_size = config['emb_kernel'], padding = (config['emb_kernel'] // 2), stride = config['emb_stride']),
+                LayerNorm(config['emb_dim']),
                 Transformer(dim = config['emb_dim'], proj_kernel = config['proj_kernel'], kv_proj_stride = config['kv_proj_stride'], depth = config['depth'], heads = config['heads'], mlp_mult = config['mlp_mult'], dropout = dropout)
             ))
 

vit_pytorch/dino.py

@@ -0,0 +1,303 @@
+import copy
+import random
+from functools import wraps, partial
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+from torchvision import transforms as T
+
+# 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
+
+# loss function # (algorithm 1 in the paper)
+
+def 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 * torch.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):
+        norm = x.norm(dim = 1, keepdim = True).clamp(min = eps)
+        return x / norm
+
+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.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.flatten(1)
+
+    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('projector')
+    def _get_projector(self, hidden):
+        _, dim = hidden.shape
+        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):
+        embed = self.get_embedding(x)
+        if not return_projection:
+            return embed
+
+        projector = self._get_projector(embed)
+        return projector(embed), embed
+
+# main class
+
+class Dino(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_centers', torch.zeros(1, num_classes_K))
+        self.register_buffer('last_teacher_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_centers = self.teacher_centering_ema_updater.update_average(self.teacher_centers, self.last_teacher_centers)
+        self.teacher_centers.copy_(new_teacher_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_proj_one, _ = self.student_encoder(local_image_one)
+        student_proj_two, _ = self.student_encoder(local_image_two)
+
+        with torch.no_grad():
+            teacher_encoder = self._get_teacher_encoder()
+            teacher_proj_one, _ = teacher_encoder(global_image_one)
+            teacher_proj_two, _ = teacher_encoder(global_image_two)
+
+        loss_fn_ = partial(
+            loss_fn,
+            student_temp = default(student_temp, self.student_temp),
+            teacher_temp = default(teacher_temp, self.teacher_temp),
+            centers = self.teacher_centers
+        )
+
+        teacher_logits_avg = torch.cat((teacher_proj_one, teacher_proj_two)).mean(dim = 0)
+        self.last_teacher_centers.copy_(teacher_logits_avg)
+
+        loss = (loss_fn_(teacher_proj_one, student_proj_two) + loss_fn_(teacher_proj_two, student_proj_one)) / 2
+        return loss

vit_pytorch/distill.py

@@ -104,7 +104,8 @@ class DistillWrapper(nn.Module):
         teacher,
         student,
         temperature = 1.,
-        alpha = 0.5
+        alpha = 0.5,
+        hard = False
     ):
         super().__init__()
         assert (isinstance(student, (DistillableViT, DistillableT2TViT, DistillableEfficientViT))) , 'student must be a vision transformer'
@@ -116,6 +117,7 @@ class DistillWrapper(nn.Module):
         num_classes = student.num_classes
         self.temperature = temperature
         self.alpha = alpha
+        self.hard = hard
 
         self.distillation_token = nn.Parameter(torch.randn(1, 1, dim))
 
@@ -137,11 +139,15 @@ class DistillWrapper(nn.Module):
 
         loss = F.cross_entropy(student_logits, labels)
 
-        distill_loss = F.kl_div(
-            F.log_softmax(distill_logits / T, dim = -1),
-            F.softmax(teacher_logits / T, dim = -1).detach(),
-        reduction = 'batchmean')
+        if not self.hard:
+            distill_loss = F.kl_div(
+                F.log_softmax(distill_logits / T, dim = -1),
+                F.softmax(teacher_logits / T, dim = -1).detach(),
+            reduction = 'batchmean')
+            distill_loss *= T ** 2
 
-        distill_loss *= T ** 2
+        else:
+            teacher_labels = teacher_logits.argmax(dim = -1)
+            distill_loss = F.cross_entropy(distill_logits, teacher_labels)
 
-        return loss * alpha + distill_loss * (1 - alpha)
+        return loss * (1 - alpha) + distill_loss * alpha

