add a version of simple vit using flash attention

* Create mp3.py

* Implementation: Position Prediction as an Effective Pretraining Strategy

* Added description for Masked Position Prediction

* MP3 image added

.github/FUNDING.yml

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

.github/workflows/python-test.yml

@@ -0,0 +1,33 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Test
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.7, 3.8, 3.9]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Test with pytest
+      run: |
+        python setup.py test

MANIFEST.in

@@ -0,0 +1 @@
+recursive-include tests *

examples/cats_and_dogs.ipynb

@@ -16,7 +16,7 @@
     "\n",
     "* Dogs vs. Cats Redux: Kernels Edition - https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition\n",
     "* Base Code - https://www.kaggle.com/reukki/pytorch-cnn-tutorial-with-cats-and-dogs/\n",
-    "* Effecient Attention Implementation - https://github.com/lucidrains/vit-pytorch#efficient-attention"
+    "* Efficient Attention Implementation - https://github.com/lucidrains/vit-pytorch#efficient-attention"
    ]
   },
   {
@@ -342,7 +342,7 @@
     "id": "ZhYDJXk2SRDu"
    },
    "source": [
-    "## Image Augumentation"
+    "## Image Augmentation"
    ]
   },
   {
@@ -364,9 +364,8 @@
     "\n",
     "val_transforms = transforms.Compose(\n",
     "    [\n",
-    "        transforms.Resize((224, 224)),\n",
-    "        transforms.RandomResizedCrop(224),\n",
-    "        transforms.RandomHorizontalFlip(),\n",
+    "        transforms.Resize(256),\n",
+    "        transforms.CenterCrop(224),\n",
     "        transforms.ToTensor(),\n",
     "    ]\n",
     ")\n",
@@ -374,9 +373,8 @@
     "\n",
     "test_transforms = transforms.Compose(\n",
     "    [\n",
-    "        transforms.Resize((224, 224)),\n",
-    "        transforms.RandomResizedCrop(224),\n",
-    "        transforms.RandomHorizontalFlip(),\n",
+    "        transforms.Resize(256),\n",
+    "        transforms.CenterCrop(224),\n",
     "        transforms.ToTensor(),\n",
     "    ]\n",
     ")\n"
@@ -499,7 +497,7 @@
     "id": "TF9yMaRrSvmv"
    },
    "source": [
-    "## Effecient Attention"
+    "## Efficient Attention"
    ]
   },
   {
@@ -1309,7 +1307,7 @@
   "celltoolbar": "Edit Metadata",
   "colab": {
    "collapsed_sections": [],
-   "name": "Effecient Attention | Cats & Dogs",
+   "name": "Efficient Attention | Cats & Dogs",
    "provenance": [],
    "toc_visible": true
   },
@@ -6250,4 +6248,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 1
-}
+}

setup.py

@@ -3,9 +3,10 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.20.6',
+  version = '1.2.0',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
+  long_description_content_type = 'text/markdown',
   author = 'Phil Wang',
   author_email = 'lucidrains@gmail.com',
   url = 'https://github.com/lucidrains/vit-pytorch',
@@ -15,10 +16,18 @@ setup(
     'image recognition'
   ],
   install_requires=[
-    'einops>=0.3',
-    'torch>=1.6',
+    'einops>=0.6.0',
+    'torch>=1.10',
     'torchvision'
   ],
+  setup_requires=[
+    'pytest-runner',
+  ],
+  tests_require=[
+    'pytest',
+    'torch==1.12.1',
+    'torchvision==0.13.1'
+  ],
   classifiers=[
     'Development Status :: 4 - Beta',
     'Intended Audience :: Developers',

tests/test.py

@@ -0,0 +1,20 @@
+import torch
+from vit_pytorch import ViT
+
+def test():
+    v = ViT(
+        image_size = 256,
+        patch_size = 32,
+        num_classes = 1000,
+        dim = 1024,
+        depth = 6,
+        heads = 16,
+        mlp_dim = 2048,
+        dropout = 0.1,
+        emb_dropout = 0.1
+    )
+
+    img = torch.randn(1, 3, 256, 256)
+
+    preds = v(img)
+    assert preds.shape == (1, 1000), 'correct logits outputted'

vit_pytorch/__init__.py

@@ -1,2 +1,5 @@
 from vit_pytorch.vit import ViT
+from vit_pytorch.simple_vit import SimpleViT
+
+from vit_pytorch.mae import MAE
 from vit_pytorch.dino import Dino

vit_pytorch/ats_vit.py

@@ -0,0 +1,267 @@
+import torch
+import torch.nn.functional as F
+from torch.nn.utils.rnn import pad_sequence
+from torch import nn, einsum
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# adaptive token sampling functions and classes
+
+def log(t, eps = 1e-6):
+    return torch.log(t + eps)
+
+def sample_gumbel(shape, device, dtype, eps = 1e-6):
+    u = torch.empty(shape, device = device, dtype = dtype).uniform_(0, 1)
+    return -log(-log(u, eps), eps)
+
+def batched_index_select(values, indices, dim = 1):
+    value_dims = values.shape[(dim + 1):]
+    values_shape, indices_shape = map(lambda t: list(t.shape), (values, indices))
+    indices = indices[(..., *((None,) * len(value_dims)))]
+    indices = indices.expand(*((-1,) * len(indices_shape)), *value_dims)
+    value_expand_len = len(indices_shape) - (dim + 1)
+    values = values[(*((slice(None),) * dim), *((None,) * value_expand_len), ...)]
+
+    value_expand_shape = [-1] * len(values.shape)
+    expand_slice = slice(dim, (dim + value_expand_len))
+    value_expand_shape[expand_slice] = indices.shape[expand_slice]
+    values = values.expand(*value_expand_shape)
+
+    dim += value_expand_len
+    return values.gather(dim, indices)
+
+class AdaptiveTokenSampling(nn.Module):
+    def __init__(self, output_num_tokens, eps = 1e-6):
+        super().__init__()
+        self.eps = eps
+        self.output_num_tokens = output_num_tokens
+
+    def forward(self, attn, value, mask):
+        heads, output_num_tokens, eps, device, dtype = attn.shape[1], self.output_num_tokens, self.eps, attn.device, attn.dtype
+
+        # first get the attention values for CLS token to all other tokens
+
+        cls_attn = attn[..., 0, 1:]
+
+        # calculate the norms of the values, for weighting the scores, as described in the paper
+
+        value_norms = value[..., 1:, :].norm(dim = -1)
+
+        # weigh the attention scores by the norm of the values, sum across all heads
+
+        cls_attn = einsum('b h n, b h n -> b n', cls_attn, value_norms)
+
+        # normalize to 1
+
+        normed_cls_attn = cls_attn / (cls_attn.sum(dim = -1, keepdim = True) + eps)
+
+        # instead of using inverse transform sampling, going to invert the softmax and use gumbel-max sampling instead
+
+        pseudo_logits = log(normed_cls_attn)
+
+        # mask out pseudo logits for gumbel-max sampling
+
+        mask_without_cls = mask[:, 1:]
+        mask_value = -torch.finfo(attn.dtype).max / 2
+        pseudo_logits = pseudo_logits.masked_fill(~mask_without_cls, mask_value)
+
+        # expand k times, k being the adaptive sampling number
+
+        pseudo_logits = repeat(pseudo_logits, 'b n -> b k n', k = output_num_tokens)
+        pseudo_logits = pseudo_logits + sample_gumbel(pseudo_logits.shape, device = device, dtype = dtype)
+
+        # gumble-max and add one to reserve 0 for padding / mask
+
+        sampled_token_ids = pseudo_logits.argmax(dim = -1) + 1
+
+        # calculate unique using torch.unique and then pad the sequence from the right
+
+        unique_sampled_token_ids_list = [torch.unique(t, sorted = True) for t in torch.unbind(sampled_token_ids)]
+        unique_sampled_token_ids = pad_sequence(unique_sampled_token_ids_list, batch_first = True)
+
+        # calculate the new mask, based on the padding
+
+        new_mask = unique_sampled_token_ids != 0
+
+        # CLS token never gets masked out (gets a value of True)
+
+        new_mask = F.pad(new_mask, (1, 0), value = True)
+
+        # prepend a 0 token id to keep the CLS attention scores
+
+        unique_sampled_token_ids = F.pad(unique_sampled_token_ids, (1, 0), value = 0)
+        expanded_unique_sampled_token_ids = repeat(unique_sampled_token_ids, 'b n -> b h n', h = heads)
+
+        # gather the new attention scores
+
+        new_attn = batched_index_select(attn, expanded_unique_sampled_token_ids, dim = 2)
+
+        # return the sampled attention scores, new mask (denoting padding), as well as the sampled token indices (for the residual)
+        return new_attn, new_mask, unique_sampled_token_ids
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0., output_num_tokens = None):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.output_num_tokens = output_num_tokens
+        self.ats = AdaptiveTokenSampling(output_num_tokens) if exists(output_num_tokens) else None
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, *, mask):
+        num_tokens = x.shape[1]
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        if exists(mask):
+            dots_mask = rearrange(mask, 'b i -> b 1 i 1') * rearrange(mask, 'b j -> b 1 1 j')
+            mask_value = -torch.finfo(dots.dtype).max
+            dots = dots.masked_fill(~dots_mask, mask_value)
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        sampled_token_ids = None
+
+        # if adaptive token sampling is enabled
+        # and number of tokens is greater than the number of output tokens
+        if exists(self.output_num_tokens) and (num_tokens - 1) > self.output_num_tokens:
+            attn, mask, sampled_token_ids = self.ats(attn, v, mask = mask)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+
+        return self.to_out(out), mask, sampled_token_ids
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, max_tokens_per_depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        assert len(max_tokens_per_depth) == depth, 'max_tokens_per_depth must be a tuple of length that is equal to the depth of the transformer'
+        assert sorted(max_tokens_per_depth, reverse = True) == list(max_tokens_per_depth), 'max_tokens_per_depth must be in decreasing order'
+        assert min(max_tokens_per_depth) > 0, 'max_tokens_per_depth must have at least 1 token at any layer'
+
+        self.layers = nn.ModuleList([])
+        for _, output_num_tokens in zip(range(depth), max_tokens_per_depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, output_num_tokens = output_num_tokens, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+
+    def forward(self, x):
+        b, n, device = *x.shape[:2], x.device
+
+        # use mask to keep track of the paddings when sampling tokens
+        # as the duplicates (when sampling) are just removed, as mentioned in the paper
+        mask = torch.ones((b, n), device = device, dtype = torch.bool)
+
+        token_ids = torch.arange(n, device = device)
+        token_ids = repeat(token_ids, 'n -> b n', b = b)
+
+        for attn, ff in self.layers:
+            attn_out, mask, sampled_token_ids = attn(x, mask = mask)
+
+            # when token sampling, one needs to then gather the residual tokens with the sampled token ids
+            if exists(sampled_token_ids):
+                x = batched_index_select(x, sampled_token_ids, dim = 1)
+                token_ids = batched_index_select(token_ids, sampled_token_ids, dim = 1)
+
+            x = x + attn_out
+
+            x = ff(x) + x
+
+        return x, token_ids
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, max_tokens_per_depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, max_tokens_per_depth, heads, dim_head, mlp_dim, dropout)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img, return_sampled_token_ids = False):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x, token_ids = self.transformer(x)
+
+        logits = self.mlp_head(x[:, 0])
+
+        if return_sampled_token_ids:
+            # remove CLS token and decrement by 1 to make -1 the padding
+            token_ids = token_ids[:, 1:] - 1
+            return logits, token_ids
+
+        return logits

vit_pytorch/cait.py

@@ -76,6 +76,7 @@ class Attention(nn.Module):
         self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
 
         self.mix_heads_pre_attn = nn.Parameter(torch.randn(heads, heads))
         self.mix_heads_post_attn = nn.Parameter(torch.randn(heads, heads))
@@ -96,7 +97,10 @@ class Attention(nn.Module):
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         dots = einsum('b h i j, h g -> b g i j', dots, self.mix_heads_pre_attn)    # talking heads, pre-softmax
+
         attn = self.attend(dots)
+        attn = self.dropout(attn)
+
         attn = einsum('b h i j, h g -> b g i j', attn, self.mix_heads_post_attn)   # talking heads, post-softmax
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
@@ -146,7 +150,9 @@ class CaiT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches, dim))

vit_pytorch/cct.py

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

vit_pytorch/cct_3d.py

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

vit_pytorch/cross_vit.py

@@ -48,6 +48,8 @@ class Attention(nn.Module):
         self.scale = dim_head ** -0.5
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
         self.to_q = nn.Linear(dim, inner_dim, bias = False)
         self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
 
