allow channels to be customizable for cvt

Co-authored-by: Artem Lukin <artyom.lukin98@gmail.com>

.github/workflows/python-publish.yml

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

.github/workflows/python-test.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: [3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v2

README.md

@@ -25,6 +25,7 @@
 - [MaxViT](#maxvit)
 - [NesT](#nest)
 - [MobileViT](#mobilevit)
+- [XCiT](#xcit)
 - [Masked Autoencoder](#masked-autoencoder)
 - [Simple Masked Image Modeling](#simple-masked-image-modeling)
 - [Masked Patch Prediction](#masked-patch-prediction)
@@ -92,7 +93,7 @@ preds = v(img) # (1, 1000)
 - `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.  
-Number of patches. `image_size` must be divisible by `patch_size`.  
+Size of patches. `image_size` must be divisible by `patch_size`.  
 The number of patches is: ` n = (image_size // patch_size) ** 2` and `n` **must be greater than 16**.
 - `num_classes`: int.  
 Number of classes to classify.
@@ -179,6 +180,24 @@ preds = v(images) # (5, 1000) - 5, because 5 images of different resolution abov
 
 ```
 
+Or if you would rather that the framework auto group the images into variable lengthed sequences that do not exceed a certain max length
+
+```python
+images = [
+    torch.randn(3, 256, 256),
+    torch.randn(3, 128, 128),
+    torch.randn(3, 128, 256),
+    torch.randn(3, 256, 128),
+    torch.randn(3, 64, 256)
+]
+
+preds = v(
+    images,
+    group_images = True,
+    group_max_seq_len = 64
+) # (5, 1000)
+```
+
 ## Distillation
 
 <img src="./images/distill.png" width="300px"></img>
@@ -754,6 +773,38 @@ img = torch.randn(1, 3, 256, 256)
 pred = mbvit_xs(img) # (1, 1000)
 ```
 
+## XCiT
+
+<img src="./images/xcit.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2106.09681">paper</a> introduces the cross covariance attention (abbreviated XCA). One can think of it as doing attention across the features dimension rather than the spatial one (another perspective would be a dynamic 1x1 convolution, the kernel being attention map defined by spatial correlations).
+
+Technically, this amounts to simply transposing the query, key, values before executing cosine similarity attention with learned temperature.
+
+```python
+import torch
+from vit_pytorch.xcit import XCiT
+
+v = XCiT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 12,                     # depth of xcit transformer
+    cls_depth = 2,                  # depth of cross attention of CLS tokens to patch, attention pool at end
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1,
+    layer_dropout = 0.05,           # randomly dropout 5% of the layers
+    local_patch_kernel_size = 3     # kernel size of the local patch interaction module (depthwise convs)
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+```
+
 ## Simple Masked Image Modeling
 
 <img src="./images/simmim.png" width="400px"/>
@@ -2002,4 +2053,23 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@inproceedings{Darcet2023VisionTN,
+    title   = {Vision Transformers Need Registers},
+    author  = {Timoth'ee Darcet and Maxime Oquab and Julien Mairal and Piotr Bojanowski},
+    year    = {2023},
+    url     = {https://api.semanticscholar.org/CorpusID:263134283}
+}
+```
+
+```bibtex
+@inproceedings{ElNouby2021XCiTCI,
+    title   = {XCiT: Cross-Covariance Image Transformers},
+    author  = {Alaaeldin El-Nouby and Hugo Touvron and Mathilde Caron and Piotr Bojanowski and Matthijs Douze and Armand Joulin and Ivan Laptev and Natalia Neverova and Gabriel Synnaeve and Jakob Verbeek and Herv{\'e} J{\'e}gou},
+    booktitle = {Neural Information Processing Systems},
+    year    = {2021},
+    url     = {https://api.semanticscholar.org/CorpusID:235458262}
+}
+```
+
 *I visualise a time when we will be to robots what dogs are to humans, and I’m rooting for the machines.* — Claude Shannon

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '1.2.7',
+  version = '1.6.3',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   long_description_content_type = 'text/markdown',
@@ -16,7 +16,7 @@ setup(
     'image recognition'
   ],
   install_requires=[
-    'einops>=0.6.1',
+    'einops>=0.7.0',
     'torch>=1.10',
     'torchvision'
   ],

vit_pytorch/__init__.py

@@ -1,10 +1,3 @@
-import torch
-from packaging import version
-
-if version.parse(torch.__version__) >= version.parse('2.0.0'):
-    from einops._torch_specific import allow_ops_in_compiled_graph
-    allow_ops_in_compiled_graph()
-
 from vit_pytorch.vit import ViT
 from vit_pytorch.simple_vit import SimpleViT
 

vit_pytorch/ats_vit.py

@@ -110,18 +110,11 @@ class AdaptiveTokenSampling(nn.Module):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -138,6 +131,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -154,6 +148,7 @@ class Attention(nn.Module):
     def forward(self, x, *, mask):
         num_tokens = x.shape[1]
 
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -189,8 +184,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _, output_num_tokens in zip(range(depth), max_tokens_per_depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, output_num_tokens = output_num_tokens, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, output_num_tokens = output_num_tokens, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
 
     def forward(self, x):

vit_pytorch/cait.py

@@ -44,18 +44,11 @@ class LayerScale(nn.Module):
     def forward(self, x, **kwargs):
         return self.fn(x, **kwargs) * self.scale
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -72,6 +65,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.to_q = nn.Linear(dim, inner_dim, bias = False)
         self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
 
@@ -89,6 +83,7 @@ class Attention(nn.Module):
     def forward(self, x, context = None):
         b, n, _, h = *x.shape, self.heads
 
+        x = self.norm(x)
         context = x if not exists(context) else torch.cat((x, context), dim = 1)
 
         qkv = (self.to_q(x), *self.to_kv(context).chunk(2, dim = -1))
@@ -115,8 +110,8 @@ class Transformer(nn.Module):
 
         for ind in range(depth):
             self.layers.append(nn.ModuleList([
-                LayerScale(dim, PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)), depth = ind + 1),
-                LayerScale(dim, PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout)), depth = ind + 1)
+                LayerScale(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout), depth = ind + 1),
+                LayerScale(dim, FeedForward(dim, mlp_dim, dropout = dropout), depth = ind + 1)
             ]))
     def forward(self, x, context = None):
         layers = dropout_layers(self.layers, dropout = self.layer_dropout)

vit_pytorch/cross_vit.py

@@ -13,22 +13,13 @@ def exists(val):
 def default(val, d):
     return val if exists(val) else d
 
-# pre-layernorm
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 # feedforward
 