vit_pytorch/levit.py

@@ -0,0 +1,193 @@
+from math import ceil
+
+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 cast_tuple(val, l = 3):
+    val = val if isinstance(val, tuple) else (val,)
+    return (*val, *((val[-1],) * max(l - len(val), 0)))
+
+def always(val):
+    return lambda *args, **kwargs: val
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mult, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Conv2d(dim, dim * mult, 1),
+            nn.Hardswish(),
+            nn.Dropout(dropout),
+            nn.Conv2d(dim * mult, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, fmap_size, heads = 8, dim_key = 32, dim_value = 64, dropout = 0., dim_out = None, downsample = False):
+        super().__init__()
+        inner_dim_key = dim_key *  heads
+        inner_dim_value = dim_value *  heads
+        dim_out = default(dim_out, dim)
+
+        self.heads = heads
+        self.scale = dim_key ** -0.5
+
+        self.to_q = nn.Sequential(nn.Conv2d(dim, inner_dim_key, 1, stride = (2 if downsample else 1), bias = False), nn.BatchNorm2d(inner_dim_key))
+        self.to_k = nn.Sequential(nn.Conv2d(dim, inner_dim_key, 1, bias = False), nn.BatchNorm2d(inner_dim_key))
+        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)
+
+        out_batch_norm = nn.BatchNorm2d(dim_out)
+        nn.init.zeros_(out_batch_norm.weight)
+
+        self.to_out = nn.Sequential(
+            nn.GELU(),
+            nn.Conv2d(inner_dim_value, dim_out, 1),
+            out_batch_norm,
+            nn.Dropout(dropout)
+        )
+
+        # positional bias
+
+        self.pos_bias = nn.Embedding(fmap_size * fmap_size, heads)
+
+        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, 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()
+
+        x_rel, y_rel = rel_pos.unbind(dim = -1)
+        pos_indices = (x_rel * fmap_size) + y_rel
+
+        self.register_buffer('pos_indices', pos_indices)
+
+    def apply_pos_bias(self, fmap):
+        bias = self.pos_bias(self.pos_indices)
+        bias = rearrange(bias, 'i j h -> () h i j')
+        return fmap + (bias / self.scale)
+
+    def forward(self, x):
+        b, n, *_, h = *x.shape, self.heads
+
+        q = self.to_q(x)
+        y = q.shape[2]
+
+        qkv = (q, self.to_k(x), self.to_v(x))
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) ... -> b h (...) d', h = h), qkv)
+
+        dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+
+        dots = self.apply_pos_bias(dots)
+
+        attn = self.attend(dots)
+
+        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)
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, fmap_size, depth, heads, dim_key, dim_value, mlp_mult = 2, dropout = 0., dim_out = None, downsample = False):
+        super().__init__()
+        dim_out = default(dim_out, dim)
+        self.layers = nn.ModuleList([])
+        self.attn_residual = (not downsample) and dim == dim_out
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, fmap_size = fmap_size, heads = heads, dim_key = dim_key, dim_value = dim_value, dropout = dropout, downsample = downsample, dim_out = dim_out),
+                FeedForward(dim_out, mlp_mult, dropout = dropout)
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            attn_res = (x if self.attn_residual else 0)
+            x = attn(x) + attn_res
+            x = ff(x) + x
+        return x
+
+class LeViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        num_classes,
+        dim,
+        depth,
+        heads,
+        mlp_mult,
+        stages = 3,
+        dim_key = 32,
+        dim_value = 64,
+        dropout = 0.,
+        num_distill_classes = None
+    ):
+        super().__init__()
+
+        dims = cast_tuple(dim, stages)
+        depths = cast_tuple(depth, stages)
+        layer_heads = cast_tuple(heads, stages)
+
+        assert all(map(lambda t: len(t) == stages, (dims, depths, layer_heads))), 'dimensions, depths, and heads must be a tuple that is less than the designated number of stages'
+
+        self.conv_embedding = nn.Sequential(
+            nn.Conv2d(3, 32, 3, stride = 2, padding = 1),
+            nn.Conv2d(32, 64, 3, stride = 2, padding = 1),
+            nn.Conv2d(64, 128, 3, stride = 2, padding = 1),
+            nn.Conv2d(128, dims[0], 3, stride = 2, padding = 1)
+        )
+
+        fmap_size = image_size // (2 ** 4)
+        layers = []
+
+        for ind, dim, depth, heads in zip(range(stages), dims, depths, layer_heads):
+            is_last = ind == (stages - 1)
+            layers.append(Transformer(dim, fmap_size, depth, heads, dim_key, dim_value, mlp_mult, dropout))
+
+            if not is_last:
+                next_dim = dims[ind + 1]
+                layers.append(Transformer(dim, fmap_size, 1, heads * 2, dim_key, dim_value, dim_out = next_dim, downsample = True))
+                fmap_size = ceil(fmap_size / 2)
+
+        self.backbone = nn.Sequential(*layers)
+
+        self.pool = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1),
+            Rearrange('... () () -> ...')
+        )
+
+        self.distill_head = nn.Linear(dim, num_distill_classes) if exists(num_distill_classes) else always(None)
+        self.mlp_head = nn.Linear(dim, num_classes)
+
+    def forward(self, img):
+        x = self.conv_embedding(img)
+
+        x = self.backbone(x)        
+
+        x = self.pool(x)
+
+        out = self.mlp_head(x)
+        distill = self.distill_head(x)
+
+        if exists(distill):
+            return out, distill
+
+        return out

vit_pytorch/local_vit.py

@@ -0,0 +1,152 @@
+from math import sqrt
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# classes
+
+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 ExcludeCLS(nn.Module):
+    def __init__(self, fn):
+        super().__init__()
+        self.fn = fn
+
+    def forward(self, x, **kwargs):
+        cls_token, x = x[:, :1], x[:, 1:]
+        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):
+    def __init__(self, dim_in, dim_out, kernel_size, padding, stride = 1, bias = True):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Conv2d(dim_in, dim_in, kernel_size = kernel_size, padding = padding, groups = dim_in, stride = stride, bias = bias),
+            nn.Conv2d(dim_in, dim_out, kernel_size = 1, bias = bias)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Conv2d(dim, hidden_dim, 1),
+            nn.Hardswish(),
+            DepthWiseConv2d(hidden_dim, hidden_dim, 3, padding = 1),
+            nn.Hardswish(),
+            nn.Dropout(dropout),
+            nn.Conv2d(hidden_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        h = w = int(sqrt(x.shape[-2]))
+        x = rearrange(x, 'b (h w) c -> b c h w', h = h, w = w)
+        x = self.net(x)
+        x = rearrange(x, 'b c h w -> b (h w) c')
+        return x
+
+# 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.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):
+        b, n, _, h = *x.shape, self.heads
+        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)
+
+        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([
+                Residual(PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout))),
+                ExcludeCLS(Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))))
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x)
+            x = ff(x)
+        return x
+
+# main class
+
+class LocalViT(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.):
+        super().__init__()
+        assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
+        num_patches = (image_size // patch_size) ** 2
+        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.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, dropout)
+
+        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)
+
+        return self.mlp_head(x[:, 0])

vit_pytorch/mae.py

@@ -0,0 +1,92 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+from einops import repeat
+
+from vit_pytorch.vit import Transformer
+
+class MAE(nn.Module):
+    def __init__(
+        self,
+        *,
+        encoder,
+        decoder_dim,
+        masking_ratio = 0.75,
+        decoder_depth = 1,
+        decoder_heads = 8,
+        decoder_dim_head = 64
+    ):
+        super().__init__()
+        assert masking_ratio > 0 and masking_ratio < 1, 'masking ratio must be kept between 0 and 1'
+        self.masking_ratio = masking_ratio
+
+        # extract some hyperparameters and functions from encoder (vision transformer to be trained)
+
+        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]
+
+        # decoder parameters
+
+        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)
+        self.decoder_pos_emb = nn.Embedding(num_patches, decoder_dim)
+        self.to_pixels = nn.Linear(decoder_dim, pixel_values_per_patch)
+
+    def forward(self, img):
+        device = img.device
+
+        # get patches
+
+        patches = self.to_patch(img)
+        batch, num_patches, *_ = patches.shape
+
+        # patch to encoder tokens and add positions
+
+        tokens = self.patch_to_emb(patches)
+        tokens = tokens + self.encoder.pos_embedding[:, 1:(num_patches + 1)]
+
+        # calculate of patches needed to be masked, and get random indices, dividing it up for mask vs unmasked
+
+        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:]
+
+        # get the unmasked tokens to be encoded
+
+        batch_range = torch.arange(batch, device = device)[:, None]
+        tokens = tokens[batch_range, unmasked_indices]
+
+        # get the patches to be masked for the final reconstruction loss
+
+        masked_patches = patches[batch_range, masked_indices]
+
+        # attend with vision transformer
+
+        encoded_tokens = self.encoder.transformer(tokens)
+
+        # project encoder to decoder dimensions, if they are not equal - the paper says you can get away with a smaller dimension for decoder
+
+        decoder_tokens = self.enc_to_dec(encoded_tokens)
+
+        # 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)
+        decoded_tokens = self.decoder(decoder_tokens)
+
+        # splice out the mask tokens and project to pixel values
+
+        mask_tokens = decoded_tokens[:, :num_masked]
+        pred_pixel_values = self.to_pixels(mask_tokens)
+
+        # calculate reconstruction loss
+
+        recon_loss = F.mse_loss(pred_pixel_values, masked_patches)
+        return recon_loss