@@ -69,6 +71,7 @@ class Attention(nn.Module):
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
@@ -183,7 +186,9 @@ class ImageEmbedder(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/crossformer.py

@@ -0,0 +1,267 @@
+import torch
+from torch import nn, einsum
+from einops import rearrange
+from einops.layers.torch import Rearrange, Reduce
+import torch.nn.functional as F
+
+# helpers
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# cross embed layer
+
+class CrossEmbedLayer(nn.Module):
+    def __init__(
+        self,
+        dim_in,
+        dim_out,
+        kernel_sizes,
+        stride = 2
+    ):
+        super().__init__()
+        kernel_sizes = sorted(kernel_sizes)
+        num_scales = len(kernel_sizes)
+
+        # calculate the dimension at each scale
+        dim_scales = [int(dim_out / (2 ** i)) for i in range(1, num_scales)]
+        dim_scales = [*dim_scales, dim_out - sum(dim_scales)]
+
+        self.convs = nn.ModuleList([])
+        for kernel, dim_scale in zip(kernel_sizes, dim_scales):
+            self.convs.append(nn.Conv2d(dim_in, dim_scale, kernel, stride = stride, padding = (kernel - stride) // 2))
+
+    def forward(self, x):
+        fmaps = tuple(map(lambda conv: conv(x), self.convs))
+        return torch.cat(fmaps, dim = 1)
+
+# dynamic positional bias
+
+def DynamicPositionBias(dim):
+    return nn.Sequential(
+        nn.Linear(2, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, 1),
+        Rearrange('... () -> ...')
+    )
+
+# transformer classes
+
+class LayerNorm(nn.Module):
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
+
+def FeedForward(dim, mult = 4, dropout = 0.):
+    return nn.Sequential(
+        LayerNorm(dim),
+        nn.Conv2d(dim, dim * mult, 1),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Conv2d(dim * mult, dim, 1)
+    )
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        attn_type,
+        window_size,
+        dim_head = 32,
+        dropout = 0.
+    ):
+        super().__init__()
+        assert attn_type in {'short', 'long'}, 'attention type must be one of local or distant'
+        heads = dim // dim_head
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        inner_dim = dim_head * heads
+
+        self.attn_type = attn_type
+        self.window_size = window_size
+
+        self.norm = LayerNorm(dim)
+
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
+        self.to_out = nn.Conv2d(inner_dim, dim, 1)
+
+        # positions
+
+        self.dpb = DynamicPositionBias(dim // 4)
+
+        # calculate and store indices for retrieving bias
+
+        pos = torch.arange(window_size)
+        grid = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
+        grid = rearrange(grid, 'c i j -> (i j) c')
+        rel_pos = grid[:, None] - grid[None, :]
+        rel_pos += window_size - 1
+        rel_pos_indices = (rel_pos * torch.tensor([2 * window_size - 1, 1])).sum(dim = -1)
+
+        self.register_buffer('rel_pos_indices', rel_pos_indices, persistent = False)
+
+    def forward(self, x):
+        *_, height, width, heads, wsz, device = *x.shape, self.heads, self.window_size, x.device
+
+        # prenorm
+
+        x = self.norm(x)
+
+        # rearrange for short or long distance attention
+
+        if self.attn_type == 'short':
+            x = rearrange(x, 'b d (h s1) (w s2) -> (b h w) d s1 s2', s1 = wsz, s2 = wsz)
+        elif self.attn_type == 'long':
+            x = rearrange(x, 'b d (l1 h) (l2 w) -> (b h w) d l1 l2', l1 = wsz, l2 = wsz)
+
+        # queries / keys / values
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = 1)
+
+        # split heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) x y -> b h (x y) d', h = heads), (q, k, v))
+        q = q * self.scale
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add dynamic positional bias
+
+        pos = torch.arange(-wsz, wsz + 1, device = device)
+        rel_pos = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
+        rel_pos = rearrange(rel_pos, 'c i j -> (i j) c')
+        biases = self.dpb(rel_pos.float())
+        rel_pos_bias = biases[self.rel_pos_indices]
+
+        sim = sim + rel_pos_bias
+
+        # attend
+
+        attn = sim.softmax(dim = -1)
+        attn = self.dropout(attn)
+
+        # merge heads
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+        out = rearrange(out, 'b h (x y) d -> b (h d) x y', x = wsz, y = wsz)
+        out = self.to_out(out)
+
+        # rearrange back for long or short distance attention
+
+        if self.attn_type == 'short':
+            out = rearrange(out, '(b h w) d s1 s2 -> b d (h s1) (w s2)', h = height // wsz, w = width // wsz)
+        elif self.attn_type == 'long':
+            out = rearrange(out, '(b h w) d l1 l2 -> b d (l1 h) (l2 w)', h = height // wsz, w = width // wsz)
+
+        return out
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        *,
+        local_window_size,
+        global_window_size,
+        depth = 4,
+        dim_head = 32,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, attn_type = 'short', window_size = local_window_size, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout),
+                Attention(dim, attn_type = 'long', window_size = global_window_size, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout)
+            ]))
+
+    def forward(self, x):
+        for short_attn, short_ff, long_attn, long_ff in self.layers:
+            x = short_attn(x) + x
+            x = short_ff(x) + x
+            x = long_attn(x) + x
+            x = long_ff(x) + x
+
+        return x
+
+# classes
+
+class CrossFormer(nn.Module):
+    def __init__(
+        self,
+        *,
+        dim = (64, 128, 256, 512),
+        depth = (2, 2, 8, 2),
+        global_window_size = (8, 4, 2, 1),
+        local_window_size = 7,
+        cross_embed_kernel_sizes = ((4, 8, 16, 32), (2, 4), (2, 4), (2, 4)),
+        cross_embed_strides = (4, 2, 2, 2),
+        num_classes = 1000,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+        channels = 3
+    ):
+        super().__init__()
+
+        dim = cast_tuple(dim, 4)
+        depth = cast_tuple(depth, 4)
+        global_window_size = cast_tuple(global_window_size, 4)
+        local_window_size = cast_tuple(local_window_size, 4)
+        cross_embed_kernel_sizes = cast_tuple(cross_embed_kernel_sizes, 4)
+        cross_embed_strides = cast_tuple(cross_embed_strides, 4)
+
+        assert len(dim) == 4
+        assert len(depth) == 4
+        assert len(global_window_size) == 4
+        assert len(local_window_size) == 4
+        assert len(cross_embed_kernel_sizes) == 4
+        assert len(cross_embed_strides) == 4
+
+        # dimensions
+
+        last_dim = dim[-1]
+        dims = [channels, *dim]
+        dim_in_and_out = tuple(zip(dims[:-1], dims[1:]))
+
+        # layers
+
+        self.layers = nn.ModuleList([])
+
+        for (dim_in, dim_out), layers, global_wsz, local_wsz, cel_kernel_sizes, cel_stride in zip(dim_in_and_out, depth, global_window_size, local_window_size, cross_embed_kernel_sizes, cross_embed_strides):
+            self.layers.append(nn.ModuleList([
+                CrossEmbedLayer(dim_in, dim_out, cel_kernel_sizes, stride = cel_stride),
+                Transformer(dim_out, local_window_size = local_wsz, global_window_size = global_wsz, depth = layers, attn_dropout = attn_dropout, ff_dropout = ff_dropout)
+            ]))
+
+        # final logits
+
+        self.to_logits = nn.Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(last_dim, num_classes)
+        )
+
+    def forward(self, x):
+        for cel, transformer in self.layers:
+            x = cel(x)
+            x = transformer(x)
+
+        return self.to_logits(x)

vit_pytorch/cvt.py

@@ -30,9 +30,9 @@ class LayerNorm(nn.Module): # layernorm, but done in the channel dimension #1
         self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
 
     def forward(self, x):
-        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (std + self.eps) * self.g + self.b
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
 class PreNorm(nn.Module):
     def __init__(self, dim, fn):
@@ -76,6 +76,7 @@ class Attention(nn.Module):
         self.scale = dim_head ** -0.5
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
 
         self.to_q = DepthWiseConv2d(dim, inner_dim, proj_kernel, padding = padding, stride = 1, bias = False)
         self.to_kv = DepthWiseConv2d(dim, inner_dim * 2, proj_kernel, padding = padding, stride = kv_proj_stride, bias = False)
@@ -94,6 +95,7 @@ class Attention(nn.Module):
         dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b i j, b j d -> b i d', attn, v)
         out = rearrange(out, '(b h) (x y) d -> b (h d) x y', h = h, y = y)
@@ -162,12 +164,14 @@ class CvT(nn.Module):
 
             dim = config['emb_dim']
 
-        self.layers = nn.Sequential(
-            *layers,
+        self.layers = nn.Sequential(*layers)
+
+        self.to_logits = nn.Sequential(
             nn.AdaptiveAvgPool2d(1),
             Rearrange('... () () -> ...'),
             nn.Linear(dim, num_classes)
         )
 
     def forward(self, x):
-        return self.layers(x)
+        latents = self.layers(x)
+        return self.to_logits(latents)

vit_pytorch/deepvit.py

@@ -42,6 +42,8 @@ class Attention(nn.Module):
 
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
+        self.dropout = nn.Dropout(dropout)
+
         self.reattn_weights = nn.Parameter(torch.randn(heads, heads))
 
         self.reattn_norm = nn.Sequential(
@@ -64,6 +66,7 @@ class Attention(nn.Module):
 
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
         attn = dots.softmax(dim=-1)
+        attn = self.dropout(attn)
 
         # re-attention
 
@@ -102,7 +105,9 @@ class DeepViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/efficient.py