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -47,6 +38,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -60,6 +52,7 @@ class Attention(nn.Module):
 
     def forward(self, x, context = None, kv_include_self = False):
         b, n, _, h = *x.shape, self.heads
+        x = self.norm(x)
         context = default(context, x)
 
         if kv_include_self:
@@ -86,8 +79,8 @@ class Transformer(nn.Module):
         self.norm = nn.LayerNorm(dim)
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
 
     def forward(self, x):
@@ -121,8 +114,8 @@ class CrossTransformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                ProjectInOut(sm_dim, lg_dim, PreNorm(lg_dim, Attention(lg_dim, heads = heads, dim_head = dim_head, dropout = dropout))),
-                ProjectInOut(lg_dim, sm_dim, PreNorm(sm_dim, Attention(sm_dim, heads = heads, dim_head = dim_head, dropout = dropout)))
+                ProjectInOut(sm_dim, lg_dim, Attention(lg_dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                ProjectInOut(lg_dim, sm_dim, Attention(sm_dim, heads = heads, dim_head = dim_head, dropout = dropout))
             ]))
 
     def forward(self, sm_tokens, lg_tokens):

vit_pytorch/cvt.py

@@ -34,19 +34,11 @@ class LayerNorm(nn.Module): # layernorm, but done in the channel dimension #1
         mean = torch.mean(x, dim = 1, keepdim = True)
         return (x - mean) / (var + self.eps).sqrt() * 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(
+            LayerNorm(dim),
             nn.Conv2d(dim, dim * mult, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -75,6 +67,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -89,6 +82,8 @@ class Attention(nn.Module):
     def forward(self, x):
         shape = x.shape
         b, n, _, y, h = *shape, self.heads
+
+        x = self.norm(x)
         q, k, v = (self.to_q(x), *self.to_kv(x).chunk(2, dim = 1))
         q, k, v = map(lambda t: rearrange(t, 'b (h d) x y -> (b h) (x y) d', h = h), (q, k, v))
 
@@ -107,8 +102,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, proj_kernel = proj_kernel, kv_proj_stride = kv_proj_stride, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout))
+                Attention(dim, proj_kernel = proj_kernel, kv_proj_stride = kv_proj_stride, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_mult, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:
@@ -145,12 +140,13 @@ class CvT(nn.Module):
         s3_heads = 6,
         s3_depth = 10,
         s3_mlp_mult = 4,
-        dropout = 0.
+        dropout = 0.,
+        channels = 3
     ):
         super().__init__()
         kwargs = dict(locals())
 
-        dim = 3
+        dim = channels
         layers = []
 
         for prefix in ('s1', 's2', 's3'):

vit_pytorch/deepvit.py

@@ -5,25 +5,11 @@ import torch.nn.functional as F
 from einops import rearrange, repeat
 from einops.layers.torch import Rearrange
 
-class Residual(nn.Module):
-    def __init__(self, fn):
-        super().__init__()
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(x, **kwargs) + x
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -40,6 +26,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.dropout = nn.Dropout(dropout)
@@ -59,6 +46,8 @@ class Attention(nn.Module):
 
     def forward(self, x):
         b, n, _, h = *x.shape, self.heads
+        x = self.norm(x)
+
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
 
@@ -86,13 +75,13 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                Residual(PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout))),
-                Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout)))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:
-            x = attn(x)
-            x = ff(x)
+            x = attn(x) + x
+            x = ff(x) + x
         return x
 
 class DeepViT(nn.Module):

vit_pytorch/local_vit.py

@@ -26,16 +26,6 @@ class ExcludeCLS(nn.Module):
         x = self.fn(x, **kwargs)
         return torch.cat((cls_token, x), dim = 1)
 
-# prenorm
-
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 # feed forward related classes
 
 class DepthWiseConv2d(nn.Module):
@@ -52,6 +42,7 @@ class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Conv2d(dim, hidden_dim, 1),
             nn.Hardswish(),
             DepthWiseConv2d(hidden_dim, hidden_dim, 3, padding = 1),
@@ -77,6 +68,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
@@ -88,6 +80,8 @@ class Attention(nn.Module):
 
     def forward(self, x):
         b, n, _, h = *x.shape, self.heads
+
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
 
@@ -106,8 +100,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                Residual(PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout))),
-                ExcludeCLS(Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))))
+                Residual(Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                ExcludeCLS(Residual(FeedForward(dim, mlp_dim, dropout = dropout)))
             ]))
     def forward(self, x):
         for attn, ff in self.layers:

vit_pytorch/max_vit.py

@@ -19,20 +19,20 @@ def cast_tuple(val, length = 1):
 
 # helper classes
 
-class PreNormResidual(nn.Module):
+class Residual(nn.Module):
     def __init__(self, dim, fn):
         super().__init__()
-        self.norm = nn.LayerNorm(dim)
         self.fn = fn
 
     def forward(self, x):
-        return self.fn(self.norm(x)) + x
+        return self.fn(x) + x
 
 class FeedForward(nn.Module):
     def __init__(self, dim, mult = 4, dropout = 0.):
         super().__init__()
         inner_dim = int(dim * mult)
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, inner_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -132,6 +132,7 @@ class Attention(nn.Module):
         self.heads = dim // dim_head
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.to_qkv = nn.Linear(dim, dim * 3, bias = False)
 
         self.attend = nn.Sequential(
@@ -160,6 +161,8 @@ class Attention(nn.Module):
     def forward(self, x):
         batch, height, width, window_height, window_width, _, device, h = *x.shape, x.device, self.heads
 
+        x = self.norm(x)
+
         # flatten
 
         x = rearrange(x, 'b x y w1 w2 d -> (b x y) (w1 w2) d')
@@ -170,7 +173,7 @@ class Attention(nn.Module):
 
         # split heads
 
-        q, k, v = map(lambda t: rearrange(t, 'b n (h d ) -> b h n d', h = h), (q, k, v))
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), (q, k, v))
 
         # scale
 
@@ -259,13 +262,13 @@ class MaxViT(nn.Module):
                         shrinkage_rate = mbconv_shrinkage_rate
                     ),
                     Rearrange('b d (x w1) (y w2) -> b x y w1 w2 d', w1 = w, w2 = w),  # block-like attention
-                    PreNormResidual(layer_dim, Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = w)),
-                    PreNormResidual(layer_dim, FeedForward(dim = layer_dim, dropout = dropout)),
+                    Residual(layer_dim, Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = w)),
+                    Residual(layer_dim, FeedForward(dim = layer_dim, dropout = dropout)),
                     Rearrange('b x y w1 w2 d -> b d (x w1) (y w2)'),
 
