add ViT for small datasets https://arxiv.org/abs/2112.13492

Add MobileViT

.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 *

README.md

@@ -16,11 +16,14 @@
 - [LeViT](#levit)
 - [CvT](#cvt)
 - [Twins SVT](#twins-svt)
+- [CrossFormer](#crossformer)
 - [RegionViT](#regionvit)
 - [NesT](#nest)
+- [MobileViT](#mobilevit)
 - [Masked Autoencoder](#masked-autoencoder)
 - [Simple Masked Image Modeling](#simple-masked-image-modeling)
 - [Masked Patch Prediction](#masked-patch-prediction)
+- [Adaptive Token Sampling](#adaptive-token-sampling)
 - [Dino](#dino)
 - [Accessing Attention](#accessing-attention)
 - [Research Ideas](#research-ideas)
@@ -493,6 +496,33 @@ img = torch.randn(1, 3, 224, 224)
 pred = model(img) # (1, 1000)
 ```
 
+## CrossFormer
+
+<img src="./images/crossformer.png" width="400px"></img>
+
+<img src="./images/crossformer2.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2108.00154">paper</a> beats PVT and Swin using alternating local and global attention. The global attention is done across the windowing dimension for reduced complexity, much like the scheme used for axial attention.
+
+They also have cross-scale embedding layer, which they shown to be a generic layer that can improve all vision transformers. Dynamic relative positional bias was also formulated to allow the net to generalize to images of greater resolution.
+
+```python
+import torch
+from vit_pytorch.crossformer import CrossFormer
+
+model = CrossFormer(
+    num_classes = 1000,                # number of output classes
+    dim = (64, 128, 256, 512),         # dimension at each stage
+    depth = (2, 2, 8, 2),              # depth of transformer at each stage
+    global_window_size = (8, 4, 2, 1), # global window sizes at each stage
+    local_window_size = 7,             # local window size (can be customized for each stage, but in paper, held constant at 7 for all stages)
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = model(img) # (1, 1000)
+```
+
 ## NesT
 
 <img src="./images/nest.png" width="400px"></img>
@@ -520,6 +550,31 @@ img = torch.randn(1, 3, 224, 224)
 pred = nest(img) # (1, 1000)
 ```
 
+## MobileViT
+
+<img src="./images/mbvit.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2110.02178">paper</a> introduce MobileViT, a light-weight and general purpose vision transformer for mobile devices. MobileViT presents a different
+perspective for the global processing of information with transformers.
+
+You can use it with the following code (ex. mobilevit_xs)
+
+```python
+import torch
+from vit_pytorch.mobile_vit import MobileViT
+
+mbvit_xs = MobileViT(
+    image_size = (256, 256),
+    dims = [96, 120, 144],
+    channels = [16, 32, 48, 48, 64, 64, 80, 80, 96, 96, 384],
+    num_classes = 1000
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+pred = mbvit_xs(img) # (1, 1000)
+```
+
 ## Simple Masked Image Modeling
 
 <img src="./images/simmim.png" width="400px"/>
@@ -568,6 +623,8 @@ A new <a href="https://arxiv.org/abs/2111.06377">Kaiming He paper</a> proposes a
 
 <a href="https://www.youtube.com/watch?v=LKixq2S2Pz8">DeepReader quick paper review</a>
 
+<a href="https://www.youtube.com/watch?v=Dp6iICL2dVI">AI Coffeebreak with Letitia</a>
+
 You can use it with the following code
 
 ```python
@@ -649,6 +706,85 @@ for _ in range(100):
 torch.save(model.state_dict(), './pretrained-net.pt')
 ```
 