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

vit_pytorch/es_vit.py

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

vit_pytorch/extractor.py

@@ -0,0 +1,90 @@
+import torch
+from torch import nn
+
+def exists(val):
+    return val is not None
+
+def identity(t):
+    return t
+
+def clone_and_detach(t):
+    return t.clone().detach()
+
+def apply_tuple_or_single(fn, val):
+    if isinstance(val, tuple):
+        return tuple(map(fn, val))
+    return fn(val)
+
+class Extractor(nn.Module):
+    def __init__(
+        self,
+        vit,
+        device = None,
+        layer = None,
+        layer_name = 'transformer',
+        layer_save_input = False,
+        return_embeddings_only = False,
+        detach = True
+    ):
+        super().__init__()
+        self.vit = vit
+
+        self.data = None
+        self.latents = None
+        self.hooks = []
+        self.hook_registered = False
+        self.ejected = False
+        self.device = device
+
+        self.layer = layer
+        self.layer_name = layer_name
+        self.layer_save_input = layer_save_input # whether to save input or output of layer
+        self.return_embeddings_only = return_embeddings_only
+
+        self.detach_fn = clone_and_detach if detach else identity
+
+    def _hook(self, _, inputs, output):
+        layer_output = inputs if self.layer_save_input else output
+        self.latents = apply_tuple_or_single(self.detach_fn, layer_output)
+
+    def _register_hook(self):
+        if not exists(self.layer):
+            assert hasattr(self.vit, self.layer_name), 'layer whose output to take as embedding not found in vision transformer'
+            layer = getattr(self.vit, self.layer_name)
+        else:
+            layer = self.layer
+
+        handle = layer.register_forward_hook(self._hook)
+        self.hooks.append(handle)
+        self.hook_registered = True
+
+    def eject(self):
+        self.ejected = True
+        for hook in self.hooks:
+            hook.remove()
+        self.hooks.clear()
+        return self.vit
+
+    def clear(self):
+        del self.latents
+        self.latents = None
+
+    def forward(
+        self,
+        img,
+        return_embeddings_only = False
+    ):
+        assert not self.ejected, 'extractor has been ejected, cannot be used anymore'
+        self.clear()
+        if not self.hook_registered:
+            self._register_hook()
+
+        pred = self.vit(img)
+
+        target_device = self.device if exists(self.device) else img.device
+        latents = apply_tuple_or_single(lambda t: t.to(target_device), self.latents)
+
+        if return_embeddings_only or self.return_embeddings_only:
+            return latents
+
+        return pred, latents

vit_pytorch/learnable_memory_vit.py

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

vit_pytorch/levit.py

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

vit_pytorch/local_vit.py

@@ -78,6 +78,7 @@ class Attention(nn.Module):
         self.scale = dim_head ** -0.5
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.to_out = nn.Sequential(
@@ -93,6 +94,7 @@ class Attention(nn.Module):
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
@@ -124,7 +126,9 @@ class LocalViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))

vit_pytorch/mae.py

@@ -0,0 +1,101 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+from einops import repeat
+
+from vit_pytorch.vit import Transformer
+
+class MAE(nn.Module):
+    def __init__(
+        self,
+        *,
+        encoder,
+        decoder_dim,
+        masking_ratio = 0.75,
+        decoder_depth = 1,
+        decoder_heads = 8,
+        decoder_dim_head = 64
+    ):
+        super().__init__()
+        assert masking_ratio > 0 and masking_ratio < 1, 'masking ratio must be kept between 0 and 1'
+        self.masking_ratio = masking_ratio
+
+        # extract some hyperparameters and functions from encoder (vision transformer to be trained)
+
+        self.encoder = encoder
+        num_patches, encoder_dim = encoder.pos_embedding.shape[-2:]
+
+        self.to_patch = encoder.to_patch_embedding[0]
+        self.patch_to_emb = nn.Sequential(*encoder.to_patch_embedding[1:])
+
+        pixel_values_per_patch = encoder.to_patch_embedding[2].weight.shape[-1]
+
+        # decoder parameters
+        self.decoder_dim = decoder_dim
+        self.enc_to_dec = nn.Linear(encoder_dim, decoder_dim) if encoder_dim != decoder_dim else nn.Identity()
+        self.mask_token = nn.Parameter(torch.randn(decoder_dim))
+        self.decoder = Transformer(dim = decoder_dim, depth = decoder_depth, heads = decoder_heads, dim_head = decoder_dim_head, mlp_dim = decoder_dim * 4)
+        self.decoder_pos_emb = nn.Embedding(num_patches, decoder_dim)
+        self.to_pixels = nn.Linear(decoder_dim, pixel_values_per_patch)
+
+    def forward(self, img):
+        device = img.device
+
+        # get patches
+
+        patches = self.to_patch(img)
+        batch, num_patches, *_ = patches.shape
+
+        # patch to encoder tokens and add positions
+
+        tokens = self.patch_to_emb(patches)
+        tokens = tokens + self.encoder.pos_embedding[:, 1:(num_patches + 1)]
+
+        # calculate of patches needed to be masked, and get random indices, dividing it up for mask vs unmasked
+
+        num_masked = int(self.masking_ratio * num_patches)
+        rand_indices = torch.rand(batch, num_patches, device = device).argsort(dim = -1)
+        masked_indices, unmasked_indices = rand_indices[:, :num_masked], rand_indices[:, num_masked:]
+
+        # get the unmasked tokens to be encoded
+
+        batch_range = torch.arange(batch, device = device)[:, None]
+        tokens = tokens[batch_range, unmasked_indices]
+
+        # get the patches to be masked for the final reconstruction loss
+
+        masked_patches = patches[batch_range, masked_indices]
+
+        # attend with vision transformer
+
+        encoded_tokens = self.encoder.transformer(tokens)
+
+        # project encoder to decoder dimensions, if they are not equal - the paper says you can get away with a smaller dimension for decoder
+
+        decoder_tokens = self.enc_to_dec(encoded_tokens)
+
+        # reapply decoder position embedding to unmasked tokens
+
+        unmasked_decoder_tokens = decoder_tokens + self.decoder_pos_emb(unmasked_indices)
+
+        # repeat mask tokens for number of masked, and add the positions using the masked indices derived above
+
+        mask_tokens = repeat(self.mask_token, 'd -> b n d', b = batch, n = num_masked)
+        mask_tokens = mask_tokens + self.decoder_pos_emb(masked_indices)
+
+        # concat the masked tokens to the decoder tokens and attend with decoder
+        
+        decoder_tokens = torch.zeros(batch, num_patches, self.decoder_dim, device=device)
+        decoder_tokens[batch_range, unmasked_indices] = unmasked_decoder_tokens
+        decoder_tokens[batch_range, masked_indices] = mask_tokens
+        decoded_tokens = self.decoder(decoder_tokens)
+
+        # splice out the mask tokens and project to pixel values
+
+        mask_tokens = decoded_tokens[batch_range, masked_indices]
+        pred_pixel_values = self.to_pixels(mask_tokens)
+
+        # calculate reconstruction loss
+
+        recon_loss = F.mse_loss(pred_pixel_values, masked_patches)
+        return recon_loss

vit_pytorch/max_vit.py

@@ -0,0 +1,288 @@
+from functools import partial
+
+import torch
+from torch import nn, einsum
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+class PreNormResidual(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
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mult = 4, dropout = 0.):
+        super().__init__()
+        inner_dim = int(dim * mult)
+        self.net = nn.Sequential(
+            nn.Linear(dim, inner_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# MBConv
+
+class SqueezeExcitation(nn.Module):
+    def __init__(self, dim, shrinkage_rate = 0.25):
+        super().__init__()
+        hidden_dim = int(dim * shrinkage_rate)
+
+        self.gate = nn.Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(dim, hidden_dim, bias = False),
+            nn.SiLU(),
+            nn.Linear(hidden_dim, dim, bias = False),
+            nn.Sigmoid(),
+            Rearrange('b c -> b c 1 1')
+        )
+
+    def forward(self, x):
+        return x * self.gate(x)
+
+
+class MBConvResidual(nn.Module):
+    def __init__(self, fn, dropout = 0.):
+        super().__init__()
+        self.fn = fn
+        self.dropsample = Dropsample(dropout)
+
+    def forward(self, x):
+        out = self.fn(x)
+        out = self.dropsample(out)
+        return out + x
+
+class Dropsample(nn.Module):
+    def __init__(self, prob = 0):
+        super().__init__()
+        self.prob = prob
+  
+    def forward(self, x):
+        device = x.device
+
+        if self.prob == 0. or (not self.training):
+            return x
+
+        keep_mask = torch.FloatTensor((x.shape[0], 1, 1, 1), device = device).uniform_() > self.prob
+        return x * keep_mask / (1 - self.prob)
+
+def MBConv(
+    dim_in,
+    dim_out,
+    *,
+    downsample,
+    expansion_rate = 4,
+    shrinkage_rate = 0.25,
+    dropout = 0.
+):
+    hidden_dim = int(expansion_rate * dim_out)
+    stride = 2 if downsample else 1
+
+    net = nn.Sequential(
+        nn.Conv2d(dim_in, hidden_dim, 1),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        nn.Conv2d(hidden_dim, hidden_dim, 3, stride = stride, padding = 1, groups = hidden_dim),
+        nn.BatchNorm2d(hidden_dim),
+        nn.GELU(),
+        SqueezeExcitation(hidden_dim, shrinkage_rate = shrinkage_rate),
+        nn.Conv2d(hidden_dim, dim_out, 1),
+        nn.BatchNorm2d(dim_out)
+    )
+
+    if dim_in == dim_out and not downsample:
+        net = MBConvResidual(net, dropout = dropout)
+
+    return net
+
+# attention related classes
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        dim_head = 32,
+        dropout = 0.,
+        window_size = 7
+    ):
+        super().__init__()
+        assert (dim % dim_head) == 0, 'dimension should be divisible by dimension per head'
+
+        self.heads = dim // dim_head
+        self.scale = dim_head ** -0.5
+
+        self.to_qkv = nn.Linear(dim, dim * 3, bias = False)
+
+        self.attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_out = nn.Sequential(
+            nn.Linear(dim, dim, bias = False),
+            nn.Dropout(dropout)
+        )
+
+        # relative positional bias
+
+        self.rel_pos_bias = nn.Embedding((2 * window_size - 1) ** 2, self.heads)
+
+        pos = torch.arange(window_size)
+        grid = torch.stack(torch.meshgrid(pos, pos, indexing = 'ij'))
+        grid = rearrange(grid, 'c i j -> (i j) c')
+        rel_pos = rearrange(grid, 'i ... -> i 1 ...') - rearrange(grid, 'j ... -> 1 j ...')
+        rel_pos += window_size - 1
+        rel_pos_indices = (rel_pos * torch.tensor([2 * window_size - 1, 1])).sum(dim = -1)
+
+        self.register_buffer('rel_pos_indices', rel_pos_indices, persistent = False)
+
+    def forward(self, x):
+        batch, height, width, window_height, window_width, _, device, h = *x.shape, x.device, self.heads
+
+        # flatten
+
+        x = rearrange(x, 'b x y w1 w2 d -> (b x y) (w1 w2) d')
+
+        # project for queries, keys, values
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = -1)
+
+        # split heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d ) -> b h n d', h = h), (q, k, v))
+
+        # scale
+
+        q = q * self.scale
+
+        # sim
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add positional bias
+
+        bias = self.rel_pos_bias(self.rel_pos_indices)
+        sim = sim + rearrange(bias, 'i j h -> h i j')
+
+        # attention
+
+        attn = self.attend(sim)
+
+        # aggregate
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+
+        # merge heads
+
+        out = rearrange(out, 'b h (w1 w2) d -> b w1 w2 (h d)', w1 = window_height, w2 = window_width)
+
+        # combine heads out
+
+        out = self.to_out(out)
+        return rearrange(out, '(b x y) ... -> b x y ...', x = height, y = width)
+
+class MaxViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        dim_head = 32,
+        dim_conv_stem = None,
+        window_size = 7,
+        mbconv_expansion_rate = 4,
+        mbconv_shrinkage_rate = 0.25,
+        dropout = 0.1,
+        channels = 3
+    ):
+        super().__init__()
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+
+        # convolutional stem
+
+        dim_conv_stem = default(dim_conv_stem, dim)
+
+        self.conv_stem = nn.Sequential(
+            nn.Conv2d(channels, dim_conv_stem, 3, stride = 2, padding = 1),
+            nn.Conv2d(dim_conv_stem, dim_conv_stem, 3, padding = 1)
+        )
+
+        # variables
+
+        num_stages = len(depth)
+
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+        dims = (dim_conv_stem, *dims)
+        dim_pairs = tuple(zip(dims[:-1], dims[1:]))
+
+        self.layers = nn.ModuleList([])
+
+        # shorthand for window size for efficient block - grid like attention
+
+        w = window_size
+
+        # iterate through stages
+
+        for ind, ((layer_dim_in, layer_dim), layer_depth) in enumerate(zip(dim_pairs, depth)):
+            for stage_ind in range(layer_depth):
+                is_first = stage_ind == 0
+                stage_dim_in = layer_dim_in if is_first else layer_dim
+
+                block = nn.Sequential(
+                    MBConv(
+                        stage_dim_in,
+                        layer_dim,
+                        downsample = is_first,
+                        expansion_rate = mbconv_expansion_rate,
+                        shrinkage_rate = mbconv_shrinkage_rate
+                    ),
+                    Rearrange('b d (x w1) (y w2) -> b x y w1 w2 d', w1 = w, w2 = w),  # block-like attention
+                    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)),
+                    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)),
+                    Rearrange('b x y w1 w2 d -> b d (w1 x) (w2 y)'),
+                )
+
+                self.layers.append(block)
+
+        # mlp head out
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, x):
+        x = self.conv_stem(x)
+
+        for stage in self.layers:
+            x = stage(x)
+
+        return self.mlp_head(x)