                     Rearrange('b d (w1 x) (w2 y) -> b x y w1 w2 d', w1 = w, w2 = w),  # grid-like attention
-                    PreNormResidual(layer_dim, Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = w)),
-                    PreNormResidual(layer_dim, FeedForward(dim = layer_dim, dropout = dropout)),
+                    Residual(layer_dim, Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = w)),
+                    Residual(layer_dim, FeedForward(dim = layer_dim, dropout = dropout)),
                     Rearrange('b x y w1 w2 d -> b d (w1 x) (w2 y)'),
                 )
 

vit_pytorch/max_vit_with_registers.py

@@ -0,0 +1,340 @@
+from functools import partial
+
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+from torch.nn import Module, ModuleList, Sequential
+
+from einops import rearrange, repeat, reduce, pack, unpack
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def pack_one(x, pattern):
+    return pack([x], pattern)
+
+def unpack_one(x, ps, pattern):
+    return unpack(x, ps, pattern)[0]
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+def FeedForward(dim, mult = 4, dropout = 0.):
+    inner_dim = int(dim * mult)
+    return Sequential(
+        nn.LayerNorm(dim),
+        nn.Linear(dim, inner_dim),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Linear(inner_dim, dim),
+        nn.Dropout(dropout)
+    )
+
+# MBConv
+
+class SqueezeExcitation(Module):
+    def __init__(self, dim, shrinkage_rate = 0.25):
+        super().__init__()
+        hidden_dim = int(dim * shrinkage_rate)
+
+        self.gate = Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(dim, hidden_dim, bias = False),
+            nn.SiLU(),
+            nn.Linear(hidden_dim, dim, bias = False),
+            nn.Sigmoid(),
+            Rearrange('b c -> b c 1 1')
+        )
+
+    def forward(self, x):
+        return x * self.gate(x)
+
+class MBConvResidual(Module):
+    def __init__(self, fn, dropout = 0.):
+        super().__init__()
+        self.fn = fn
+        self.dropsample = Dropsample(dropout)
+
+    def forward(self, x):
+        out = self.fn(x)
+        out = self.dropsample(out)
+        return out + x
+
+class Dropsample(Module):
+    def __init__(self, prob = 0):
+        super().__init__()
+        self.prob = prob
+  
+    def forward(self, x):
+        device = x.device
+
+        if self.prob == 0. or (not self.training):
+            return x
+
+        keep_mask = torch.FloatTensor((x.shape[0], 1, 1, 1), device = device).uniform_() > self.prob
+        return x * keep_mask / (1 - self.prob)
+
+def MBConv(
+    dim_in,
+    dim_out,
+    *,
+    downsample,
+    expansion_rate = 4,
+    shrinkage_rate = 0.25,
+    dropout = 0.
+):
+    hidden_dim = int(expansion_rate * dim_out)
+    stride = 2 if downsample else 1
+
+    net = Sequential(
+        nn.Conv2d(dim_in, hidden_dim, 1),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        nn.Conv2d(hidden_dim, hidden_dim, 3, stride = stride, padding = 1, groups = hidden_dim),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        SqueezeExcitation(hidden_dim, shrinkage_rate = shrinkage_rate),
+        nn.Conv2d(hidden_dim, dim_out, 1),
+        nn.BatchNorm2d(dim_out)
+    )
+
+    if dim_in == dim_out and not downsample:
+        net = MBConvResidual(net, dropout = dropout)
+
+    return net
+
+# attention related classes
+
+class Attention(Module):
+    def __init__(
+        self,
+        dim,
+        dim_head = 32,
+        dropout = 0.,
+        window_size = 7,
+        num_registers = 1
+    ):
+        super().__init__()
+        assert num_registers > 0
+        assert (dim % dim_head) == 0, 'dimension should be divisible by dimension per head'
+
+        self.heads = dim // dim_head
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.to_qkv = nn.Linear(dim, dim * 3, bias = False)
+
+        self.attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_out = nn.Sequential(
+            nn.Linear(dim, dim, bias = False),
+            nn.Dropout(dropout)
+        )
+
+        # relative positional bias
+
+        num_rel_pos_bias = (2 * window_size - 1) ** 2
+
+        self.rel_pos_bias = nn.Embedding(num_rel_pos_bias + 1, self.heads)
+
+        pos = torch.arange(window_size)
+        grid = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
+        grid = rearrange(grid, 'c i j -> (i j) c')
+        rel_pos = rearrange(grid, 'i ... -> i 1 ...') - rearrange(grid, 'j ... -> 1 j ...')
+        rel_pos += window_size - 1
+        rel_pos_indices = (rel_pos * torch.tensor([2 * window_size - 1, 1])).sum(dim = -1)
+
+        rel_pos_indices = F.pad(rel_pos_indices, (num_registers, 0, num_registers, 0), value = num_rel_pos_bias)
+        self.register_buffer('rel_pos_indices', rel_pos_indices, persistent = False)
+
+    def forward(self, x):
+        device, h, bias_indices = x.device, self.heads, self.rel_pos_indices
+
+        x = self.norm(x)
+
+        # project for queries, keys, values
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = -1)
+
+        # split heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), (q, k, v))
+
+        # scale
+
+        q = q * self.scale
+
+        # sim
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add positional bias
+
+        bias = self.rel_pos_bias(bias_indices)
+        sim = sim + rearrange(bias, 'i j h -> h i j')
+
+        # attention
+
+        attn = self.attend(sim)
+
+        # aggregate
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+
+        # combine heads out
+
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class MaxViT(Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        dim_head = 32,
+        dim_conv_stem = None,
+        window_size = 7,
+        mbconv_expansion_rate = 4,
+        mbconv_shrinkage_rate = 0.25,
+        dropout = 0.1,
+        channels = 3,
+        num_register_tokens = 4
+    ):
+        super().__init__()
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+        assert num_register_tokens > 0
+
+        # convolutional stem
+
+        dim_conv_stem = default(dim_conv_stem, dim)
+
+        self.conv_stem = Sequential(
+            nn.Conv2d(channels, dim_conv_stem, 3, stride = 2, padding = 1),
+            nn.Conv2d(dim_conv_stem, dim_conv_stem, 3, padding = 1)
+        )
+
+        # variables
+
+        num_stages = len(depth)
+
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+        dims = (dim_conv_stem, *dims)
+        dim_pairs = tuple(zip(dims[:-1], dims[1:]))
+
+        self.layers = nn.ModuleList([])
+
+        # window size
+
+        self.window_size = window_size
+
+        self.register_tokens = nn.ParameterList([])
+
+        # iterate through stages
+
+        for ind, ((layer_dim_in, layer_dim), layer_depth) in enumerate(zip(dim_pairs, depth)):
+            for stage_ind in range(layer_depth):
+                is_first = stage_ind == 0
+                stage_dim_in = layer_dim_in if is_first else layer_dim
+
+                conv = MBConv(
+                    stage_dim_in,
+                    layer_dim,
+                    downsample = is_first,
+                    expansion_rate = mbconv_expansion_rate,
+                    shrinkage_rate = mbconv_shrinkage_rate
+                )
+
+                block_attn = Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = window_size, num_registers = num_register_tokens)
+                block_ff = FeedForward(dim = layer_dim, dropout = dropout)
+
+                grid_attn = Attention(dim = layer_dim, dim_head = dim_head, dropout = dropout, window_size = window_size, num_registers = num_register_tokens)
+                grid_ff = FeedForward(dim = layer_dim, dropout = dropout)
+
+                register_tokens = nn.Parameter(torch.randn(num_register_tokens, layer_dim))
+
+                self.layers.append(ModuleList([
+                    conv,
+                    ModuleList([block_attn, block_ff]),
+                    ModuleList([grid_attn, grid_ff])
+                ]))
+
+                self.register_tokens.append(register_tokens)
+
+        # mlp head out
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, x):
+        b, w = x.shape[0], self.window_size
+
+        x = self.conv_stem(x)
+
+        for (conv, (block_attn, block_ff), (grid_attn, grid_ff)), register_tokens in zip(self.layers, self.register_tokens):
+            x = conv(x)
+
+            # block-like attention
+
+            x = rearrange(x, 'b d (x w1) (y w2) -> b x y w1 w2 d', w1 = w, w2 = w)
+
+            # prepare register tokens
+
+            r = repeat(register_tokens, 'n d -> b x y n d', b = b, x = x.shape[1],y = x.shape[2])
+            r, register_batch_ps = pack_one(r, '* n d')
+
+            x, window_ps = pack_one(x, 'b x y * d')
+            x, batch_ps  = pack_one(x, '* n d')
+            x, register_ps = pack([r, x], 'b * d')
+
+            x = block_attn(x) + x
+            x = block_ff(x) + x
+
+            r, x = unpack(x, register_ps, 'b * d')
+
+            x = unpack_one(x, batch_ps, '* n d')
+            x = unpack_one(x, window_ps, 'b x y * d')
+            x = rearrange(x, 'b x y w1 w2 d -> b d (x w1) (y w2)')
+
+            r = unpack_one(r, register_batch_ps, '* n d')
+
+            # grid-like attention
+
+            x = rearrange(x, 'b d (w1 x) (w2 y) -> b x y w1 w2 d', w1 = w, w2 = w)
+
+            # prepare register tokens
+
+            r = reduce(r, 'b x y n d -> b n d', 'mean')
+            r = repeat(r, 'b n d -> b x y n d', x = x.shape[1], y = x.shape[2])
+            r, register_batch_ps = pack_one(r, '* n d')
+
+            x, window_ps = pack_one(x, 'b x y * d')
+            x, batch_ps  = pack_one(x, '* n d')
+            x, register_ps = pack([r, x], 'b * d')
+
+            x = grid_attn(x) + x
+
+            r, x = unpack(x, register_ps, 'b * d')
+
+            x = grid_ff(x) + x
+
+            x = unpack_one(x, batch_ps, '* n d')
+            x = unpack_one(x, window_ps, 'b x y * d')
+            x = rearrange(x, 'b x y w1 w2 d -> b d (w1 x) (w2 y)')
+
+        return self.mlp_head(x)