+## Adaptive Token Sampling
+
+<img src="./images/ats.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2111.15667">paper</a> proposes to use the CLS attention scores, re-weighed by the norms of the value heads, as means to discard unimportant tokens at different layers.
+
+```python
+import torch
+from vit_pytorch.ats_vit import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 16,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    max_tokens_per_depth = (256, 128, 64, 32, 16, 8), # a tuple that denotes the maximum number of tokens that any given layer should have. if the layer has greater than this amount, it will undergo adaptive token sampling
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(4, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+
+# you can also get a list of the final sampled patch ids
+# a value of -1 denotes padding
+
+preds, token_ids = v(img, return_sampled_token_ids = True) # (1, 1000), (1, <=8)
+```
+
+## Vision Transformer for Small Datasets
+
+<img src="./images/vit_for_small_datasets.png" width="400px"></img>
+
+This paper proposes a new image to patch function that incorporates shifts of the image, before normalizing and dividing the image into patches. I have found shifting to be extremely helpful in some other transformers work, so decided to include this for further explorations. It also includes the `LRA` with the learned temperature and masking out of token attention to itself.
+
+You can use as follows:
+
+```python
+import torch
+from vit_pytorch.vit_for_small_dataset import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 16,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(4, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+```
+
+You can also use the `SPT` from this paper as a standalone module
+
+```python
+import torch
+from vit_pytorch.vit_for_small_dataset import SPT
+
+spt = SPT(
+    dim = 1024,
+    patch_size = 16,
+    channels = 3
+)
+
+img = torch.randn(4, 3, 256, 256)
+
+tokens = spt(img) # (4, 256, 1024)
+```
+
 ## Dino
 