vit_pytorch/mobile_vit.py

@@ -0,0 +1,252 @@
+import torch
+import torch.nn as nn
+
+from einops import rearrange
+from einops.layers.torch import Reduce
+
+# helpers
+
+def conv_1x1_bn(inp, oup):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.SiLU()
+    )
+
+def conv_nxn_bn(inp, oup, kernel_size=3, stride=1):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, kernel_size, stride, 1, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.SiLU()
+    )
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout=0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.SiLU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads=8, dim_head=64, dropout=0.):
+        super().__init__()
+        inner_dim = dim_head * heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim=-1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias=False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim=-1)
+        q, k, v = map(lambda t: rearrange(
+            t, 'b p n (h d) -> b p h n d', h=self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b p h n d -> b p n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    """Transformer block described in ViT.
+    Paper: https://arxiv.org/abs/2010.11929
+    Based on: https://github.com/lucidrains/vit-pytorch
+    """
+
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout=0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads, dim_head, dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout))
+            ]))
+
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class MV2Block(nn.Module):
+    """MV2 block described in MobileNetV2.
+    Paper: https://arxiv.org/pdf/1801.04381
+    Based on: https://github.com/tonylins/pytorch-mobilenet-v2
+    """
+
+    def __init__(self, inp, oup, stride=1, expansion=4):
+        super().__init__()
+        self.stride = stride
+        assert stride in [1, 2]
+
+        hidden_dim = int(inp * expansion)
+        self.use_res_connect = self.stride == 1 and inp == oup
+
+        if expansion == 1:
+            self.conv = nn.Sequential(
+                # dw
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride,
+                          1, groups=hidden_dim, bias=False),
+                nn.BatchNorm2d(hidden_dim),
+                nn.SiLU(),
+                # pw-linear
+                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
+                nn.BatchNorm2d(oup),
+            )
+        else:
+            self.conv = nn.Sequential(
+                # pw
+                nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
+                nn.BatchNorm2d(hidden_dim),
+                nn.SiLU(),
+                # dw
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride,
+                          1, groups=hidden_dim, bias=False),
+                nn.BatchNorm2d(hidden_dim),
+                nn.SiLU(),
+                # pw-linear
+                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
+                nn.BatchNorm2d(oup),
+            )
+
+    def forward(self, x):
+        out = self.conv(x)
+        if self.use_res_connect:
+            out = out + x
+        return out
+
+class MobileViTBlock(nn.Module):
+    def __init__(self, dim, depth, channel, kernel_size, patch_size, mlp_dim, dropout=0.):
+        super().__init__()
+        self.ph, self.pw = patch_size
+
+        self.conv1 = conv_nxn_bn(channel, channel, kernel_size)
+        self.conv2 = conv_1x1_bn(channel, dim)
+
+        self.transformer = Transformer(dim, depth, 4, 8, mlp_dim, dropout)
+
+        self.conv3 = conv_1x1_bn(dim, channel)
+        self.conv4 = conv_nxn_bn(2 * channel, channel, kernel_size)
+
+    def forward(self, x):
+        y = x.clone()
+
+        # Local representations
+        x = self.conv1(x)
+        x = self.conv2(x)
+
+        # 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)
+
+        # Fusion
+        x = self.conv3(x)
+        x = torch.cat((x, y), 1)
+        x = self.conv4(x)
+        return x
+
+class MobileViT(nn.Module):
+    """MobileViT.
+    Paper: https://arxiv.org/abs/2110.02178
+    Based on: https://github.com/chinhsuanwu/mobilevit-pytorch
+    """
+
+    def __init__(
+        self,
+        image_size,
+        dims,
+        channels,
+        num_classes,
+        expansion=4,
+        kernel_size=3,
+        patch_size=(2, 2),
+        depths=(2, 4, 3)
+    ):
+        super().__init__()
+        assert len(dims) == 3, 'dims must be a tuple of 3'
+        assert len(depths) == 3, 'depths must be a tuple of 3'
+
+        ih, iw = image_size
+        ph, pw = patch_size
+        assert ih % ph == 0 and iw % pw == 0
+
+        init_dim, *_, last_dim = channels
+
+        self.conv1 = conv_nxn_bn(3, init_dim, stride=2)
+
+        self.stem = nn.ModuleList([])
+        self.stem.append(MV2Block(channels[0], channels[1], 1, expansion))
+        self.stem.append(MV2Block(channels[1], channels[2], 2, expansion))
+        self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
+        self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
+
+        self.trunk = nn.ModuleList([])
+        self.trunk.append(nn.ModuleList([
+            MV2Block(channels[3], channels[4], 2, expansion),
+            MobileViTBlock(dims[0], depths[0], channels[5],
+                           kernel_size, patch_size, int(dims[0] * 2))
+        ]))
+
+        self.trunk.append(nn.ModuleList([
+            MV2Block(channels[5], channels[6], 2, expansion),
+            MobileViTBlock(dims[1], depths[1], channels[7],
+                           kernel_size, patch_size, int(dims[1] * 4))
+        ]))
+
+        self.trunk.append(nn.ModuleList([
+            MV2Block(channels[7], channels[8], 2, expansion),
+            MobileViTBlock(dims[2], depths[2], channels[9],
+                           kernel_size, patch_size, int(dims[2] * 4))
+        ]))
+
+        self.to_logits = nn.Sequential(
+            conv_1x1_bn(channels[-2], last_dim),
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(channels[-1], num_classes, bias=False)
+        )
+
+    def forward(self, x):
+        x = self.conv1(x)
+
+        for conv in self.stem:
+            x = conv(x)
+
+        for conv, attn in self.trunk:
+            x = conv(x)
+            x = attn(x)
+
+        return self.to_logits(x)

vit_pytorch/mp3.py

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

vit_pytorch/nest.py

@@ -20,9 +20,9 @@ class LayerNorm(nn.Module):
         self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
 
     def forward(self, x):
-        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (std + self.eps) * self.g + self.b
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
 class PreNorm(nn.Module):
     def __init__(self, dim, fn):
@@ -55,6 +55,7 @@ class Attention(nn.Module):
         self.scale = dim_head ** -0.5
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
 
         self.to_out = nn.Sequential(
@@ -71,6 +72,7 @@ class Attention(nn.Module):
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h (x y) d -> b (h d) x y', x = h, y = w)
@@ -129,19 +131,22 @@ class NesT(nn.Module):
         fmap_size = image_size // patch_size
         blocks = 2 ** (num_hierarchies - 1)
 
-        seq_len = (fmap_size // blocks) ** 2   # sequence length is held constant across heirarchy
+        seq_len = (fmap_size // blocks) ** 2   # sequence length is held constant across hierarchy
         hierarchies = list(reversed(range(num_hierarchies)))
-        mults = [2 ** i for i in hierarchies]
+        mults = [2 ** i for i in reversed(hierarchies)]
 
         layer_heads = list(map(lambda t: t * heads, mults))
         layer_dims = list(map(lambda t: t * dim, mults))
+        last_dim = layer_dims[-1]
 
         layer_dims = [*layer_dims, layer_dims[-1]]
         dim_pairs = zip(layer_dims[:-1], layer_dims[1:])
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (p1 p2 c) h w', p1 = patch_size, p2 = patch_size),
+            LayerNorm(patch_dim),
             nn.Conv2d(patch_dim, layer_dims[0], 1),
+            LayerNorm(layer_dims[0])
         )
 
         block_repeats = cast_tuple(block_repeats, num_hierarchies)
@@ -157,10 +162,11 @@ class NesT(nn.Module):
                 Aggregate(dim_in, dim_out) if not is_last else nn.Identity()
             ]))
 
+
         self.mlp_head = nn.Sequential(
-            LayerNorm(dim),
+            LayerNorm(last_dim),
             Reduce('b c h w -> b c', 'mean'),
-            nn.Linear(dim, num_classes)
+            nn.Linear(last_dim, num_classes)
         )
 
     def forward(self, img):

vit_pytorch/parallel_vit.py

@@ -0,0 +1,140 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class Parallel(nn.Module):
+    def __init__(self, *fns):
+        super().__init__()
+        self.fns = nn.ModuleList(fns)
+
+    def forward(self, x):
+        return sum([fn(x) for fn in self.fns])
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, num_parallel_branches = 2, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        attn_block = lambda: PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout))
+        ff_block = lambda: PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))        
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Parallel(*[attn_block() for _ in range(num_parallel_branches)]),
+                Parallel(*[ff_block() for _ in range(num_parallel_branches)]),
+            ]))
+
+    def forward(self, x):
+        for attns, ffs in self.layers:
+            x = attns(x) + x
+            x = ffs(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', num_parallel_branches = 2, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, num_parallel_branches, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/pit.py