vit_pytorch/mobile_vit.py

@@ -22,20 +22,11 @@ def conv_nxn_bn(inp, oup, kernel_size=3, stride=1):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout=0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.SiLU(),
             nn.Dropout(dropout),
@@ -53,6 +44,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim=-1)
         self.dropout = nn.Dropout(dropout)
 
@@ -64,9 +56,10 @@ class Attention(nn.Module):
         )
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim=-1)
-        q, k, v = map(lambda t: rearrange(
-            t, 'b p n (h d) -> b p h n d', h=self.heads), qkv)
+
+        q, k, v = map(lambda t: rearrange(t, 'b p n (h d) -> b p h n d', h=self.heads), qkv)
 
         dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
 
@@ -88,8 +81,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads, dim_head, dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout))
+                Attention(dim, heads, dim_head, dropout),
+                FeedForward(dim, mlp_dim, dropout)
             ]))
 
     def forward(self, x):
@@ -167,11 +160,9 @@ class MobileViTBlock(nn.Module):
 
         # Global representations
         _, _, h, w = x.shape
-        x = rearrange(x, 'b d (h ph) (w pw) -> b (ph pw) (h w) d',
-                      ph=self.ph, pw=self.pw)
-        x = self.transformer(x)
-        x = rearrange(x, 'b (ph pw) (h w) d -> b d (h ph) (w pw)',
-                      h=h//self.ph, w=w//self.pw, ph=self.ph, pw=self.pw)
+        x = rearrange(x, 'b d (h ph) (w pw) -> b (ph pw) (h w) d', ph=self.ph, pw=self.pw)
+        x = self.transformer(x)        
+        x = rearrange(x, 'b (ph pw) (h w) d -> b d (h ph) (w pw)', h=h//self.ph, w=w//self.pw, ph=self.ph, pw=self.pw)
 
         # Fusion
         x = self.conv3(x)

vit_pytorch/na_vit.py

@@ -1,5 +1,5 @@
 from functools import partial
-from typing import List
+from typing import List, Union
 
 import torch
 import torch.nn.functional as F
@@ -17,12 +17,58 @@ def exists(val):
 def default(val, d):
     return val if exists(val) else d
 
+def always(val):
+    return lambda *args: val
+
 def pair(t):
     return t if isinstance(t, tuple) else (t, t)
 
 def divisible_by(numer, denom):
     return (numer % denom) == 0
 
+# auto grouping images
+
+def group_images_by_max_seq_len(
+    images: List[Tensor],
+    patch_size: int,
+    calc_token_dropout = None,
+    max_seq_len = 2048
+
+) -> List[List[Tensor]]:
+
+    calc_token_dropout = default(calc_token_dropout, always(0.))
+
+    groups = []
+    group = []
+    seq_len = 0
+
+    if isinstance(calc_token_dropout, (float, int)):
+        calc_token_dropout = always(calc_token_dropout)
+
+    for image in images:
+        assert isinstance(image, Tensor)
+
+        image_dims = image.shape[-2:]
+        ph, pw = map(lambda t: t // patch_size, image_dims)
+
+        image_seq_len = (ph * pw)
+        image_seq_len = int(image_seq_len * (1 - calc_token_dropout(*image_dims)))
+
+        assert image_seq_len <= max_seq_len, f'image with dimensions {image_dims} exceeds maximum sequence length'
+
+        if (seq_len + image_seq_len) > max_seq_len:
+            groups.append(group)
+            group = []
+            seq_len = 0
+
+        group.append(image)
+        seq_len += image_seq_len
+
+    if len(group) > 0:
+        groups.append(group)
+
+    return groups
+
 # normalization
 # they use layernorm without bias, something that pytorch does not offer
 
@@ -138,14 +184,25 @@ class Transformer(nn.Module):
         return self.norm(x)
 
 class NaViT(nn.Module):
-    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., token_dropout_prob = 0.):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., token_dropout_prob = None):
         super().__init__()
         image_height, image_width = pair(image_size)
 
         # what percent of tokens to dropout
-        # in paper, they found this should vary depending on resolution (todo - figure out how to do this, maybe with callback?)
+        # if int or float given, then assume constant dropout prob
+        # otherwise accept a callback that in turn calculates dropout prob from height and width
 
-        self.token_dropout_prob = token_dropout_prob
+        self.calc_token_dropout = None
+
+        if callable(token_dropout_prob):
+            self.calc_token_dropout = token_dropout_prob
+
+        elif isinstance(token_dropout_prob, (float, int)):
+            assert 0. < token_dropout_prob < 1.
+            token_dropout_prob = float(token_dropout_prob)
+            self.calc_token_dropout = lambda height, width: token_dropout_prob
+
+        # calculate patching related stuff
 
         assert divisible_by(image_height, patch_size) and divisible_by(image_width, patch_size), 'Image dimensions must be divisible by the patch size.'
 