vit_pytorch/mpp.py

@@ -1,20 +1,20 @@
 import math
-from functools import reduce
 
 import torch
 from torch import nn
 import torch.nn.functional as F
 
-from einops import rearrange, repeat
+from einops import rearrange, repeat, reduce
 
 # helpers
 
+def exists(val):
+    return val is not None
 
 def prob_mask_like(t, prob):
     batch, seq_length, _ = t.shape
     return torch.zeros((batch, seq_length)).float().uniform_(0, 1) < prob
 
-
 def get_mask_subset_with_prob(patched_input, prob):
     batch, seq_len, _, device = *patched_input.shape, patched_input.device
     max_masked = math.ceil(prob * seq_len)
@@ -31,43 +31,45 @@ def get_mask_subset_with_prob(patched_input, prob):
 
 
 class MPPLoss(nn.Module):
-    def __init__(self, patch_size, channels, output_channel_bits,
-                 max_pixel_val):
-        super(MPPLoss, self).__init__()
+    def __init__(
+        self,
+        patch_size,
+        channels,
+        output_channel_bits,
+        max_pixel_val,
+        mean,
+        std
+    ):
+        super().__init__()
         self.patch_size = patch_size
         self.channels = channels
         self.output_channel_bits = output_channel_bits
         self.max_pixel_val = max_pixel_val
 
+        self.mean = torch.tensor(mean).view(-1, 1, 1) if mean else None
+        self.std = torch.tensor(std).view(-1, 1, 1) if std else None
+
     def forward(self, predicted_patches, target, mask):
+        p, c, mpv, bits, device = self.patch_size, self.channels, self.max_pixel_val, self.output_channel_bits, target.device
+        bin_size = mpv / (2 ** bits)
+
+        # un-normalize input
+        if exists(self.mean) and exists(self.std):
+            target = target * self.std + self.mean
+
         # reshape target to patches
-        p = self.patch_size
-        target = rearrange(target,
-                           "b c (h p1) (w p2) -> b (h w) c (p1 p2) ",
-                           p1=p,
-                           p2=p)
+        target = target.clamp(max = mpv) # clamp just in case
+        avg_target = reduce(target, 'b c (h p1) (w p2) -> b (h w) c', 'mean', p1 = p, p2 = p).contiguous()
 
-        avg_target = target.mean(dim=3)
-
-        bin_size = self.max_pixel_val / self.output_channel_bits
-        channel_bins = torch.arange(bin_size, self.max_pixel_val, bin_size)
+        channel_bins = torch.arange(bin_size, mpv, bin_size, device = device)
         discretized_target = torch.bucketize(avg_target, channel_bins)
-        discretized_target = F.one_hot(discretized_target,
-                                       self.output_channel_bits)
-        c, bi = self.channels, self.output_channel_bits
-        discretized_target = rearrange(discretized_target,
-                                       "b n c bi -> b n (c bi)",
-                                       c=c,
-                                       bi=bi)
 
-        bin_mask = 2**torch.arange(c * bi - 1, -1,
-                                   -1).to(discretized_target.device,
-                                          discretized_target.dtype)
-        target_label = torch.sum(bin_mask * discretized_target, -1)
+        bin_mask = (2 ** bits) ** torch.arange(0, c, device = device).long()
+        bin_mask = rearrange(bin_mask, 'c -> () () c')
 
-        predicted_patches = predicted_patches[mask]
-        target_label = target_label[mask]
-        loss = F.cross_entropy(predicted_patches, target_label)
+        target_label = torch.sum(bin_mask * discretized_target, dim = -1)
+
+        loss = F.cross_entropy(predicted_patches[mask], target_label[mask])
         return loss
 
 
@@ -75,21 +77,24 @@ class MPPLoss(nn.Module):
 
 
 class MPP(nn.Module):
-    def __init__(self,
-                 transformer,
-                 patch_size,
-                 dim,
-                 output_channel_bits=3,
-                 channels=3,
-                 max_pixel_val=1.0,
-                 mask_prob=0.15,
-                 replace_prob=0.5,
-                 random_patch_prob=0.5):
+    def __init__(
+        self,
+        transformer,
+        patch_size,
+        dim,
+        output_channel_bits=3,
+        channels=3,
+        max_pixel_val=1.0,
+        mask_prob=0.15,
+        replace_prob=0.5,
+        random_patch_prob=0.5,
+        mean=None,
+        std=None
+    ):
         super().__init__()
-
         self.transformer = transformer
         self.loss = MPPLoss(patch_size, channels, output_channel_bits,
-                            max_pixel_val)
+                            max_pixel_val, mean, std)
 
         # output transformation
         self.to_bits = nn.Linear(dim, 2**(output_channel_bits * channels))
@@ -103,7 +108,7 @@ class MPP(nn.Module):
         self.random_patch_prob = random_patch_prob
 