@@ -48,6 +48,7 @@ class Attention(nn.Module):
         self.scale = dim_head ** -0.5
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.to_out = nn.Sequential(
@@ -63,6 +64,7 @@ class Attention(nn.Module):
         dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
@@ -129,14 +131,15 @@ class PiT(nn.Module):
         mlp_dim,
         dim_head = 64,
         dropout = 0.,
-        emb_dropout = 0.
+        emb_dropout = 0.,
+        channels = 3
     ):
         super().__init__()
         assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
         assert isinstance(depth, tuple), 'depth must be a tuple of integers, specifying the number of blocks before each downsizing'
         heads = cast_tuple(heads, len(depth))
 
-        patch_dim = 3 * patch_size ** 2
+        patch_dim = channels * patch_size ** 2
 
         self.to_patch_embedding = nn.Sequential(
             nn.Unfold(kernel_size = patch_size, stride = patch_size // 2),

vit_pytorch/recorder.py

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

vit_pytorch/regionvit.py

@@ -0,0 +1,269 @@
+import torch
+from torch import nn, einsum
+from einops import rearrange
+from einops.layers.torch import Rearrange, Reduce
+import torch.nn.functional as F
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+def divisible_by(val, d):
+    return (val % d) == 0
+
+# helper classes
+
+class Downsample(nn.Module):
+    def __init__(self, dim_in, dim_out):
+        super().__init__()
+        self.conv = nn.Conv2d(dim_in, dim_out, 3, stride = 2, padding = 1)
+
+    def forward(self, x):
+        return self.conv(x)
+
+class PEG(nn.Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        self.proj = nn.Conv2d(dim, dim, kernel_size = kernel_size, padding = kernel_size // 2, groups = dim, stride = 1)
+
+    def forward(self, x):
+        return self.proj(x) + x
+
+# transformer classes
+
+def FeedForward(dim, mult = 4, dropout = 0.):
+    return nn.Sequential(
+        nn.LayerNorm(dim),
+        nn.Linear(dim, dim * mult, 1),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Linear(dim * mult, dim, 1)
+    )
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        heads = 4,
+        dim_head = 32,
+        dropout = 0.
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        inner_dim = dim_head * heads
+
+        self.norm = nn.LayerNorm(dim)
+        self.dropout = nn.Dropout(dropout)
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, rel_pos_bias = None):
+        h = self.heads
+
+        # prenorm
+
+        x = self.norm(x)
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = -1)
+
+        # split heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), (q, k, v))
+        q = q * self.scale
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add relative positional bias for local tokens
+
+        if exists(rel_pos_bias):
+            sim = sim + rel_pos_bias
+
+        attn = sim.softmax(dim = -1)
+        attn = self.dropout(attn)
+
+        # merge heads
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class R2LTransformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        *,
+        window_size,
+        depth = 4,
+        heads = 4,
+        dim_head = 32,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        self.window_size = window_size
+        rel_positions = 2 * window_size - 1
+        self.local_rel_pos_bias = nn.Embedding(rel_positions ** 2, heads)
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, heads = heads, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout)
+            ]))
+
+    def forward(self, local_tokens, region_tokens):
+        device = local_tokens.device
+        lh, lw = local_tokens.shape[-2:]
+        rh, rw = region_tokens.shape[-2:]
+        window_size_h, window_size_w = lh // rh, lw // rw
+
+        local_tokens = rearrange(local_tokens, 'b c h w -> b (h w) c')
+        region_tokens = rearrange(region_tokens, 'b c h w -> b (h w) c')
+
+        # calculate local relative positional bias
+        
+        h_range = torch.arange(window_size_h, device = device)
+        w_range = torch.arange(window_size_w, device = device)
+
+        grid_x, grid_y = torch.meshgrid(h_range, w_range, indexing = 'ij')
+        grid = torch.stack((grid_x, grid_y))
+        grid = rearrange(grid, 'c h w -> c (h w)')
+        grid = (grid[:, :, None] - grid[:, None, :]) + (self.window_size - 1)
+        bias_indices = (grid * torch.tensor([1, self.window_size * 2 - 1], device = device)[:, None, None]).sum(dim = 0)
+        rel_pos_bias = self.local_rel_pos_bias(bias_indices)
+        rel_pos_bias = rearrange(rel_pos_bias, 'i j h -> () h i j')
+        rel_pos_bias = F.pad(rel_pos_bias, (1, 0, 1, 0), value = 0)
+
+        # go through r2l transformer layers
+
+        for attn, ff in self.layers:
+            region_tokens = attn(region_tokens) + region_tokens
+
+            # concat region tokens to local tokens
+
+            local_tokens = rearrange(local_tokens, 'b (h w) d -> b h w d', h = lh)
+            local_tokens = rearrange(local_tokens, 'b (h p1) (w p2) d -> (b h w) (p1 p2) d', p1 = window_size_h, p2 = window_size_w)
+            region_tokens = rearrange(region_tokens, 'b n d -> (b n) () d')
+
+            # do self attention on local tokens, along with its regional token
+
+            region_and_local_tokens = torch.cat((region_tokens, local_tokens), dim = 1)
+            region_and_local_tokens = attn(region_and_local_tokens, rel_pos_bias = rel_pos_bias) + region_and_local_tokens
+
+            # feedforward
+
+            region_and_local_tokens = ff(region_and_local_tokens) + region_and_local_tokens
+
+            # split back local and regional tokens
+
+            region_tokens, local_tokens = region_and_local_tokens[:, :1], region_and_local_tokens[:, 1:]
+            local_tokens = rearrange(local_tokens, '(b h w) (p1 p2) d -> b (h p1 w p2) d', h = lh // window_size_h, w = lw // window_size_w, p1 = window_size_h)
+            region_tokens = rearrange(region_tokens, '(b n) () d -> b n d', n = rh * rw)
+
+        local_tokens = rearrange(local_tokens, 'b (h w) c -> b c h w', h = lh, w = lw)
+        region_tokens = rearrange(region_tokens, 'b (h w) c -> b c h w', h = rh, w = rw)
+        return local_tokens, region_tokens
+
+# classes
+
+class RegionViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        dim = (64, 128, 256, 512),
+        depth = (2, 2, 8, 2),
+        window_size = 7,
+        num_classes = 1000,
+        tokenize_local_3_conv = False,
+        local_patch_size = 4,
+        use_peg = False,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+        channels = 3,
+    ):
+        super().__init__()
+        dim = cast_tuple(dim, 4)
+        depth = cast_tuple(depth, 4)
+        assert len(dim) == 4, 'dim needs to be a single value or a tuple of length 4'
+        assert len(depth) == 4, 'depth needs to be a single value or a tuple of length 4'
+
+        self.local_patch_size = local_patch_size
+
+        region_patch_size = local_patch_size * window_size
+        self.region_patch_size = local_patch_size * window_size
+
+        init_dim, *_, last_dim = dim
+
+        # local and region encoders
+
+        if tokenize_local_3_conv:
+            self.local_encoder = nn.Sequential(
+                nn.Conv2d(3, init_dim, 3, 2, 1),
+                nn.LayerNorm(init_dim),
+                nn.GELU(),
+                nn.Conv2d(init_dim, init_dim, 3, 2, 1),
+                nn.LayerNorm(init_dim),
+                nn.GELU(),
+                nn.Conv2d(init_dim, init_dim, 3, 1, 1)
+            )
+        else:
+            self.local_encoder = nn.Conv2d(3, init_dim, 8, 4, 3)
+
+        self.region_encoder = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (c p1 p2) h w', p1 = region_patch_size, p2 = region_patch_size),
+            nn.Conv2d((region_patch_size ** 2) * channels, init_dim, 1)
+        )
+
+        # layers
+
+        current_dim = init_dim
+        self.layers = nn.ModuleList([])
+
+        for ind, dim, num_layers in zip(range(4), dim, depth):
+            not_first = ind != 0
+            need_downsample = not_first
+            need_peg = not_first and use_peg
+
+            self.layers.append(nn.ModuleList([
+                Downsample(current_dim, dim) if need_downsample else nn.Identity(),
+                PEG(dim) if need_peg else nn.Identity(),
+                R2LTransformer(dim, depth = num_layers, window_size = window_size, attn_dropout = attn_dropout, ff_dropout = ff_dropout)
+            ]))
+
+            current_dim = dim
+
+        # final logits
+
+        self.to_logits = nn.Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.LayerNorm(last_dim),
+            nn.Linear(last_dim, num_classes)
+        )
+
+    def forward(self, x):
+        *_, h, w = x.shape
+        assert divisible_by(h, self.region_patch_size) and divisible_by(w, self.region_patch_size), 'height and width must be divisible by region patch size'
+        assert divisible_by(h, self.local_patch_size) and divisible_by(w, self.local_patch_size), 'height and width must be divisible by local patch size'
+
+        local_tokens = self.local_encoder(x)
+        region_tokens = self.region_encoder(x)
+
+        for down, peg, transformer in self.layers:
+            local_tokens, region_tokens = down(local_tokens), down(region_tokens)
+            local_tokens = peg(local_tokens)
+            local_tokens, region_tokens = transformer(local_tokens, region_tokens)
+
+        return self.to_logits(region_tokens)

vit_pytorch/rvt.py

@@ -19,7 +19,7 @@ class AxialRotaryEmbedding(nn.Module):
     def __init__(self, dim, max_freq = 10):
         super().__init__()
         self.dim = dim
-        scales = torch.logspace(0., log(max_freq / 2) / log(2), self.dim // 4, base = 2)
+        scales = torch.linspace(1., max_freq / 2, self.dim // 4)
         self.register_buffer('scales', scales)
 
     def forward(self, x):
@@ -104,6 +104,7 @@ class Attention(nn.Module):
         self.scale = dim_head ** -0.5
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
 
         self.use_ds_conv = use_ds_conv
 
@@ -148,16 +149,17 @@ class Attention(nn.Module):
         dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
         out = einsum('b i j, b j d -> b i d', attn, v)
         out = rearrange(out, '(b h) n d -> b n (h d)', h = h)
         return self.to_out(out)
 
 class Transformer(nn.Module):
-    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0., use_rotary = True, use_ds_conv = True, use_glu = True):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, image_size, dropout = 0., use_rotary = True, use_ds_conv = True, use_glu = True):
         super().__init__()
         self.layers = nn.ModuleList([])
-        self.pos_emb = AxialRotaryEmbedding(dim_head)
+        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)),
@@ -187,7 +189,7 @@ class RvT(nn.Module):
         )
 
         self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
-        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout, use_rotary, use_ds_conv, use_glu)
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, image_size, dropout, use_rotary, use_ds_conv, use_glu)
 