@@ -188,13 +245,25 @@ class NaViT(nn.Module):
 
     def forward(
         self,
-        batched_images: List[List[Tensor]] # assume different resolution images already grouped correctly
+        batched_images: Union[List[Tensor], List[List[Tensor]]], # assume different resolution images already grouped correctly
+        group_images = False,
+        group_max_seq_len = 2048
     ):
-        p, c, device, has_token_dropout = self.patch_size, self.channels, self.device, self.token_dropout_prob > 0.
+        p, c, device, has_token_dropout = self.patch_size, self.channels, self.device, exists(self.calc_token_dropout)
 
         arange = partial(torch.arange, device = device)
         pad_sequence = partial(orig_pad_sequence, batch_first = True)
 
+        # auto pack if specified
+
+        if group_images:
+            batched_images = group_images_by_max_seq_len(
+                batched_images,
+                patch_size = self.patch_size,
+                calc_token_dropout = self.calc_token_dropout,
+                max_seq_len = group_max_seq_len
+            )
+
         # process images into variable lengthed sequences with attention mask
 
         num_images = []
@@ -227,8 +296,10 @@ class NaViT(nn.Module):
                 seq_len = seq.shape[-2]
 
                 if has_token_dropout:
-                    num_keep = max(1, int(seq_len * (1 - self.token_dropout_prob)))
+                    token_dropout = self.calc_token_dropout(*image_dims)
+                    num_keep = max(1, int(seq_len * (1 - token_dropout)))
                     keep_indices = torch.randn((seq_len,), device = device).topk(num_keep, dim = -1).indices
+
                     seq = seq[keep_indices]
                     pos = pos[keep_indices]
 

vit_pytorch/nest.py

@@ -24,19 +24,11 @@ class LayerNorm(nn.Module):
         mean = torch.mean(x, dim = 1, keepdim = True)
         return (x - mean) / (var + self.eps).sqrt() * 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(
+            LayerNorm(dim),
             nn.Conv2d(dim, dim * mlp_mult, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -54,6 +46,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
@@ -66,6 +59,8 @@ class Attention(nn.Module):
     def forward(self, x):
         b, c, h, w, heads = *x.shape, self.heads
 
+        x = self.norm(x)
+
         qkv = self.to_qkv(x).chunk(3, dim = 1)
         q, k, v = map(lambda t: rearrange(t, 'b (h d) x y -> b h (x y) d', h = heads), qkv)
 
@@ -93,8 +88,8 @@ class Transformer(nn.Module):
 
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout))
+                Attention(dim, heads = heads, dropout = dropout),
+                FeedForward(dim, mlp_mult, dropout = dropout)
             ]))
     def forward(self, x):
         *_, h, w = x.shape

vit_pytorch/parallel_vit.py

@@ -19,18 +19,11 @@ class Parallel(nn.Module):
     def forward(self, x):
         return sum([fn(x) for fn in self.fns])
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -49,6 +42,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -60,6 +54,7 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -77,8 +72,8 @@ class Transformer(nn.Module):
         super().__init__()
         self.layers = nn.ModuleList([])
 
-        attn_block = lambda: PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout))
-        ff_block = lambda: PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))        
+        attn_block = lambda: Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)
+        ff_block = lambda: FeedForward(dim, mlp_dim, dropout = dropout)
 
         for _ in range(depth):
             self.layers.append(nn.ModuleList([

vit_pytorch/pit.py

@@ -17,18 +17,11 @@ def conv_output_size(image_size, kernel_size, stride, padding = 0):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -47,6 +40,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
@@ -58,6 +52,8 @@ class Attention(nn.Module):
 
     def forward(self, x):
         b, n, _, h = *x.shape, self.heads
+
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
 
@@ -76,8 +72,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:

vit_pytorch/rvt.py

@@ -55,14 +55,6 @@ class DepthWiseConv2d(nn.Module):
 
 # helper classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class SpatialConv(nn.Module):
     def __init__(self, dim_in, dim_out, kernel, bias = False):
         super().__init__()
@@ -86,6 +78,7 @@ class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0., use_glu = True):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim * 2 if use_glu else hidden_dim),
             GEGLU() if use_glu else nn.GELU(),
             nn.Dropout(dropout),
@@ -103,6 +96,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -121,6 +115,9 @@ class Attention(nn.Module):
         b, n, _, h = *x.shape, self.heads
 
         to_q_kwargs = {'fmap_dims': fmap_dims} if self.use_ds_conv else {}
+
+        x = self.norm(x)
+
         q = self.to_q(x, **to_q_kwargs)
 
         qkv = (q, *self.to_kv(x).chunk(2, dim = -1))
@@ -162,8 +159,8 @@ class Transformer(nn.Module):
         self.pos_emb = AxialRotaryEmbedding(dim_head, max_freq = image_size)
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout, use_rotary = use_rotary, use_ds_conv = use_ds_conv)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout, use_glu = use_glu))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout, use_rotary = use_rotary, use_ds_conv = use_ds_conv),
+                FeedForward(dim, mlp_dim, dropout = dropout, use_glu = use_glu)
             ]))
     def forward(self, x, fmap_dims):
         pos_emb = self.pos_emb(x[:, 1:])

vit_pytorch/scalable_vit.py

@@ -33,15 +33,6 @@ class ChanLayerNorm(nn.Module):
         mean = torch.mean(x, dim = 1, keepdim = True)
         return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = ChanLayerNorm(dim)
-        self.fn = fn
-
-    def forward(self, x):
-        return self.fn(self.norm(x))
-
 class Downsample(nn.Module):
     def __init__(self, dim_in, dim_out):
         super().__init__()
@@ -65,6 +56,7 @@ class FeedForward(nn.Module):
         super().__init__()
         inner_dim = dim * expansion_factor
         self.net = nn.Sequential(
+            ChanLayerNorm(dim),
             nn.Conv2d(dim, inner_dim, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -92,6 +84,7 @@ class ScalableSelfAttention(nn.Module):
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
+        self.norm = ChanLayerNorm(dim)
         self.to_q = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
         self.to_k = nn.Conv2d(dim, dim_key * heads, reduction_factor, stride = reduction_factor, bias = False)
         self.to_v = nn.Conv2d(dim, dim_value * heads, reduction_factor, stride = reduction_factor, bias = False)
@@ -104,6 +97,8 @@ class ScalableSelfAttention(nn.Module):
     def forward(self, x):
         height, width, heads = *x.shape[-2:], self.heads
 