 <img src="./images/dino.png" width="350px"></img>
@@ -744,6 +880,41 @@ to cleanup the class and the hooks once you have collected enough data
 v = v.eject()  # wrapper is discarded and original ViT instance is returned
 ```
 
+## Accessing Embeddings
+
+You can similarly access the embeddings with the `Extractor` wrapper
+
+```python
+import torch
+from vit_pytorch.vit import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+# import Recorder and wrap the ViT
+
+from vit_pytorch.extractor import Extractor
+v = Extractor(v)
+
+# forward pass now returns predictions and the attention maps
+
+img = torch.randn(1, 3, 256, 256)
+logits, embeddings = v(img)
+
+# there is one extra token due to the CLS token
+
+embeddings # (1, 65, 1024) - (batch x patches x model dim)
+```
+
 ## Research Ideas
 
 ### Efficient Attention
@@ -1045,6 +1216,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{wang2021crossformer,
+    title   = {CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention}, 
+    author  = {Wenxiao Wang and Lu Yao and Long Chen and Binbin Lin and Deng Cai and Xiaofei He and Wei Liu},
+    year    = {2021},
+    eprint  = {2108.00154},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{caron2021emerging,
     title   = {Emerging Properties in Self-Supervised Vision Transformers},
@@ -1078,6 +1260,39 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{fayyaz2021ats,
+    title   = {ATS: Adaptive Token Sampling For Efficient Vision Transformers},
+    author  = {Mohsen Fayyaz and Soroush Abbasi Kouhpayegani and Farnoush Rezaei Jafari and Eric Sommerlade and Hamid Reza Vaezi Joze and Hamed Pirsiavash and Juergen Gall},
+    year    = {2021},
+    eprint  = {2111.15667},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{mehta2021mobilevit,
+    title   = {MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer},
+    author  = {Sachin Mehta and Mohammad Rastegari},
+    year    = {2021},
+    eprint  = {2110.02178},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{lee2021vision,
+    title   = {Vision Transformer for Small-Size Datasets}, 
+    author  = {Seung Hoon Lee and Seunghyun Lee and Byung Cheol Song},
+    year    = {2021},
+    eprint  = {2112.13492},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{vaswani2017attention,
     title   = {Attention Is All You Need},

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.23.2',
+  version = '0.26.0',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',
@@ -19,6 +19,12 @@ setup(
     'torch>=1.6',
     'torchvision'
   ],
+  setup_requires=[
+    'pytest-runner',
+  ],
+  tests_require=[
+    'pytest'
+  ],
   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/ats_vit.py

@@ -0,0 +1,262 @@
+import torch
+import torch.nn.functional as F
+from torch.nn.utils.rnn import pad_sequence
+from torch import nn, einsum
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# adaptive token sampling functions and classes
+
+def log(t, eps = 1e-6):
+    return torch.log(t + eps)
+
+def sample_gumbel(shape, device, dtype, eps = 1e-6):
+    u = torch.empty(shape, device = device, dtype = dtype).uniform_(0, 1)
+    return -log(-log(u, eps), eps)
+
+def batched_index_select(values, indices, dim = 1):
+    value_dims = values.shape[(dim + 1):]
+    values_shape, indices_shape = map(lambda t: list(t.shape), (values, indices))
+    indices = indices[(..., *((None,) * len(value_dims)))]
+    indices = indices.expand(*((-1,) * len(indices_shape)), *value_dims)
+    value_expand_len = len(indices_shape) - (dim + 1)
+    values = values[(*((slice(None),) * dim), *((None,) * value_expand_len), ...)]
+
+    value_expand_shape = [-1] * len(values.shape)
+    expand_slice = slice(dim, (dim + value_expand_len))
+    value_expand_shape[expand_slice] = indices.shape[expand_slice]
+    values = values.expand(*value_expand_shape)
+
+    dim += value_expand_len
+    return values.gather(dim, indices)
+
+class AdaptiveTokenSampling(nn.Module):
+    def __init__(self, output_num_tokens, eps = 1e-6):
+        super().__init__()
+        self.eps = eps
+        self.output_num_tokens = output_num_tokens
+
+    def forward(self, attn, value, mask):
+        heads, output_num_tokens, eps, device, dtype = attn.shape[1], self.output_num_tokens, self.eps, attn.device, attn.dtype
+
+        # first get the attention values for CLS token to all other tokens
+
+        cls_attn = attn[..., 0, 1:]
+
+        # calculate the norms of the values, for weighting the scores, as described in the paper
+
+        value_norms = value[..., 1:, :].norm(dim = -1)
+
+        # weigh the attention scores by the norm of the values, sum across all heads
+
+        cls_attn = einsum('b h n, b h n -> b n', cls_attn, value_norms)
+
+        # normalize to 1
+
+        normed_cls_attn = cls_attn / (cls_attn.sum(dim = -1, keepdim = True) + eps)
+
+        # instead of using inverse transform sampling, going to invert the softmax and use gumbel-max sampling instead