         self.mlp_head = nn.Sequential(
             nn.LayerNorm(dim),

vit_pytorch/scalable_vit.py

@@ -0,0 +1,306 @@
+from functools import partial
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val, d):
+    return val if exists(val) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+class ChanLayerNorm(nn.Module):
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
+
+class 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__()
+        self.conv = nn.Conv2d(dim_in, dim_out, 3, stride = 2, padding = 1)
+
+    def forward(self, x):
+        return self.conv(x)
+
+class PEG(nn.Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        self.proj = nn.Conv2d(dim, dim, kernel_size = kernel_size, padding = kernel_size // 2, groups = dim, stride = 1)
+
+    def forward(self, x):
+        return self.proj(x) + x
+
+# feedforward
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, expansion_factor = 4, dropout = 0.):
+        super().__init__()
+        inner_dim = dim * expansion_factor
+        self.net = nn.Sequential(
+            nn.Conv2d(dim, inner_dim, 1),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# attention
+
+class ScalableSelfAttention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        heads = 8,
+        dim_key = 32,
+        dim_value = 32,
+        dropout = 0.,
+        reduction_factor = 1
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_key ** -0.5
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_q = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
+        self.to_k = nn.Conv2d(dim, dim_key * heads, reduction_factor, stride = reduction_factor, bias = False)
+        self.to_v = nn.Conv2d(dim, dim_value * heads, reduction_factor, stride = reduction_factor, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(dim_value * heads, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        height, width, heads = *x.shape[-2:], self.heads
+
+        q, k, v = self.to_q(x), self.to_k(x), self.to_v(x)
+
+        # split out heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) ... -> b h (...) d', h = heads), (q, k, v))
+
+        # similarity
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        # attention
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        # aggregate values
+
+        out = torch.matmul(attn, v)
+
+        # merge back heads
+
+        out = rearrange(out, 'b h (x y) d -> b (h d) x y', x = height, y = width)
+        return self.to_out(out)
+
+class InteractiveWindowedSelfAttention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        window_size,
+        heads = 8,
+        dim_key = 32,
+        dim_value = 32,
+        dropout = 0.
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_key ** -0.5
+        self.window_size = window_size
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.local_interactive_module = nn.Conv2d(dim_value * heads, dim_value * heads, 3, padding = 1)
+
+        self.to_q = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
+        self.to_k = nn.Conv2d(dim, dim_key * heads, 1, bias = False)
+        self.to_v = nn.Conv2d(dim, dim_value * heads, 1, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(dim_value * heads, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        height, width, heads, wsz = *x.shape[-2:], self.heads, self.window_size
+
+        wsz_h, wsz_w = default(wsz, height), default(wsz, width)
+        assert (height % wsz_h) == 0 and (width % wsz_w) == 0, f'height ({height}) or width ({width}) of feature map is not divisible by the window size ({wsz_h}, {wsz_w})'
+
+        q, k, v = self.to_q(x), self.to_k(x), self.to_v(x)
+
+        # get output of LIM
+
+        local_out = self.local_interactive_module(v)
+
+        # divide into window (and split out heads) for efficient self attention
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) (x w1) (y w2) -> (b x y) h (w1 w2) d', h = heads, w1 = wsz_h, w2 = wsz_w), (q, k, v))
+
+        # similarity
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        # attention
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        # aggregate values
+
+        out = torch.matmul(attn, v)
+
+        # reshape the windows back to full feature map (and merge heads)
+
+        out = rearrange(out, '(b x y) h (w1 w2) d -> b (h d) (x w1) (y w2)', x = height // wsz_h, y = width // wsz_w, w1 = wsz_h, w2 = wsz_w)
+
+        # add LIM output 
+
+        out = out + local_out
+
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        depth,
+        heads = 8,
+        ff_expansion_factor = 4,
+        dropout = 0.,
+        ssa_dim_key = 32,
+        ssa_dim_value = 32,
+        ssa_reduction_factor = 1,
+        iwsa_dim_key = 32,
+        iwsa_dim_value = 32,
+        iwsa_window_size = None,
+        norm_output = True
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for ind in range(depth):
+            is_first = ind == 0
+
+            self.layers.append(nn.ModuleList([
+                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)),
+                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))
+            ]))
+
+        self.norm = ChanLayerNorm(dim) if norm_output else nn.Identity()
+
+    def forward(self, x):
+        for ssa, ff1, peg, iwsa, ff2 in self.layers:
+            x = ssa(x) + x
+            x = ff1(x) + x
+
+            if exists(peg):
+                x = peg(x)
+
+            x = iwsa(x) + x
+            x = ff2(x) + x
+
+        return self.norm(x)
+
+class ScalableViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        heads,
+        reduction_factor,
+        window_size = None,
+        iwsa_dim_key = 32,
+        iwsa_dim_value = 32,
+        ssa_dim_key = 32,
+        ssa_dim_value = 32,
+        ff_expansion_factor = 4,
+        channels = 3,
+        dropout = 0.
+    ):
+        super().__init__()
+        self.to_patches = nn.Conv2d(channels, dim, 7, stride = 4, padding = 3)
+
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+
+        num_stages = len(depth)
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+
+        hyperparams_per_stage = [
+            heads,
+            ssa_dim_key,
+            ssa_dim_value,
+            reduction_factor,
+            iwsa_dim_key,
+            iwsa_dim_value,
+            window_size,
+        ]
+
+        hyperparams_per_stage = list(map(partial(cast_tuple, length = num_stages), hyperparams_per_stage))
+        assert all(tuple(map(lambda arr: len(arr) == num_stages, hyperparams_per_stage)))
+
+        self.layers = nn.ModuleList([])
+
+        for ind, (layer_dim, layer_depth, layer_heads, layer_ssa_dim_key, layer_ssa_dim_value, layer_ssa_reduction_factor, layer_iwsa_dim_key, layer_iwsa_dim_value, layer_window_size) in enumerate(zip(dims, depth, *hyperparams_per_stage)):
+            is_last = ind == (num_stages - 1)
+
+            self.layers.append(nn.ModuleList([
+                Transformer(dim = layer_dim, depth = layer_depth, heads = layer_heads, ff_expansion_factor = ff_expansion_factor, dropout = dropout, ssa_dim_key = layer_ssa_dim_key, ssa_dim_value = layer_ssa_dim_value, ssa_reduction_factor = layer_ssa_reduction_factor, iwsa_dim_key = layer_iwsa_dim_key, iwsa_dim_value = layer_iwsa_dim_value, iwsa_window_size = layer_window_size, norm_output = not is_last),
+                Downsample(layer_dim, layer_dim * 2) if not is_last else None
+            ]))
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patches(img)
+
+        for transformer, downsample in self.layers:
+            x = transformer(x)
+
+            if exists(downsample):
+                x = downsample(x)
+
+        return self.mlp_head(x)

vit_pytorch/sep_vit.py

@@ -0,0 +1,294 @@
+from functools import partial
+
+import torch
+from torch import nn, einsum
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# helper classes
+
+class ChanLayerNorm(nn.Module):
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
+
+class 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__()
+        kernel_size = stride * 2 - 1
+        padding = kernel_size // 2
+        self.conv = nn.Conv2d(dim_in, dim_out, kernel_size, stride = stride, padding = padding)
+
+    def forward(self, x):
+        return self.conv(x)
+
+class PEG(nn.Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        self.proj = nn.Conv2d(dim, dim, kernel_size = kernel_size, padding = kernel_size // 2, groups = dim, stride = 1)
+
+    def forward(self, x):
+        return self.proj(x) + x
+
+# feedforward
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mult = 4, dropout = 0.):
+        super().__init__()
+        inner_dim = int(dim * mult)
+        self.net = nn.Sequential(
+            nn.Conv2d(dim, inner_dim, 1),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# attention
+
+class DSSA(nn.Module):
+    def __init__(
+        self,
+        dim,
+        heads = 8,
+        dim_head = 32,
+        dropout = 0.,
+        window_size = 7
+    ):
+        super().__init__()
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.window_size = window_size
+        inner_dim = dim_head * heads
+
+        self.attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_qkv = nn.Conv1d(dim, inner_dim * 3, 1, bias = False)
+
+        # window tokens
+
+        self.window_tokens = nn.Parameter(torch.randn(dim))
+
+        # prenorm and non-linearity for window tokens
+        # then projection to queries and keys for window tokens
+
+        self.window_tokens_to_qk = nn.Sequential(
+            nn.LayerNorm(dim_head),
+            nn.GELU(),
+            Rearrange('b h n c -> b (h c) n'),
+            nn.Conv1d(inner_dim, inner_dim * 2, 1),
+            Rearrange('b (h c) n -> b h n c', h = heads),
+        )
+
+        # window attention
+
+        self.window_attend = nn.Sequential(
+            nn.Softmax(dim = -1),
+            nn.Dropout(dropout)
+        )
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        """
+        einstein notation
+
+        b - batch
+        c - channels
+        w1 - window size (height)
+        w2 - also window size (width)
+        i - sequence dimension (source)
+        j - sequence dimension (target dimension to be reduced)
+        h - heads
+        x - height of feature map divided by window size
+        y - width of feature map divided by window size
+        """
+
+        batch, height, width, heads, wsz = x.shape[0], *x.shape[-2:], self.heads, self.window_size
+        assert (height % wsz) == 0 and (width % wsz) == 0, f'height {height} and width {width} must be divisible by window size {wsz}'
+        num_windows = (height // wsz) * (width // wsz)
+
+        # fold in windows for "depthwise" attention - not sure why it is named depthwise when it is just "windowed" attention
+
+        x = rearrange(x, 'b c (h w1) (w w2) -> (b h w) c (w1 w2)', w1 = wsz, w2 = wsz)
+
+        # add windowing tokens
+
+        w = repeat(self.window_tokens, 'c -> b c 1', b = x.shape[0])
+        x = torch.cat((w, x), dim = -1)
+
+        # project for queries, keys, value
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = 1)
+
+        # split out heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) ... -> b h (...) d', h = heads), (q, k, v))
+
+        # scale
+
+        q = q * self.scale
+
+        # similarity
+
+        dots = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # attention
+
+        attn = self.attend(dots)
+
+        # aggregate values
+
+        out = torch.matmul(attn, v)
+
+        # split out windowed tokens
+
+        window_tokens, windowed_fmaps = out[:, :, 0], out[:, :, 1:]
+
+        # early return if there is only 1 window
+
+        if num_windows == 1:
+            fmap = rearrange(windowed_fmaps, '(b x y) h (w1 w2) d -> b (h d) (x w1) (y w2)', x = height // wsz, y = width // wsz, w1 = wsz, w2 = wsz)
+            return self.to_out(fmap)
+
+        # carry out the pointwise attention, the main novelty in the paper
+
+        window_tokens = rearrange(window_tokens, '(b x y) h d -> b h (x y) d', x = height // wsz, y = width // wsz)
+        windowed_fmaps = rearrange(windowed_fmaps, '(b x y) h n d -> b h (x y) n d', x = height // wsz, y = width // wsz)
+
+        # windowed queries and keys (preceded by prenorm activation)
+
+        w_q, w_k = self.window_tokens_to_qk(window_tokens).chunk(2, dim = -1)
+
+        # scale
+
+        w_q = w_q * self.scale
+
+        # similarities
+
+        w_dots = einsum('b h i d, b h j d -> b h i j', w_q, w_k)
+
+        w_attn = self.window_attend(w_dots)
+
+        # aggregate the feature maps from the "depthwise" attention step (the most interesting part of the paper, one i haven't seen before)
+
+        aggregated_windowed_fmap = einsum('b h i j, b h j w d -> b h i w d', w_attn, windowed_fmaps)
+
+        # fold back the windows and then combine heads for aggregation
+
+        fmap = rearrange(aggregated_windowed_fmap, 'b h (x y) (w1 w2) d -> b (h d) (x w1) (y w2)', x = height // wsz, y = width // wsz, w1 = wsz, w2 = wsz)
+        return self.to_out(fmap)
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        depth,
+        dim_head = 32,
+        heads = 8,
+        ff_mult = 4,
+        dropout = 0.,
+        norm_output = True
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        for ind in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, DSSA(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mult = ff_mult, dropout = dropout)),
+            ]))
+
+        self.norm = ChanLayerNorm(dim) if norm_output else nn.Identity()
+
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+
+        return self.norm(x)
+
+class SepViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        dim,
+        depth,
+        heads,
+        window_size = 7,
+        dim_head = 32,
+        ff_mult = 4,
+        channels = 3,
+        dropout = 0.
+    ):
+        super().__init__()
+        assert isinstance(depth, tuple), 'depth needs to be tuple if integers indicating number of transformer blocks at that stage'
+
+        num_stages = len(depth)
+
+        dims = tuple(map(lambda i: (2 ** i) * dim, range(num_stages)))
+        dims = (channels, *dims)
+        dim_pairs = tuple(zip(dims[:-1], dims[1:]))
+
+        strides = (4, *((2,) * (num_stages - 1)))
+
+        hyperparams_per_stage = [heads, window_size]
+        hyperparams_per_stage = list(map(partial(cast_tuple, length = num_stages), hyperparams_per_stage))
+        assert all(tuple(map(lambda arr: len(arr) == num_stages, hyperparams_per_stage)))
+
+        self.layers = nn.ModuleList([])
+
+        for ind, ((layer_dim_in, layer_dim), layer_depth, layer_stride, layer_heads, layer_window_size) in enumerate(zip(dim_pairs, depth, strides, *hyperparams_per_stage)):
+            is_last = ind == (num_stages - 1)
+
+            self.layers.append(nn.ModuleList([
+                OverlappingPatchEmbed(layer_dim_in, layer_dim, stride = layer_stride),
+                PEG(layer_dim),
+                Transformer(dim = layer_dim, depth = layer_depth, heads = layer_heads, ff_mult = ff_mult, dropout = dropout, norm_output = not is_last),
+            ]))
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b d h w -> b d', 'mean'),
+            nn.LayerNorm(dims[-1]),
+            nn.Linear(dims[-1], num_classes)
+        )
+
+    def forward(self, x):
+
+        for ope, peg, transformer in self.layers:
+            x = ope(x)
+            x = peg(x)
+            x = transformer(x)
+
+        return self.mlp_head(x)