         # token ids
-        self.mask_token = nn.Parameter(torch.randn(1, 1, dim * channels))
+        self.mask_token = nn.Parameter(torch.randn(1, 1, channels * patch_size ** 2))
 
     def forward(self, input, **kwargs):
         transformer = self.transformer
@@ -127,8 +132,9 @@ class MPP(nn.Module):
             random_patch_sampling_prob = self.random_patch_prob / (
                 1 - self.replace_prob)
             random_patch_prob = prob_mask_like(input,
-                                               random_patch_sampling_prob)
-            bool_random_patch_prob = mask * random_patch_prob == True
+                                               random_patch_sampling_prob).to(mask.device)
+
+            bool_random_patch_prob = mask * (random_patch_prob == True)
             random_patches = torch.randint(0,
                                            input.shape[1],
                                            (input.shape[0], input.shape[1]),
@@ -140,7 +146,7 @@ class MPP(nn.Module):
                 bool_random_patch_prob]
 
         # [mask] input
-        replace_prob = prob_mask_like(input, self.replace_prob)
+        replace_prob = prob_mask_like(input, self.replace_prob).to(mask.device)
         bool_mask_replace = (mask * replace_prob) == True
         masked_input[bool_mask_replace] = self.mask_token
 

vit_pytorch/nest.py

@@ -0,0 +1,179 @@
+from functools import partial
+import torch
+from torch import nn, einsum
+
+from einops import rearrange
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def cast_tuple(val, depth):
+    return val if isinstance(val, tuple) else ((val,) * depth)
+
+# classes
+
+class LayerNorm(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):
+        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        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)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mlp_mult = 4, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Conv2d(dim, dim * mlp_mult, 1),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Conv2d(dim * mlp_mult, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dropout = 0.):
+        super().__init__()
+        dim_head = dim // heads
+        inner_dim = dim_head * heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        b, c, h, w, heads = *x.shape, self.heads
+
+        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)
+
+        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)
+        return self.to_out(out)
+
+def Aggregate(dim, dim_out):
+    return nn.Sequential(
+        nn.Conv2d(dim, dim_out, 3, padding = 1),
+        LayerNorm(dim_out),
+        nn.MaxPool2d(3, stride = 2, padding = 1)
+    )
+
+class Transformer(nn.Module):
+    def __init__(self, dim, seq_len, depth, heads, mlp_mult, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        self.pos_emb = nn.Parameter(torch.randn(seq_len))
+
+        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))
+            ]))
+    def forward(self, x):
+        *_, h, w = x.shape
+
+        pos_emb = self.pos_emb[:(h * w)]
+        pos_emb = rearrange(pos_emb, '(h w) -> () () h w', h = h, w = w)
+        x = x + pos_emb
+
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class NesT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        patch_size,
+        num_classes,
+        dim,
+        heads,
+        num_hierarchies,
+        block_repeats,
+        mlp_mult = 4,
+        channels = 3,
+        dim_head = 64,
+        dropout = 0.
+    ):
+        super().__init__()
+        assert (image_size % patch_size) == 0, 'Image dimensions must be divisible by the patch size.'
+        num_patches = (image_size // patch_size) ** 2
+        patch_dim = channels * patch_size ** 2
+        fmap_size = image_size // patch_size
+        blocks = 2 ** (num_hierarchies - 1)
+
+        seq_len = (fmap_size // blocks) ** 2   # sequence length is held constant across heirarchy
+        hierarchies = list(reversed(range(num_hierarchies)))
+        mults = [2 ** i for i in hierarchies]
+
+        layer_heads = list(map(lambda t: t * heads, mults))
+        layer_dims = list(map(lambda t: t * dim, mults))
+
+        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),
+            nn.Conv2d(patch_dim, layer_dims[0], 1),
+        )
+
+        block_repeats = cast_tuple(block_repeats, num_hierarchies)
+
+        self.layers = nn.ModuleList([])
+
+        for level, heads, (dim_in, dim_out), block_repeat in zip(hierarchies, layer_heads, dim_pairs, block_repeats):
+            is_last = level == 0
+            depth = block_repeat
+
+            self.layers.append(nn.ModuleList([
+                Transformer(dim_in, seq_len, depth, heads, mlp_mult, dropout),
+                Aggregate(dim_in, dim_out) if not is_last else nn.Identity()
+            ]))
+
+        self.mlp_head = nn.Sequential(
+            LayerNorm(dim),
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, c, h, w = x.shape
+
+        num_hierarchies = len(self.layers)
+
+        for level, (transformer, aggregate) in zip(reversed(range(num_hierarchies)), self.layers):
+            block_size = 2 ** level
+            x = rearrange(x, 'b c (b1 h) (b2 w) -> (b b1 b2) c h w', b1 = block_size, b2 = block_size)
+            x = transformer(x)
+            x = rearrange(x, '(b b1 b2) c h w -> b c (b1 h) (b2 w)', b1 = block_size, b2 = block_size)
+            x = aggregate(x)
+
+        return self.mlp_head(x)

vit_pytorch/pit.py

@@ -89,8 +89,8 @@ class DepthWiseConv2d(nn.Module):
     def __init__(self, dim_in, dim_out, kernel_size, padding, stride, bias = True):
         super().__init__()
         self.net = nn.Sequential(
-            nn.Conv2d(dim_in, dim_in, kernel_size = kernel_size, padding = padding, groups = dim_in, stride = stride, bias = bias),
-            nn.Conv2d(dim_in, dim_out, kernel_size = 1, bias = bias)
+            nn.Conv2d(dim_in, dim_out, kernel_size = kernel_size, padding = padding, groups = dim_in, stride = stride, bias = bias),
+            nn.Conv2d(dim_out, dim_out, kernel_size = 1, bias = bias)
         )
     def forward(self, x):
         return self.net(x)
@@ -129,14 +129,15 @@ class PiT(nn.Module):
         mlp_dim,
         dim_head = 64,
         dropout = 0.,
-        emb_dropout = 0.
+        emb_dropout = 0.,
+        channels = 3
     ):
         super().__init__()
         assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
         assert isinstance(depth, tuple), 'depth must be a tuple of integers, specifying the number of blocks before each downsizing'
         heads = cast_tuple(heads, len(depth))
 
-        patch_dim = 3 * patch_size ** 2
+        patch_dim = channels * patch_size ** 2
 
         self.to_patch_embedding = nn.Sequential(
             nn.Unfold(kernel_size = patch_size, stride = patch_size // 2),
@@ -162,8 +163,9 @@ class PiT(nn.Module):
                 layers.append(Pool(dim))
                 dim *= 2
 