+        x = self.norm(x)
+
         q, k, v = self.to_q(x), self.to_k(x), self.to_v(x)
 
         # split out heads
@@ -145,6 +140,7 @@ class InteractiveWindowedSelfAttention(nn.Module):
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
+        self.norm = ChanLayerNorm(dim)
         self.local_interactive_module = nn.Conv2d(dim_value * heads, dim_value * heads, 3, padding = 1)
 
         self.to_q = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
@@ -159,6 +155,8 @@ class InteractiveWindowedSelfAttention(nn.Module):
     def forward(self, x):
         height, width, heads, wsz = *x.shape[-2:], self.heads, self.window_size
 
+        x = self.norm(x)
+
         wsz_h, wsz_w = default(wsz, height), default(wsz, width)
         assert (height % wsz_h) == 0 and (width % wsz_w) == 0, f'height ({height}) or width ({width}) of feature map is not divisible by the window size ({wsz_h}, {wsz_w})'
 
@@ -217,11 +215,11 @@ class Transformer(nn.Module):
             is_first = ind == 0
 
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, ScalableSelfAttention(dim, heads = heads, dim_key = ssa_dim_key, dim_value = ssa_dim_value, reduction_factor = ssa_reduction_factor, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, expansion_factor = ff_expansion_factor, dropout = dropout)),
+                ScalableSelfAttention(dim, heads = heads, dim_key = ssa_dim_key, dim_value = ssa_dim_value, reduction_factor = ssa_reduction_factor, dropout = dropout),
+                FeedForward(dim, expansion_factor = ff_expansion_factor, dropout = dropout),
                 PEG(dim) if is_first else None,
-                PreNorm(dim, FeedForward(dim, expansion_factor = ff_expansion_factor, dropout = dropout)),
-                PreNorm(dim, InteractiveWindowedSelfAttention(dim, heads = heads, dim_key = iwsa_dim_key, dim_value = iwsa_dim_value, window_size = iwsa_window_size, dropout = dropout))
+                FeedForward(dim, expansion_factor = ff_expansion_factor, dropout = dropout),
+                InteractiveWindowedSelfAttention(dim, heads = heads, dim_key = iwsa_dim_key, dim_value = iwsa_dim_value, window_size = iwsa_window_size, dropout = dropout)
             ]))
 
         self.norm = ChanLayerNorm(dim) if norm_output else nn.Identity()

vit_pytorch/sep_vit.py

@@ -25,15 +25,6 @@ class ChanLayerNorm(nn.Module):
         mean = torch.mean(x, dim = 1, keepdim = True)
         return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = ChanLayerNorm(dim)
-        self.fn = fn
-
-    def forward(self, x):
-        return self.fn(self.norm(x))
-
 class OverlappingPatchEmbed(nn.Module):
     def __init__(self, dim_in, dim_out, stride = 2):
         super().__init__()
@@ -59,6 +50,7 @@ class FeedForward(nn.Module):
         super().__init__()
         inner_dim = int(dim * mult)
         self.net = nn.Sequential(
+            ChanLayerNorm(dim),
             nn.Conv2d(dim, inner_dim, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -85,6 +77,8 @@ class DSSA(nn.Module):
         self.window_size = window_size
         inner_dim = dim_head * heads
 
+        self.norm = ChanLayerNorm(dim)
+
         self.attend = nn.Sequential(
             nn.Softmax(dim = -1),
             nn.Dropout(dropout)
@@ -138,6 +132,8 @@ class DSSA(nn.Module):
         assert (height % wsz) == 0 and (width % wsz) == 0, f'height {height} and width {width} must be divisible by window size {wsz}'
         num_windows = (height // wsz) * (width // wsz)
 
+        x = self.norm(x)
+
         # fold in windows for "depthwise" attention - not sure why it is named depthwise when it is just "windowed" attention
 
         x = rearrange(x, 'b c (h w1) (w w2) -> (b h w) c (w1 w2)', w1 = wsz, w2 = wsz)
@@ -225,8 +221,8 @@ class Transformer(nn.Module):
 
         for ind in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, DSSA(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mult = ff_mult, dropout = dropout)),
+                DSSA(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mult = ff_mult, dropout = dropout),
             ]))
 
         self.norm = ChanLayerNorm(dim) if norm_output else nn.Identity()

vit_pytorch/simple_vit.py

@@ -64,6 +64,7 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
@@ -74,7 +75,7 @@ class Transformer(nn.Module):
         for attn, ff in self.layers:
             x = attn(x) + x
             x = ff(x) + x
-        return x
+        return self.norm(x)
 
 class SimpleViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
@@ -101,12 +102,10 @@ class SimpleViT(nn.Module):
 
         self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
 
-        self.to_latent = nn.Identity()
-        self.linear_head = nn.Sequential(
-            nn.LayerNorm(dim),
-            nn.Linear(dim, num_classes)
-        )
         self.pool = "mean"
+        self.to_latent = nn.Identity()
+
+        self.linear_head = nn.Linear(dim, num_classes)
 
     def forward(self, img):
         device = img.device

vit_pytorch/simple_vit_1d.py

@@ -62,6 +62,7 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
@@ -72,7 +73,7 @@ class Transformer(nn.Module):
         for attn, ff in self.layers:
             x = attn(x) + x
             x = ff(x) + x
-        return x
+        return self.norm(x)
 
 class SimpleViT(nn.Module):
     def __init__(self, *, seq_len, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
@@ -93,10 +94,7 @@ class SimpleViT(nn.Module):
         self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
 
         self.to_latent = nn.Identity()
-        self.linear_head = nn.Sequential(
-            nn.LayerNorm(dim),
-            nn.Linear(dim, num_classes)
-        )
+        self.linear_head = nn.Linear(dim, num_classes)
 
     def forward(self, series):
         *_, n, dtype = *series.shape, series.dtype

vit_pytorch/simple_vit_3d.py

@@ -77,6 +77,7 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
@@ -87,7 +88,7 @@ class Transformer(nn.Module):
         for attn, ff in self.layers:
             x = attn(x) + x
             x = ff(x) + x
-        return x
+        return self.norm(x)
 
 class SimpleViT(nn.Module):
     def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
@@ -111,10 +112,7 @@ class SimpleViT(nn.Module):
         self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
 