vit_pytorch/simmim.py

@@ -0,0 +1,87 @@
+import torch
+from torch import nn
+import torch.nn.functional as F
+from einops import repeat
+
+class SimMIM(nn.Module):
+    def __init__(
+        self,
+        *,
+        encoder,
+        masking_ratio = 0.5
+    ):
+        super().__init__()
+        assert masking_ratio > 0 and masking_ratio < 1, 'masking ratio must be kept between 0 and 1'
+        self.masking_ratio = masking_ratio
+
+        # extract some hyperparameters and functions from encoder (vision transformer to be trained)
+
+        self.encoder = encoder
+        num_patches, encoder_dim = encoder.pos_embedding.shape[-2:]
+
+        self.to_patch = encoder.to_patch_embedding[0]
+        self.patch_to_emb = nn.Sequential(*encoder.to_patch_embedding[1:])
+
+        pixel_values_per_patch = encoder.to_patch_embedding[2].weight.shape[-1]
+
+        # simple linear head
+
+        self.mask_token = nn.Parameter(torch.randn(encoder_dim))
+        self.to_pixels = nn.Linear(encoder_dim, pixel_values_per_patch)
+
+    def forward(self, img):
+        device = img.device
+
+        # get patches
+
+        patches = self.to_patch(img)
+        batch, num_patches, *_ = patches.shape
+
+        # for indexing purposes
+
+        batch_range = torch.arange(batch, device = device)[:, None]
+
+        # get positions
+
+        pos_emb = self.encoder.pos_embedding[:, 1:(num_patches + 1)]
+
+        # patch to encoder tokens and add positions
+
+        tokens = self.patch_to_emb(patches)
+        tokens = tokens + pos_emb
+
+        # prepare mask tokens
+
+        mask_tokens = repeat(self.mask_token, 'd -> b n d', b = batch, n = num_patches)
+        mask_tokens = mask_tokens + pos_emb
+
+        # calculate of patches needed to be masked, and get positions (indices) to be masked
+
+        num_masked = int(self.masking_ratio * num_patches)
+        masked_indices = torch.rand(batch, num_patches, device = device).topk(k = num_masked, dim = -1).indices
+        masked_bool_mask = torch.zeros((batch, num_patches), device = device).scatter_(-1, masked_indices, 1).bool()
+
+        # mask tokens
+
+        tokens = torch.where(masked_bool_mask[..., None], mask_tokens, tokens)
+
+        # attend with vision transformer
+
+        encoded = self.encoder.transformer(tokens)
+
+        # get the masked tokens
+
+        encoded_mask_tokens = encoded[batch_range, masked_indices]
+
+        # small linear projection for predicted pixel values
+
+        pred_pixel_values = self.to_pixels(encoded_mask_tokens)
+
+        # get the masked patches for the final reconstruction loss
+
+        masked_patches = patches[batch_range, masked_indices]
+
+        # calculate reconstruction loss
+
+        recon_loss = F.l1_loss(pred_pixel_values, masked_patches) / num_masked
+        return recon_loss

vit_pytorch/simple_flash_attn_vit.py

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

vit_pytorch/simple_vit.py

@@ -0,0 +1,118 @@
+import torch
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_2d(patches, temperature = 10000, dtype = torch.float32):
+    _, h, w, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    y, x = torch.meshgrid(torch.arange(h, device = device), torch.arange(w, device = device), indexing = 'ij')
+    assert (dim % 4) == 0, 'feature dimension must be multiple of 4 for sincos emb'
+    omega = torch.arange(dim // 4, device = device) / (dim // 4 - 1)
+    omega = 1. / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :] 
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim = 1)
+    return pe.type(dtype)
+
+# 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.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 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.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b h w (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        *_, h, w, dtype = *img.shape, img.dtype
+
+        x = self.to_patch_embedding(img)
+        pe = posemb_sincos_2d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/simple_vit_1d.py

@@ -0,0 +1,127 @@
+import torch
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def posemb_sincos_1d(patches, temperature = 10000, dtype = torch.float32):
+    _, n, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    n = torch.arange(n, device = device)
+    assert (dim % 2) == 0, 'feature dimension must be multiple of 2 for sincos emb'
+    omega = torch.arange(dim // 2, device = device) / (dim // 2 - 1)
+    omega = 1. / (temperature ** omega)
+
+    n = n.flatten()[:, None] * omega[None, :]
+    pe = torch.cat((n.sin(), n.cos()), dim = 1)
+    return pe.type(dtype)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.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 x
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, seq_len, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
+        super().__init__()
+
+        assert seq_len % patch_size == 0
+
+        num_patches = seq_len // patch_size
+        patch_dim = channels * patch_size
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (n p) -> b n (p c)', p = patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, series):
+        *_, n, dtype = *series.shape, series.dtype
+
+        x = self.to_patch_embedding(series)
+        pe = posemb_sincos_1d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)
+
+if __name__ == '__main__':
+
+    v = SimpleViT(
+        seq_len = 256,
+        patch_size = 16,
+        num_classes = 1000,
+        dim = 1024,
+        depth = 6,
+        heads = 8,
+        mlp_dim = 2048
+    )
+
+    time_series = torch.randn(4, 3, 256)
+    logits = v(time_series) # (4, 1000)

vit_pytorch/simple_vit_3d.py

@@ -0,0 +1,130 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_3d(patches, temperature = 10000, dtype = torch.float32):
+    _, f, h, w, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    z, y, x = torch.meshgrid(
+        torch.arange(f, device = device),
+        torch.arange(h, device = device),
+        torch.arange(w, device = device),
+    indexing = 'ij')
+
+    fourier_dim = dim // 6
+
+    omega = torch.arange(fourier_dim, device = device) / (fourier_dim - 1)
+    omega = 1. / (temperature ** omega)
+
+    z = z.flatten()[:, None] * omega[None, :]
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :] 
+
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos(), z.sin(), z.cos()), dim = 1)
+
+    pe = F.pad(pe, (0, dim - (fourier_dim * 6))) # pad if feature dimension not cleanly divisible by 6
+    return pe.type(dtype)
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.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 x
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(image_patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        assert frames % frame_patch_size == 0, 'Frames must be divisible by the frame patch size'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width) * (frames // frame_patch_size)
+        patch_dim = channels * patch_height * patch_width * frame_patch_size
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f h w (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, video):
+        *_, h, w, dtype = *video.shape, video.dtype
+
+        x = self.to_patch_embedding(video)
+        pe = posemb_sincos_3d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/simple_vit_with_patch_dropout.py

@@ -0,0 +1,143 @@
+import torch
+from torch import nn
+
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+def posemb_sincos_2d(patches, temperature = 10000, dtype = torch.float32):
+    _, h, w, dim, device, dtype = *patches.shape, patches.device, patches.dtype
+
+    y, x = torch.meshgrid(torch.arange(h, device = device), torch.arange(w, device = device), indexing = 'ij')
+    assert (dim % 4) == 0, 'feature dimension must be multiple of 4 for sincos emb'
+    omega = torch.arange(dim // 4, device = device) / (dim // 4 - 1)
+    omega = 1. / (temperature ** omega)
+
+    y = y.flatten()[:, None] * omega[None, :]
+    x = x.flatten()[:, None] * omega[None, :] 
+    pe = torch.cat((x.sin(), x.cos(), y.sin(), y.cos()), dim = 1)
+    return pe.type(dtype)
+
+# patch dropout
+
+class PatchDropout(nn.Module):
+    def __init__(self, prob):
+        super().__init__()
+        assert 0 <= prob < 1.
+        self.prob = prob
+
+    def forward(self, x):
+        if not self.training or self.prob == 0.:
+            return x
+
+        b, n, _, device = *x.shape, x.device
+
+        batch_indices = torch.arange(b, device = device)
+        batch_indices = rearrange(batch_indices, '... -> ... 1')
+        num_patches_keep = max(1, int(n * (1 - self.prob)))
+        patch_indices_keep = torch.randn(b, n, device = device).topk(num_patches_keep, dim = -1).indices
+
+        return x[batch_indices, patch_indices_keep]
+
+# classes
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Linear(hidden_dim, dim),
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        self.norm = nn.LayerNorm(dim)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+        self.to_out = nn.Linear(inner_dim, dim, bias = False)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim):
+        super().__init__()
+        self.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 x
+
+class SimpleViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, patch_dropout = 0.5):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b h w (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.patch_dropout = PatchDropout(patch_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim)
+
+        self.to_latent = nn.Identity()
+        self.linear_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        *_, h, w, dtype = *img.shape, img.dtype
+
+        x = self.to_patch_embedding(img)
+        pe = posemb_sincos_2d(x)
+        x = rearrange(x, 'b ... d -> b (...) d') + pe
+
+        x = self.patch_dropout(x)
+
+        x = self.transformer(x)
+        x = x.mean(dim = 1)
+
+        x = self.to_latent(x)
+        return self.linear_head(x)

vit_pytorch/twins_svt.py

@@ -38,9 +38,9 @@ class LayerNorm(nn.Module):
         self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
 
     def forward(self, x):
-        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (std + self.eps) * self.g + self.b
+        return (x - mean) / (var + self.eps).sqrt() * self.g + self.b
 
 class PreNorm(nn.Module):
     def __init__(self, dim, fn):
@@ -71,7 +71,12 @@ class PatchEmbedding(nn.Module):
         self.dim = dim
         self.dim_out = dim_out
         self.patch_size = patch_size
-        self.proj = nn.Conv2d(patch_size ** 2 * dim, dim_out, 1)
+
+        self.proj = nn.Sequential(
+            LayerNorm(patch_size ** 2 * dim),
+            nn.Conv2d(patch_size ** 2 * dim, dim_out, 1),
+            LayerNorm(dim_out)
+        )
 
     def forward(self, fmap):
         p = self.patch_size
@@ -130,6 +135,8 @@ class GlobalAttention(nn.Module):
         self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
         self.to_kv = nn.Conv2d(dim, inner_dim * 2, k, stride = k, bias = False)
 