-        self.layers = nn.Sequential(
-            *layers,
+        self.layers = nn.Sequential(*layers)
+
+        self.mlp_head = nn.Sequential(
             nn.LayerNorm(dim),
             nn.Linear(dim, num_classes)
         )
@@ -174,7 +176,9 @@ class PiT(nn.Module):
 
         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
+        x += self.pos_embedding[:, :n+1]
         x = self.dropout(x)
 
-        return self.layers(x)
+        x = self.layers(x)
+
+        return self.mlp_head(x[:, 0])

vit_pytorch/recorder.py

@@ -8,7 +8,7 @@ def find_modules(nn_module, type):
     return [module for module in nn_module.modules() if isinstance(module, type)]
 
 class Recorder(nn.Module):
-    def __init__(self, vit):
+    def __init__(self, vit, device = None):
         super().__init__()
         self.vit = vit
 
@@ -17,6 +17,7 @@ class Recorder(nn.Module):
         self.hooks = []
         self.hook_registered = False
         self.ejected = False
+        self.device = device
 
     def _hook(self, _, input, output):
         self.recordings.append(output.clone().detach())
@@ -45,10 +46,14 @@ class Recorder(nn.Module):
     def forward(self, img):
         assert not self.ejected, 'recorder has been ejected, cannot be used anymore'
         self.clear()
-
         if not self.hook_registered:
             self._register_hook()
 
         pred = self.vit(img)
-        attns = torch.stack(self.recordings, dim = 1)
+
+        # move all recordings to one device before stacking
+        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)
         return pred, attns

vit_pytorch/regionvit.py

@@ -0,0 +1,263 @@
+import torch
+from torch import nn, einsum
+from einops import rearrange
+from einops.layers.torch import Rearrange, Reduce
+import torch.nn.functional as F
+
+# 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)
+
+def divisible_by(val, d):
+    return (val % d) == 0
+
+# helper classes
+
+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
+
+# transformer classes
+
+def FeedForward(dim, mult = 4, dropout = 0.):
+    return nn.Sequential(
+        nn.LayerNorm(dim),
+        nn.Linear(dim, dim * mult, 1),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Linear(dim * mult, dim, 1)
+    )
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        heads = 4,
+        dim_head = 32,
+        dropout = 0.
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        inner_dim = dim_head * heads
+
+        self.norm = nn.LayerNorm(dim)
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim)
+
+    def forward(self, x, rel_pos_bias = None):
+        h = self.heads
+
+        # prenorm
+
+        x = self.norm(x)
+
+        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))
+        q = q * self.scale
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add relative positional bias for local tokens
+
+        if exists(rel_pos_bias):
+            sim = sim + rel_pos_bias
+
+        attn = sim.softmax(dim = -1)
+
+        # merge heads
+
+        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 R2LTransformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        *,
+        window_size,
+        depth = 4,
+        heads = 4,
+        dim_head = 32,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        self.window_size = window_size
+        rel_positions = 2 * window_size - 1
+        self.local_rel_pos_bias = nn.Embedding(rel_positions ** 2, heads)
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout)
+            ]))
+
+    def forward(self, local_tokens, region_tokens):
+        device = local_tokens.device
+        lh, lw = local_tokens.shape[-2:]
+        rh, rw = region_tokens.shape[-2:]
+        window_size_h, window_size_w = lh // rh, lw // rw
+
+        local_tokens = rearrange(local_tokens, 'b c h w -> b (h w) c')
+        region_tokens = rearrange(region_tokens, 'b c h w -> b (h w) c')
+
+        # calculate local relative positional bias
+        
+        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 = torch.stack((grid_x, grid_y))
+        grid = rearrange(grid, 'c h w -> c (h w)')
+        grid = (grid[:, :, None] - grid[:, None, :]) + (self.window_size - 1)
+        bias_indices = (grid * torch.tensor([1, self.window_size * 2 - 1], device = device)[:, None, None]).sum(dim = 0)
+        rel_pos_bias = self.local_rel_pos_bias(bias_indices)
+        rel_pos_bias = rearrange(rel_pos_bias, 'i j h -> () h i j')
+        rel_pos_bias = F.pad(rel_pos_bias, (1, 0, 1, 0), value = 0)
+
+        # go through r2l transformer layers
+
+        for attn, ff in self.layers:
+            region_tokens = attn(region_tokens) + region_tokens
+
+            # concat region tokens to local tokens
+
+            local_tokens = rearrange(local_tokens, 'b (h w) d -> b h w d', h = lh)
+            local_tokens = rearrange(local_tokens, 'b (h p1) (w p2) d -> (b h w) (p1 p2) d', p1 = window_size_h, p2 = window_size_w)
+            region_tokens = rearrange(region_tokens, 'b n d -> (b n) () d')
+
+            # do self attention on local tokens, along with its regional token
+
+            region_and_local_tokens = torch.cat((region_tokens, local_tokens), dim = 1)
+            region_and_local_tokens = attn(region_and_local_tokens, rel_pos_bias = rel_pos_bias) + region_and_local_tokens
+
+            # feedforward
+
+            region_and_local_tokens = ff(region_and_local_tokens) + region_and_local_tokens
+
+            # split back local and regional tokens
+
+            region_tokens, local_tokens = region_and_local_tokens[:, :1], region_and_local_tokens[:, 1:]
+            local_tokens = rearrange(local_tokens, '(b h w) (p1 p2) d -> b (h p1 w p2) d', h = lh // window_size_h, w = lw // window_size_w, p1 = window_size_h)
+            region_tokens = rearrange(region_tokens, '(b n) () d -> b n d', n = rh * rw)
+
+        local_tokens = rearrange(local_tokens, 'b (h w) c -> b c h w', h = lh, w = lw)
+        region_tokens = rearrange(region_tokens, 'b (h w) c -> b c h w', h = rh, w = rw)
+        return local_tokens, region_tokens
+
+# classes
+
+class RegionViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        dim = (64, 128, 256, 512),
+        depth = (2, 2, 8, 2),
+        window_size = 7,
+        num_classes = 1000,
+        tokenize_local_3_conv = False,
+        local_patch_size = 4,
+        use_peg = False,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+        channels = 3,
+    ):
+        super().__init__()
+        dim = cast_tuple(dim, 4)
+        depth = cast_tuple(depth, 4)
+        assert len(dim) == 4, 'dim needs to be a single value or a tuple of length 4'
+        assert len(depth) == 4, 'depth needs to be a single value or a tuple of length 4'
+
+        self.local_patch_size = local_patch_size
+
+        region_patch_size = local_patch_size * window_size
+        self.region_patch_size = local_patch_size * window_size
+
+        init_dim, *_, last_dim = dim
+
+        # local and region encoders
+
+        if tokenize_local_3_conv:
+            self.local_encoder = nn.Sequential(
+                nn.Conv2d(3, init_dim, 3, 2, 1),
+                nn.LayerNorm(init_dim),
+                nn.GELU(),
+                nn.Conv2d(init_dim, init_dim, 3, 2, 1),
+                nn.LayerNorm(init_dim),
+                nn.GELU(),
+                nn.Conv2d(init_dim, init_dim, 3, 1, 1)
+            )
+        else:
+            self.local_encoder = nn.Conv2d(3, init_dim, 8, 4, 3)
+
+        self.region_encoder = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (c p1 p2) h w', p1 = region_patch_size, p2 = region_patch_size),
+            nn.Conv2d((region_patch_size ** 2) * channels, init_dim, 1)
+        )
+
+        # layers
+
+        current_dim = init_dim
+        self.layers = nn.ModuleList([])
+
+        for ind, dim, num_layers in zip(range(4), dim, depth):
+            not_first = ind != 0
+            need_downsample = not_first
+            need_peg = not_first and use_peg
+
+            self.layers.append(nn.ModuleList([
+                Downsample(current_dim, dim) if need_downsample else nn.Identity(),
+                PEG(dim) if need_peg else nn.Identity(),
+                R2LTransformer(dim, depth = num_layers, window_size = window_size, attn_dropout = attn_dropout, ff_dropout = ff_dropout)
+            ]))
+
+            current_dim = dim
+
+        # final logits
+
+        self.to_logits = nn.Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.LayerNorm(last_dim),
+            nn.Linear(last_dim, num_classes)
+        )
+
+    def forward(self, x):
+        *_, h, w = x.shape
+        assert divisible_by(h, self.region_patch_size) and divisible_by(w, self.region_patch_size), 'height and width must be divisible by region patch size'
+        assert divisible_by(h, self.local_patch_size) and divisible_by(w, self.local_patch_size), 'height and width must be divisible by local patch size'
+
+        local_tokens = self.local_encoder(x)
+        region_tokens = self.region_encoder(x)
+
+        for down, peg, transformer in self.layers:
+            local_tokens, region_tokens = down(local_tokens), down(region_tokens)
+            local_tokens = peg(local_tokens)
+            local_tokens, region_tokens = transformer(local_tokens, region_tokens)
+
+        return self.to_logits(region_tokens)