         self.to_latent = nn.Identity()
-        self.linear_head = nn.Sequential(
-            nn.LayerNorm(dim),
-            nn.Linear(dim, num_classes)
-        )
+        self.linear_head = nn.Linear(dim, num_classes)
 
     def forward(self, video):
         *_, h, w, dtype = *video.shape, video.dtype

vit_pytorch/simple_vit_with_patch_dropout.py

@@ -87,6 +87,7 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
@@ -97,7 +98,7 @@ class Transformer(nn.Module):
         for attn, ff in self.layers:
             x = attn(x) + x
             x = ff(x) + x
-        return x
+        return self.norm(x)
 
 class SimpleViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, patch_dropout = 0.5):
@@ -122,10 +123,7 @@ class SimpleViT(nn.Module):
         self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
 
         self.to_latent = nn.Identity()
-        self.linear_head = nn.Sequential(
-            nn.LayerNorm(dim),
-            nn.Linear(dim, num_classes)
-        )
+        self.linear_head = nn.Linear(dim, num_classes)
 
     def forward(self, img):
         *_, h, w, dtype = *img.shape, img.dtype

vit_pytorch/simple_vit_with_qk_norm.py

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

vit_pytorch/simple_vit_with_register_tokens.py

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

vit_pytorch/twins_svt.py

@@ -42,20 +42,11 @@ class LayerNorm(nn.Module):
         mean = torch.mean(x, dim = 1, keepdim = True)
         return (x - mean) / (var + self.eps).sqrt() * 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(
+            LayerNorm(dim),
             nn.Conv2d(dim, dim * mult, 1),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -99,6 +90,7 @@ class LocalAttention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
         self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
         self.to_kv = nn.Conv2d(dim, inner_dim * 2, 1, bias = False)
 
@@ -108,6 +100,8 @@ class LocalAttention(nn.Module):
         )
 
     def forward(self, fmap):
+        fmap = self.norm(fmap)
+
         shape, p = fmap.shape, self.patch_size
         b, n, x, y, h = *shape, self.heads
         x, y = map(lambda t: t // p, (x, y))
@@ -132,6 +126,8 @@ class GlobalAttention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = LayerNorm(dim)
+
         self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
         self.to_kv = nn.Conv2d(dim, inner_dim * 2, k, stride = k, bias = False)
 
@@ -143,6 +139,8 @@ class GlobalAttention(nn.Module):
         )
 
     def forward(self, x):
+        x = self.norm(x)
+
         shape = x.shape
         b, n, _, y, h = *shape, self.heads
         q, k, v = (self.to_q(x), *self.to_kv(x).chunk(2, dim = 1))
@@ -164,10 +162,10 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                Residual(PreNorm(dim, LocalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, patch_size = local_patch_size))) if has_local else nn.Identity(),
-                Residual(PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout))) if has_local else nn.Identity(),
-                Residual(PreNorm(dim, GlobalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, k = global_k))),
-                Residual(PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout)))
+                Residual(LocalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, patch_size = local_patch_size)) if has_local else nn.Identity(),
+                Residual(FeedForward(dim, mlp_mult, dropout = dropout)) if has_local else nn.Identity(),
+                Residual(GlobalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, k = global_k)),
+                Residual(FeedForward(dim, mlp_mult, dropout = dropout))
             ]))
     def forward(self, x):
         for local_attn, ff1, global_attn, ff2 in self.layers:

vit_pytorch/vit.py

@@ -11,24 +11,18 @@ def pair(t):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
             nn.Linear(hidden_dim, dim),
             nn.Dropout(dropout)
         )
+
     def forward(self, x):
         return self.net(x)
 
@@ -41,6 +35,8 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
+
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -52,6 +48,8 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
+
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -67,17 +65,20 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
+
     def forward(self, x):
         for attn, ff in self.layers:
             x = attn(x) + x
             x = ff(x) + x
-        return x
+
+        return self.norm(x)
 
 class ViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
@@ -107,10 +108,7 @@ class ViT(nn.Module):
         self.pool = pool
         self.to_latent = nn.Identity()
 
-        self.mlp_head = nn.Sequential(
-            nn.LayerNorm(dim),
-            nn.Linear(dim, num_classes)
-        )
+        self.mlp_head = nn.Linear(dim, num_classes)
 
     def forward(self, img):
         x = self.to_patch_embedding(img)

vit_pytorch/vit_1d.py

@@ -6,18 +6,11 @@ from einops.layers.torch import Rearrange
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -36,6 +29,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -47,6 +41,7 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -65,8 +60,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:

vit_pytorch/vit_3d.py

@@ -11,18 +11,11 @@ def pair(t):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -41,6 +34,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -52,6 +46,7 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -70,8 +65,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:

vit_pytorch/vit_for_small_dataset.py

@@ -13,18 +13,11 @@ def pair(t):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -41,6 +34,7 @@ class LSA(nn.Module):
         self.heads = heads
         self.temperature = nn.Parameter(torch.log(torch.tensor(dim_head ** -0.5)))
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -52,6 +46,7 @@ class LSA(nn.Module):
         )
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -74,8 +69,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, LSA(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                LSA(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:

vit_pytorch/vit_with_patch_dropout.py

@@ -30,18 +30,11 @@ class PatchDropout(nn.Module):
 
         return x[batch_indices, patch_indices_keep]
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -60,6 +53,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -71,6 +65,7 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -89,8 +84,8 @@ class Transformer(nn.Module):
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:

vit_pytorch/vit_with_patch_merger.py

@@ -32,18 +32,11 @@ class PatchMerger(nn.Module):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -62,6 +55,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -73,6 +67,7 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -88,6 +83,7 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0., patch_merge_layer = None, patch_merge_num_tokens = 8):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
 
         self.patch_merge_layer_index = default(patch_merge_layer, depth // 2) - 1 # default to mid-way through transformer, as shown in paper
@@ -95,8 +91,8 @@ class Transformer(nn.Module):
 
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for index, (attn, ff) in enumerate(self.layers):
@@ -106,7 +102,7 @@ class Transformer(nn.Module):
             if index == self.patch_merge_layer_index:
                 x = self.patch_merger(x)
 
-        return x
+        return self.norm(x)
 
 class ViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, patch_merge_layer = None, patch_merge_num_tokens = 8, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
@@ -133,7 +129,6 @@ class ViT(nn.Module):
 
         self.mlp_head = nn.Sequential(
             Reduce('b n d -> b d', 'mean'),
-            nn.LayerNorm(dim),
             nn.Linear(dim, num_classes)
         )
 

vit_pytorch/vivit.py

@@ -14,18 +14,11 @@ def pair(t):
 