+
+        pseudo_logits = log(normed_cls_attn)
+
+        # mask out pseudo logits for gumbel-max sampling
+
+        mask_without_cls = mask[:, 1:]
+        mask_value = -torch.finfo(attn.dtype).max / 2
+        pseudo_logits = pseudo_logits.masked_fill(~mask_without_cls, mask_value)
+
+        # expand k times, k being the adaptive sampling number
+
+        pseudo_logits = repeat(pseudo_logits, 'b n -> b k n', k = output_num_tokens)
+        pseudo_logits = pseudo_logits + sample_gumbel(pseudo_logits.shape, device = device, dtype = dtype)
+
+        # gumble-max and add one to reserve 0 for padding / mask
+
+        sampled_token_ids = pseudo_logits.argmax(dim = -1) + 1
+
+        # calculate unique using torch.unique and then pad the sequence from the right
+
+        unique_sampled_token_ids_list = [torch.unique(t, sorted = True) for t in torch.unbind(sampled_token_ids)]
+        unique_sampled_token_ids = pad_sequence(unique_sampled_token_ids_list, batch_first = True)
+
+        # calculate the new mask, based on the padding
+
+        new_mask = unique_sampled_token_ids != 0
+
+        # CLS token never gets masked out (gets a value of True)
+
+        new_mask = F.pad(new_mask, (1, 0), value = True)
+
+        # prepend a 0 token id to keep the CLS attention scores
+
+        unique_sampled_token_ids = F.pad(unique_sampled_token_ids, (1, 0), value = 0)
+        expanded_unique_sampled_token_ids = repeat(unique_sampled_token_ids, 'b n -> b h n', h = heads)
+
+        # gather the new attention scores
+
+        new_attn = batched_index_select(attn, expanded_unique_sampled_token_ids, dim = 2)
+
+        # return the sampled attention scores, new mask (denoting padding), as well as the sampled token indices (for the residual)
+        return new_attn, new_mask, unique_sampled_token_ids
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0., output_num_tokens = None):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.output_num_tokens = output_num_tokens
+        self.ats = AdaptiveTokenSampling(output_num_tokens) if exists(output_num_tokens) else None
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, *, mask):
+        num_tokens = x.shape[1]
+
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        if exists(mask):
+            dots_mask = rearrange(mask, 'b i -> b 1 i 1') * rearrange(mask, 'b j -> b 1 1 j')
+            mask_value = -torch.finfo(dots.dtype).max
+            dots = dots.masked_fill(~dots_mask, mask_value)
+
+        attn = self.attend(dots)
+
+        sampled_token_ids = None
+
+        # if adaptive token sampling is enabled
+        # and number of tokens is greater than the number of output tokens
+        if exists(self.output_num_tokens) and (num_tokens - 1) > self.output_num_tokens:
+            attn, mask, sampled_token_ids = self.ats(attn, v, mask = mask)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+
+        return self.to_out(out), mask, sampled_token_ids
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, max_tokens_per_depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        assert len(max_tokens_per_depth) == depth, 'max_tokens_per_depth must be a tuple of length that is equal to the depth of the transformer'
+        assert sorted(max_tokens_per_depth, reverse = True) == list(max_tokens_per_depth), 'max_tokens_per_depth must be in decreasing order'
+        assert min(max_tokens_per_depth) > 0, 'max_tokens_per_depth must have at least 1 token at any layer'
+
+        self.layers = nn.ModuleList([])
+        for _, output_num_tokens in zip(range(depth), max_tokens_per_depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, output_num_tokens = output_num_tokens, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+
+    def forward(self, x):
+        b, n, device = *x.shape[:2], x.device
+
+        # use mask to keep track of the paddings when sampling tokens
+        # as the duplicates (when sampling) are just removed, as mentioned in the paper
+        mask = torch.ones((b, n), device = device, dtype = torch.bool)
+
+        token_ids = torch.arange(n, device = device)
+        token_ids = repeat(token_ids, 'n -> b n', b = b)
+
+        for attn, ff in self.layers:
+            attn_out, mask, sampled_token_ids = attn(x, mask = mask)
+
+            # when token sampling, one needs to then gather the residual tokens with the sampled token ids
+            if exists(sampled_token_ids):
+                x = batched_index_select(x, sampled_token_ids, dim = 1)
+                token_ids = batched_index_select(token_ids, sampled_token_ids, dim = 1)
+
+            x = x + attn_out
+
+            x = ff(x) + x
+
+        return x, token_ids
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, max_tokens_per_depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, max_tokens_per_depth, heads, dim_head, mlp_dim, dropout)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img, return_sampled_token_ids = False):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x, token_ids = self.transformer(x)