vit_pytorch/rvt.py

@@ -0,0 +1,209 @@
+from math import sqrt, pi, log
+
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# rotary embeddings
+
+def rotate_every_two(x):
+    x = rearrange(x, '... (d j) -> ... d j', j = 2)
+    x1, x2 = x.unbind(dim = -1)
+    x = torch.stack((-x2, x1), dim = -1)
+    return rearrange(x, '... d j -> ... (d j)')
+
+class AxialRotaryEmbedding(nn.Module):
+    def __init__(self, dim, max_freq = 10):
+        super().__init__()
+        self.dim = dim
+        scales = torch.linspace(1., max_freq / 2, self.dim // 4)
+        self.register_buffer('scales', scales)
+
+    def forward(self, x):
+        device, dtype, n = x.device, x.dtype, int(sqrt(x.shape[-2]))
+
+        seq = torch.linspace(-1., 1., steps = n, device = device)
+        seq = seq.unsqueeze(-1)
+
+        scales = self.scales[(*((None,) * (len(seq.shape) - 1)), Ellipsis)]
+        scales = scales.to(x)
+
+        seq = seq * scales * pi
+
+        x_sinu = repeat(seq, 'i d -> i j d', j = n)
+        y_sinu = repeat(seq, 'j d -> i j d', i = n)
+
+        sin = torch.cat((x_sinu.sin(), y_sinu.sin()), dim = -1)
+        cos = torch.cat((x_sinu.cos(), y_sinu.cos()), dim = -1)
+
+        sin, cos = map(lambda t: rearrange(t, 'i j d -> (i j) d'), (sin, cos))
+        sin, cos = map(lambda t: repeat(t, 'n d -> () n (d j)', j = 2), (sin, cos))
+        return sin, cos
+
+class DepthWiseConv2d(nn.Module):
+    def __init__(self, dim_in, dim_out, kernel_size, padding, stride = 1, bias = True):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Conv2d(dim_in, dim_in, kernel_size = kernel_size, padding = padding, groups = dim_in, stride = stride, bias = bias),
+            nn.Conv2d(dim_in, dim_out, kernel_size = 1, bias = bias)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# 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__()
+        self.conv = DepthWiseConv2d(dim_in, dim_out, kernel, padding = kernel // 2, bias = False)
+        self.cls_proj = nn.Linear(dim_in, dim_out) if dim_in != dim_out else nn.Identity()
+
+    def forward(self, x, fmap_dims):
+        cls_token, x = x[:, :1], x[:, 1:]
+        x = rearrange(x, 'b (h w) d -> b d h w', **fmap_dims)
+        x = self.conv(x)
+        x = rearrange(x, 'b d h w -> b (h w) d')
+        cls_token = self.cls_proj(cls_token)
+        return torch.cat((cls_token, x), dim = 1)
+
+class GEGLU(nn.Module):
+    def forward(self, x):
+        x, gates = x.chunk(2, dim = -1)
+        return F.gelu(gates) * x
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0., use_glu = True):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim * 2 if use_glu else hidden_dim),
+            GEGLU() if use_glu else 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., use_rotary = True, use_ds_conv = True, conv_query_kernel = 5):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.use_rotary = use_rotary
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.use_ds_conv = use_ds_conv
+
+        self.to_q = SpatialConv(dim, inner_dim, conv_query_kernel, bias = False) if use_ds_conv else 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, pos_emb, fmap_dims):
+        b, n, _, h = *x.shape, self.heads
+
+        to_q_kwargs = {'fmap_dims': fmap_dims} if self.use_ds_conv else {}
+        q = self.to_q(x, **to_q_kwargs)
+
+        qkv = (q, *self.to_kv(x).chunk(2, dim = -1))
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h = h), qkv)
+
+        if self.use_rotary:
+            # apply 2d rotary embeddings to queries and keys, excluding CLS tokens
+
+            sin, cos = pos_emb
+            dim_rotary = sin.shape[-1]
+
+            (q_cls, q), (k_cls, k) = map(lambda t: (t[:, :1], t[:, 1:]), (q, k))
+
+            # handle the case where rotary dimension < head dimension
+
+            (q, q_pass), (k, k_pass) = map(lambda t: (t[..., :dim_rotary], t[..., dim_rotary:]), (q, k))
+            q, k = map(lambda t: (t * cos) + (rotate_every_two(t) * sin), (q, k))
+            q, k = map(lambda t: torch.cat(t, dim = -1), ((q, q_pass), (k, k_pass)))
+
+            # concat back the CLS tokens
+
+            q = torch.cat((q_cls, q), dim = 1)
+            k = torch.cat((k_cls, k), dim = 1)
+
+        dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
+
+        attn = self.attend(dots)
+
+        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)
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, image_size, dropout = 0., use_rotary = True, use_ds_conv = True, use_glu = True):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        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))
+            ]))
+    def forward(self, x, fmap_dims):
+        pos_emb = self.pos_emb(x[:, 1:])
+
+        for attn, ff in self.layers:
+            x = attn(x, pos_emb = pos_emb, fmap_dims = fmap_dims) + x
+            x = ff(x) + x
+        return x
+
+# Rotary Vision Transformer
+
+class RvT(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., use_rotary = True, use_ds_conv = True, use_glu = True):
+        super().__init__()
+        assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
+        num_patches = (image_size // patch_size) ** 2
+        patch_dim = channels * patch_size ** 2
+
+        self.patch_size = patch_size
+        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.Linear(patch_dim, dim),
+        )
+
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, image_size, dropout, use_rotary, use_ds_conv, use_glu)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        b, _, h, w, p = *img.shape, self.patch_size
+
+        x = self.to_patch_embedding(img)
+        n = x.shape[1]
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+
+        fmap_dims = {'h': h // p, 'w': w // p}
+        x = self.transformer(x, fmap_dims = fmap_dims)
+
+        return self.mlp_head(x[:, 0])