 # classes
 
-class PreNorm(nn.Module):
-    def __init__(self, dim, fn):
-        super().__init__()
-        self.norm = nn.LayerNorm(dim)
-        self.fn = fn
-    def forward(self, x, **kwargs):
-        return self.fn(self.norm(x), **kwargs)
-
 class FeedForward(nn.Module):
     def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
             nn.Dropout(dropout),
@@ -44,6 +37,7 @@ class Attention(nn.Module):
         self.heads = heads
         self.scale = dim_head ** -0.5
 
+        self.norm = nn.LayerNorm(dim)
         self.attend = nn.Softmax(dim = -1)
         self.dropout = nn.Dropout(dropout)
 
@@ -55,6 +49,7 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
+        x = self.norm(x)
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
@@ -70,17 +65,18 @@ class Attention(nn.Module):
 class Transformer(nn.Module):
     def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
         super().__init__()
+        self.norm = nn.LayerNorm(dim)
         self.layers = nn.ModuleList([])
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
-                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
+                FeedForward(dim, mlp_dim, dropout = dropout)
             ]))
     def forward(self, x):
         for attn, ff in self.layers:
             x = attn(x) + x
             x = ff(x) + x
-        return x
+        return self.norm(x)
 
 class ViT(nn.Module):
     def __init__(
@@ -137,10 +133,7 @@ class ViT(nn.Module):
         self.pool = pool
         self.to_latent = nn.Identity()
 
-        self.mlp_head = nn.Sequential(
-            nn.LayerNorm(dim),
-            nn.Linear(dim, num_classes)
-        )
+        self.mlp_head = nn.Linear(dim, num_classes)
 
     def forward(self, video):
         x = self.to_patch_embedding(video)

vit_pytorch/xcit.py

@@ -0,0 +1,283 @@
+from random import randrange
+
+import torch
+from torch import nn, einsum
+from torch.nn import Module, ModuleList
+import torch.nn.functional as F
+
+from einops import rearrange, repeat, pack, unpack
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def pack_one(t, pattern):
+    return pack([t], pattern)
+
+def unpack_one(t, ps, pattern):
+    return unpack(t, ps, pattern)[0]
+
+def l2norm(t):
+    return F.normalize(t, dim = -1, p = 2)
+
+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(Module):
+    def __init__(self, dim, fn, depth):
+        super().__init__()
+        if depth <= 18:
+            init_eps = 0.1
+        elif 18 > depth <= 24:
+            init_eps = 1e-5
+        else:
+            init_eps = 1e-6
+
+        self.fn = fn
+        self.scale = nn.Parameter(torch.full((dim,), init_eps))
+
+    def forward(self, x, **kwargs):
+        return self.fn(x, **kwargs) * self.scale
+
+class FeedForward(Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head * heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.norm = nn.LayerNorm(dim)
+        self.to_q = nn.Linear(dim, inner_dim, bias = False)
+        self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, context = None):
+        h = self.heads
+
+        x = self.norm(x)
+        context = x if not exists(context) else torch.cat((x, context), dim = 1)
+
+        qkv = (self.to_q(x), *self.to_kv(context).chunk(2, dim = -1))
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+
+        attn = self.attend(sim)
+        attn = self.dropout(attn)
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class XCAttention(Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head * heads
+        self.heads = heads
+        self.norm = nn.LayerNorm(dim)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.temperature = nn.Parameter(torch.ones(heads, 1, 1))
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        h = self.heads
+        x, ps = pack_one(x, 'b * d')
+
+        x = self.norm(x)
+        q, k, v = self.to_qkv(x).chunk(3, dim = -1)
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h d n', h = h), (q, k, v))
+
+        q, k = map(l2norm, (q, k))
+
+        sim = einsum('b h i n, b h j n -> b h i j', q, k) * self.temperature.exp()
+
+        attn = self.attend(sim)
+        attn = self.dropout(attn)
+
+        out = einsum('b h i j, b h j n -> b h i n', attn, v)
+        out = rearrange(out, 'b h d n -> b n (h d)')
+
+        out = unpack_one(out, ps, 'b * d')
+        return self.to_out(out)
+
+class LocalPatchInteraction(Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        assert (kernel_size % 2) == 1
+        padding = kernel_size // 2
+
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            Rearrange('b h w c -> b c h w'),
+            nn.Conv2d(dim, dim, kernel_size, padding = padding, groups = dim),
+            nn.BatchNorm2d(dim),
+            nn.GELU(),
+            nn.Conv2d(dim, dim, kernel_size, padding = padding, groups = dim),
+            Rearrange('b c h w -> b h w c'),
+        )
+
+    def forward(self, x):
+        return self.net(x)
+
+class Transformer(Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0., layer_dropout = 0.):
+        super().__init__()
+        self.layers = ModuleList([])
+        self.layer_dropout = layer_dropout
+
+        for ind in range(depth):
+            layer = ind + 1
+            self.layers.append(ModuleList([
+                LayerScale(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout), depth = layer),
+                LayerScale(dim, FeedForward(dim, mlp_dim, dropout = dropout), depth = layer)
+            ]))
+
+    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 XCATransformer(Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, local_patch_kernel_size = 3, dropout = 0., layer_dropout = 0.):
+        super().__init__()
+        self.layers = ModuleList([])
+        self.layer_dropout = layer_dropout
+
+        for ind in range(depth):
+            layer = ind + 1
+            self.layers.append(ModuleList([
+                LayerScale(dim, XCAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout), depth = layer),
+                LayerScale(dim, LocalPatchInteraction(dim, local_patch_kernel_size), depth = layer),
+                LayerScale(dim, FeedForward(dim, mlp_dim, dropout = dropout), depth = layer)
+            ]))
+
+    def forward(self, x):
+        layers = dropout_layers(self.layers, dropout = self.layer_dropout)
+
+        for cross_covariance_attn, local_patch_interaction, ff in layers:
+            x = cross_covariance_attn(x) + x
+            x = local_patch_interaction(x) + x
+            x = ff(x) + x
+
+        return x
+
+class XCiT(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.,
+        local_patch_kernel_size = 3,
+        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.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches, dim))
+        self.cls_token = nn.Parameter(torch.randn(dim))
+
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.xcit_transformer = XCATransformer(dim, depth, heads, dim_head, mlp_dim, local_patch_kernel_size, dropout, layer_dropout)
+
+        self.final_norm = nn.LayerNorm(dim)
+
+        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)
+
+        x, ps = pack_one(x, 'b * d')
+
+        b, n, _ = x.shape
+        x += self.pos_embedding[:, :n]
+
+        x = unpack_one(x, ps, 'b * d')
+
+        x = self.dropout(x)
+
+        x = self.xcit_transformer(x)
+
+        x = self.final_norm(x)
+
+        cls_tokens = repeat(self.cls_token, 'd -> b 1 d', b = b)
+
+        x = rearrange(x, 'b ... d -> b (...) d')
+        cls_tokens = self.cls_transformer(cls_tokens, context = x)
+
+        return self.mlp_head(cls_tokens[:, 0])