+        self.dropout = nn.Dropout(dropout)
+
         self.to_out = nn.Sequential(
             nn.Conv2d(inner_dim, dim, 1),
             nn.Dropout(dropout)
@@ -145,6 +152,7 @@ class GlobalAttention(nn.Module):
         dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
 
         attn = dots.softmax(dim = -1)
+        attn = self.dropout(attn)
 
         out = einsum('b i j, b j d -> b i d', attn, v)
         out = rearrange(out, '(b h) (x y) d -> b (h d) x y', h = h, y = y)

vit_pytorch/vit.py

@@ -1,5 +1,5 @@
 import torch
-from torch import nn, einsum
+from torch import nn
 
 from einops import rearrange, repeat
 from einops.layers.torch import Rearrange
@@ -42,6 +42,8 @@ class Attention(nn.Module):
         self.scale = dim_head ** -0.5
 
         self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
         self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
 
         self.to_out = nn.Sequential(
@@ -50,15 +52,15 @@ class Attention(nn.Module):
         ) if project_out else nn.Identity()
 
     def forward(self, x):
-        b, n, _, h = *x.shape, self.heads
         qkv = self.to_qkv(x).chunk(3, dim = -1)
-        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
 
-        dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
 
         attn = self.attend(dots)
+        attn = self.dropout(attn)
 
-        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+        out = torch.matmul(attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
         return self.to_out(out)
 
@@ -91,7 +93,9 @@ class ViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
@@ -112,7 +116,7 @@ class ViT(nn.Module):
         x = self.to_patch_embedding(img)
         b, n, _ = x.shape
 
-        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        cls_tokens = repeat(self.cls_token, '1 1 d -> b 1 d', b = b)
         x = torch.cat((cls_tokens, x), dim=1)
         x += self.pos_embedding[:, :(n + 1)]
         x = self.dropout(x)

vit_pytorch/vit_1d.py

@@ -0,0 +1,135 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat, pack, unpack
+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.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, seq_len, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        assert (seq_len % patch_size) == 0
+
+        num_patches = seq_len // patch_size
+        patch_dim = channels * patch_size
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (n p) -> b n (p c)', p = patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, series):
+        x = self.to_patch_embedding(series)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, 'd -> b d', b = b)
+
+        x, ps = pack([cls_tokens, x], 'b * d')
+
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        cls_tokens, _ = unpack(x, ps, 'b * d')
+
+        return self.mlp_head(cls_tokens)
+
+if __name__ == '__main__':
+
+    v = ViT(
+        seq_len = 256,
+        patch_size = 16,
+        num_classes = 1000,
+        dim = 1024,
+        depth = 6,
+        heads = 8,
+        mlp_dim = 2048,
+        dropout = 0.1,
+        emb_dropout = 0.1
+    )
+
+    time_series = torch.randn(4, 3, 256)
+    logits = v(time_series) # (4, 1000)

vit_pytorch/vit_3d.py

@@ -0,0 +1,131 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(image_patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        assert frames % frame_patch_size == 0, 'Frames must be divisible by frame patch size'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width) * (frames // frame_patch_size)
+        patch_dim = channels * patch_height * patch_width * frame_patch_size
+
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (f pf) (h p1) (w p2) -> b (f h w) (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, video):
+        x = self.to_patch_embedding(video)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '1 1 d -> b 1 d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/vit_for_small_dataset.py

@@ -0,0 +1,145 @@
+from math import sqrt
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class LSA(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.temperature = nn.Parameter(torch.log(torch.tensor(dim_head ** -0.5)))
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.temperature.exp()
+
+        mask = torch.eye(dots.shape[-1], device = dots.device, dtype = torch.bool)
+        mask_value = -torch.finfo(dots.dtype).max
+        dots = dots.masked_fill(mask, mask_value)
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, LSA(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class SPT(nn.Module):
+    def __init__(self, *, dim, patch_size, channels = 3):
+        super().__init__()
+        patch_dim = patch_size * patch_size * 5 * channels
+
+        self.to_patch_tokens = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim)
+        )
+
+    def forward(self, x):
+        shifts = ((1, -1, 0, 0), (-1, 1, 0, 0), (0, 0, 1, -1), (0, 0, -1, 1))
+        shifted_x = list(map(lambda shift: F.pad(x, shift), shifts))
+        x_with_shifts = torch.cat((x, *shifted_x), dim = 1)
+        return self.to_patch_tokens(x_with_shifts)
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = SPT(dim = dim, patch_size = patch_size, channels = channels)
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/vit_with_patch_dropout.py

@@ -0,0 +1,152 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class PatchDropout(nn.Module):
+    def __init__(self, prob):
+        super().__init__()
+        assert 0 <= prob < 1.
+        self.prob = prob
+
+    def forward(self, x):
+        if not self.training or self.prob == 0.:
+            return x
+
+        b, n, _, device = *x.shape, x.device
+
+        batch_indices = torch.arange(b, device = device)
+        batch_indices = rearrange(batch_indices, '... -> ... 1')
+        num_patches_keep = max(1, int(n * (1 - self.prob)))
+        patch_indices_keep = torch.randn(b, n, device = device).topk(num_patches_keep, dim = -1).indices
+
+        return x[batch_indices, patch_indices_keep]
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., patch_dropout = 0.25):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(num_patches, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+
+        self.patch_dropout = PatchDropout(patch_dropout)
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        x += self.pos_embedding
+
+        x = self.patch_dropout(x)
+
+        cls_tokens = repeat(self.cls_token, '1 1 d -> b 1 d', b = b)
+
+        x = torch.cat((cls_tokens, x), dim=1)
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)

vit_pytorch/vit_with_patch_merger.py

@@ -0,0 +1,149 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange, Reduce
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def default(val ,d):
+    return val if exists(val) else d
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# patch merger class
+
+class PatchMerger(nn.Module):
+    def __init__(self, dim, num_tokens_out):
+        super().__init__()
+        self.scale = dim ** -0.5
+        self.norm = nn.LayerNorm(dim)
+        self.queries = nn.Parameter(torch.randn(num_tokens_out, dim))
+
+    def forward(self, x):
+        x = self.norm(x)
+        sim = torch.matmul(self.queries, x.transpose(-1, -2)) * self.scale
+        attn = sim.softmax(dim = -1)
+        return torch.matmul(attn, x)
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0., patch_merge_layer = None, patch_merge_num_tokens = 8):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        self.patch_merge_layer_index = default(patch_merge_layer, depth // 2) - 1 # default to mid-way through transformer, as shown in paper
+        self.patch_merger = PatchMerger(dim = dim, num_tokens_out = patch_merge_num_tokens)
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+    def forward(self, x):
+        for index, (attn, ff) in enumerate(self.layers):
+            x = attn(x) + x
+            x = ff(x) + x
+
+            if index == self.patch_merge_layer_index:
+                x = self.patch_merger(x)
+
+        return x
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, patch_merge_layer = None, patch_merge_num_tokens = 8, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout, patch_merge_layer, patch_merge_num_tokens)
+
+        self.mlp_head = nn.Sequential(
+            Reduce('b n d -> b d', 'mean'),
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        x += self.pos_embedding[:, :n]
+        x = self.dropout(x)
+
+        x = self.transformer(x)
+
+        return self.mlp_head(x)

vit_pytorch/vivit.py

@@ -0,0 +1,185 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat, reduce
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        image_patch_size,
+        frames,
+        frame_patch_size,
+        num_classes,
+        dim,
+        spatial_depth,
+        temporal_depth,
+        heads,
+        mlp_dim,
+        pool = 'cls',
+        channels = 3,
+        dim_head = 64,
+        dropout = 0.,
+        emb_dropout = 0.
+    ):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(image_patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        assert frames % frame_patch_size == 0, 'Frames must be divisible by frame patch size'
+
+        num_image_patches = (image_height // patch_height) * (image_width // patch_width)
+        num_frame_patches = (frames // frame_patch_size)
+
+        patch_dim = channels * patch_height * patch_width * frame_patch_size
+
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.global_average_pool = pool == 'mean'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f (h w) (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            nn.LayerNorm(patch_dim),
+            nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_frame_patches, num_image_patches, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.spatial_cls_token = nn.Parameter(torch.randn(1, 1, dim)) if not self.global_average_pool else None
+        self.temporal_cls_token = nn.Parameter(torch.randn(1, 1, dim)) if not self.global_average_pool else None
+
+        self.spatial_transformer = Transformer(dim, spatial_depth, heads, dim_head, mlp_dim, dropout)
+        self.temporal_transformer = Transformer(dim, temporal_depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, video):
+        x = self.to_patch_embedding(video)
+        b, f, n, _ = x.shape
+
+        x = x + self.pos_embedding
+
+        if exists(self.spatial_cls_token):
+            spatial_cls_tokens = repeat(self.spatial_cls_token, '1 1 d -> b f 1 d', b = b, f = f)
+            x = torch.cat((spatial_cls_tokens, x), dim = 2)
+
+        x = self.dropout(x)
+
+        x = rearrange(x, 'b f n d -> (b f) n d')
+
+        # attend across space
+
+        x = self.spatial_transformer(x)
+
+        x = rearrange(x, '(b f) n d -> b f n d', b = b)
+
+        # excise out the spatial cls tokens or average pool for temporal attention
+
+        x = x[:, :, 0] if not self.global_average_pool else reduce(x, 'b f n d -> b f d', 'mean')
+
+        # append temporal CLS tokens
+
+        if exists(self.temporal_cls_token):
+            temporal_cls_tokens = repeat(self.temporal_cls_token, '1 1 d-> b 1 d', b = b)
+
+            x = torch.cat((temporal_cls_tokens, x), dim = 1)
+
+        # attend across time
+
+        x = self.temporal_transformer(x)
+
+        # excise out temporal cls token or average pool
+
+        x = x[:, 0] if not self.global_average_pool else reduce(x, 'b f d -> b d', 'mean')
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)