vit_pytorch/simmim.py

@@ -0,0 +1,84 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+from einops import repeat
+
+class SimMIM(nn.Module):
+    def __init__(
+        self,
+        *,
+        encoder,
+        masking_ratio = 0.5
+    ):
+        super().__init__()
+        assert masking_ratio > 0 and masking_ratio < 1, 'masking ratio must be kept between 0 and 1'
+        self.masking_ratio = masking_ratio
+
+        # extract some hyperparameters and functions from encoder (vision transformer to be trained)
+
+        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]
+
+        # simple linear head
+
+        self.mask_token = nn.Parameter(torch.randn(encoder_dim))
+        self.to_pixels = nn.Linear(encoder_dim, pixel_values_per_patch)
+
+    def forward(self, img):
+        device = img.device
+
+        # get patches
+
+        patches = self.to_patch(img)
+        batch, num_patches, *_ = patches.shape
+
+        # for indexing purposes
+
+        batch_range = torch.arange(batch, device = device)[:, None]
+
+        # get positions
+
+        pos_emb = self.encoder.pos_embedding[:, 1:(num_patches + 1)]
+
+        # patch to encoder tokens and add positions
+
+        tokens = self.patch_to_emb(patches)
+        tokens = tokens + pos_emb
+
+        # prepare mask tokens
+
+        mask_tokens = repeat(self.mask_token, 'd -> b n d', b = batch, n = num_patches)
+        mask_tokens = mask_tokens + pos_emb
+
+        # calculate of patches needed to be masked, and get positions (indices) to be masked
+
+        num_masked = int(self.masking_ratio * num_patches)
+        masked_indices = torch.rand(batch, num_patches, device = device).topk(k = num_masked, dim = -1).indices
+        masked_bool_mask = torch.zeros((batch, num_patches), device = device).scatter_(-1, masked_indices, 1).bool()
+
+        # mask tokens
+
+        tokens = torch.where(masked_bool_mask[..., None], mask_tokens, tokens)
+
+        # attend with vision transformer
+
+        encoded = self.encoder.transformer(tokens)
+
+        # get the masked tokens
+
+        encoded_mask_tokens = encoded[batch_range, masked_indices]
+
+        # small linear projection for predicted pixel values
+
+        pred_pixel_values = self.to_pixels(encoded_mask_tokens)
+
+        # get the masked patches for the final reconstruction loss
+
+        masked_patches = patches[batch_range, masked_indices]
+
+        # calculate reconstruction loss
+
+        recon_loss = F.l1_loss(pred_pixel_values, masked_patches) / num_masked
+        return recon_loss

vit_pytorch/t2t.py

@@ -35,13 +35,14 @@ class T2TViT(nn.Module):
         for i, (kernel_size, stride) in enumerate(t2t_layers):
             layer_dim *= kernel_size ** 2
             is_first = i == 0
+            is_last = i == (len(t2t_layers) - 1)
             output_image_size = conv_output_size(output_image_size, kernel_size, stride, stride // 2)
 
             layers.extend([
                 RearrangeImage() if not is_first else nn.Identity(),
                 nn.Unfold(kernel_size = kernel_size, stride = stride, padding = stride // 2),
                 Rearrange('b c n -> b n c'),
-                Transformer(dim = layer_dim, heads = 1, depth = 1, dim_head = layer_dim, mlp_dim = layer_dim, dropout = dropout),
+                Transformer(dim = layer_dim, heads = 1, depth = 1, dim_head = layer_dim, mlp_dim = layer_dim, dropout = dropout) if not is_last else nn.Identity(),
             ])
 
         layers.append(nn.Linear(layer_dim, dim))
@@ -71,7 +72,7 @@ class T2TViT(nn.Module):
 
         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
+        x += self.pos_embedding[:, :n+1]
         x = self.dropout(x)
 
         x = self.transformer(x)

vit_pytorch/twins_svt.py

@@ -0,0 +1,229 @@
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helper methods
+
+def group_dict_by_key(cond, d):
+    return_val = [dict(), dict()]
+    for key in d.keys():
+        match = bool(cond(key))
+        ind = int(not match)
+        return_val[ind][key] = d[key]
+    return (*return_val,)
+
+def group_by_key_prefix_and_remove_prefix(prefix, d):
+    kwargs_with_prefix, kwargs = group_dict_by_key(lambda x: x.startswith(prefix), d)
+    kwargs_without_prefix = dict(map(lambda x: (x[0][len(prefix):], x[1]), tuple(kwargs_with_prefix.items())))
+    return kwargs_without_prefix, kwargs
+
+# classes
+
+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 LayerNorm(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):
+        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        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)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mult = 4, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Conv2d(dim, dim * mult, 1),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Conv2d(dim * mult, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class PatchEmbedding(nn.Module):
+    def __init__(self, *, dim, dim_out, patch_size):
+        super().__init__()
+        self.dim = dim
+        self.dim_out = dim_out
+        self.patch_size = patch_size
+        self.proj = nn.Conv2d(patch_size ** 2 * dim, dim_out, 1)
+
+    def forward(self, fmap):
+        p = self.patch_size
+        fmap = rearrange(fmap, 'b c (h p1) (w p2) -> b (c p1 p2) h w', p1 = p, p2 = p)
+        return self.proj(fmap)
+
+class PEG(nn.Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        self.proj = Residual(nn.Conv2d(dim, dim, kernel_size = kernel_size, padding = kernel_size // 2, groups = dim, stride = 1))
+
+    def forward(self, x):
+        return self.proj(x)
+
+class LocalAttention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0., patch_size = 7):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.patch_size = patch_size
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
+        self.to_kv = nn.Conv2d(dim, inner_dim * 2, 1, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, 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))
+
+        fmap = rearrange(fmap, 'b c (x p1) (y p2) -> (b x y) c p1 p2', p1 = p, p2 = p)
+
+        q, k, v = (self.to_q(fmap), *self.to_kv(fmap).chunk(2, dim = 1))
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) p1 p2 -> (b h) (p1 p2) d', h = h), (q, k, v))
+
+        dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
+
+        attn = dots.softmax(dim = - 1)
+
+        out = einsum('b i j, b j d -> b i d', attn, v)
+        out = rearrange(out, '(b x y h) (p1 p2) d -> b (h d) (x p1) (y p2)', h = h, x = x, y = y, p1 = p, p2 = p)
+        return self.to_out(out)
+
+class GlobalAttention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0., k = 7):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        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.to_out = nn.Sequential(
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, 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))
+
+        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 = dots.softmax(dim = -1)
+
+        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)
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads = 8, dim_head = 64, mlp_mult = 4, local_patch_size = 7, global_k = 7, dropout = 0., has_local = True):
+        super().__init__()
+        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)))
+            ]))
+    def forward(self, x):
+        for local_attn, ff1, global_attn, ff2 in self.layers:
+            x = local_attn(x)
+            x = ff1(x)
+            x = global_attn(x)
+            x = ff2(x)
+        return x
+
+class TwinsSVT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        s1_emb_dim = 64,
+        s1_patch_size = 4,
+        s1_local_patch_size = 7,
+        s1_global_k = 7,
+        s1_depth = 1,
+        s2_emb_dim = 128,
+        s2_patch_size = 2,
+        s2_local_patch_size = 7,
+        s2_global_k = 7,
+        s2_depth = 1,
+        s3_emb_dim = 256,
+        s3_patch_size = 2,
+        s3_local_patch_size = 7,
+        s3_global_k = 7,
+        s3_depth = 5,
+        s4_emb_dim = 512,
+        s4_patch_size = 2,
+        s4_local_patch_size = 7,
+        s4_global_k = 7,
+        s4_depth = 4,
+        peg_kernel_size = 3,
+        dropout = 0.
+    ):
+        super().__init__()
+        kwargs = dict(locals())
+
+        dim = 3
+        layers = []
+
+        for prefix in ('s1', 's2', 's3', 's4'):
+            config, kwargs = group_by_key_prefix_and_remove_prefix(f'{prefix}_', kwargs)
+            is_last = prefix == 's4'
+
+            dim_next = config['emb_dim']
+
+            layers.append(nn.Sequential(
+                PatchEmbedding(dim = dim, dim_out = dim_next, patch_size = config['patch_size']),
+                Transformer(dim = dim_next, depth = 1, local_patch_size = config['local_patch_size'], global_k = config['global_k'], dropout = dropout, has_local = not is_last),
+                PEG(dim = dim_next, kernel_size = peg_kernel_size),
+                Transformer(dim = dim_next, depth = config['depth'],  local_patch_size = config['local_patch_size'], global_k = config['global_k'], dropout = dropout, has_local = not is_last)
+            ))
+
+            dim = dim_next
+
+        self.layers = nn.Sequential(
+            *layers,
+            nn.AdaptiveAvgPool2d(1),
+            Rearrange('... () () -> ...'),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, x):
+        return self.layers(x)

vit_pytorch/vit.py

@@ -1,10 +1,16 @@
 import torch
-from torch import nn, einsum
-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 PreNorm(nn.Module):
     def __init__(self, dim, fn):
         super().__init__()
@@ -44,15 +50,14 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
-        b, n, _, h = *x.shape, self.heads
         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)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
-        dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
 
         attn = self.attend(dots)
 
-        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+        out = torch.matmul(attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
         return self.to_out(out)
 
@@ -74,13 +79,17 @@ class Transformer(nn.Module):
 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__()
-        assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
-        num_patches = (image_size // patch_size) ** 2
-        patch_dim = channels * patch_size ** 2
+        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_size, p2 = patch_size),
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
             nn.Linear(patch_dim, dim),
         )