+
+        logits = self.mlp_head(x[:, 0])
+
+        if return_sampled_token_ids:
+            # remove CLS token and decrement by 1 to make -1 the padding
+            token_ids = token_ids[:, 1:] - 1
+            return logits, token_ids
+
+        return logits

vit_pytorch/crossformer.py

@@ -0,0 +1,263 @@
+import torch
+from torch import nn, einsum
+from einops import rearrange
+from einops.layers.torch import Rearrange, Reduce
+import torch.nn.functional as F
+
+# helpers
+
+def cast_tuple(val, length = 1):
+    return val if isinstance(val, tuple) else ((val,) * length)
+
+# cross embed layer
+
+class CrossEmbedLayer(nn.Module):
+    def __init__(
+        self,
+        dim_in,
+        dim_out,
+        kernel_sizes,
+        stride = 2
+    ):
+        super().__init__()
+        kernel_sizes = sorted(kernel_sizes)
+        num_scales = len(kernel_sizes)
+
+        # calculate the dimension at each scale
+        dim_scales = [int(dim_out / (2 ** i)) for i in range(1, num_scales)]
+        dim_scales = [*dim_scales, dim_out - sum(dim_scales)]
+
+        self.convs = nn.ModuleList([])
+        for kernel, dim_scale in zip(kernel_sizes, dim_scales):
+            self.convs.append(nn.Conv2d(dim_in, dim_scale, kernel, stride = stride, padding = (kernel - stride) // 2))
+
+    def forward(self, x):
+        fmaps = tuple(map(lambda conv: conv(x), self.convs))
+        return torch.cat(fmaps, dim = 1)
+
+# dynamic positional bias
+
+def DynamicPositionBias(dim):
+    return nn.Sequential(
+        nn.Linear(2, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, dim),
+        nn.LayerNorm(dim),
+        nn.ReLU(),
+        nn.Linear(dim, 1),
+        Rearrange('... () -> ...')
+    )
+
+# transformer classes
+
+class LayerNorm(nn.Module):
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (std + self.eps) * self.g + self.b
+
+def FeedForward(dim, mult = 4, dropout = 0.):
+    return nn.Sequential(
+        LayerNorm(dim),
+        nn.Conv2d(dim, dim * mult, 1),
+        nn.GELU(),
+        nn.Dropout(dropout),
+        nn.Conv2d(dim * mult, dim, 1)
+    )
+
+class Attention(nn.Module):
+    def __init__(
+        self,
+        dim,
+        attn_type,
+        window_size,
+        dim_head = 32,
+        dropout = 0.
+    ):
+        super().__init__()
+        assert attn_type in {'short', 'long'}, 'attention type must be one of local or distant'
+        heads = dim // dim_head
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+        inner_dim = dim_head * heads
+
+        self.attn_type = attn_type
+        self.window_size = window_size
+
+        self.norm = LayerNorm(dim)
+        self.to_qkv = nn.Conv2d(dim, inner_dim * 3, 1, bias = False)
+        self.to_out = nn.Conv2d(inner_dim, dim, 1)
+
+        # positions
+
+        self.dpb = DynamicPositionBias(dim // 4)
+
+        # calculate and store indices for retrieving bias
+
+        pos = torch.arange(window_size)
+        grid = torch.stack(torch.meshgrid(pos, pos))
+        grid = rearrange(grid, 'c i j -> (i j) c')
+        rel_pos = grid[:, None] - grid[None, :]
+        rel_pos += window_size - 1
+        rel_pos_indices = (rel_pos * torch.tensor([2 * window_size - 1, 1])).sum(dim = -1)
+
+        self.register_buffer('rel_pos_indices', rel_pos_indices, persistent = False)
+
+    def forward(self, x):
+        *_, height, width, heads, wsz, device = *x.shape, self.heads, self.window_size, x.device
+
+        # prenorm
+
+        x = self.norm(x)
+
+        # rearrange for short or long distance attention
+
+        if self.attn_type == 'short':
+            x = rearrange(x, 'b d (h s1) (w s2) -> (b h w) d s1 s2', s1 = wsz, s2 = wsz)
+        elif self.attn_type == 'long':
+            x = rearrange(x, 'b d (l1 h) (l2 w) -> (b h w) d l1 l2', l1 = wsz, l2 = wsz)
+
+        # queries / keys / values
+
+        q, k, v = self.to_qkv(x).chunk(3, dim = 1)
+
+        # split heads
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) x y -> b h (x y) d', h = heads), (q, k, v))
+        q = q * self.scale
+
+        sim = einsum('b h i d, b h j d -> b h i j', q, k)
+
+        # add dynamic positional bias
+
+        pos = torch.arange(-wsz, wsz + 1, device = device)
+        rel_pos = torch.stack(torch.meshgrid(pos, pos))
+        rel_pos = rearrange(rel_pos, 'c i j -> (i j) c')
+        biases = self.dpb(rel_pos.float())
+        rel_pos_bias = biases[self.rel_pos_indices]
+
+        sim = sim + rel_pos_bias
+
+        # attend
+
+        attn = sim.softmax(dim = -1)
+
+        # merge heads
+
+        out = einsum('b h i j, b h j d -> b h i d', attn, v)
+        out = rearrange(out, 'b h (x y) d -> b (h d) x y', x = wsz, y = wsz)
+        out = self.to_out(out)
+
+        # rearrange back for long or short distance attention
+
+        if self.attn_type == 'short':
+            out = rearrange(out, '(b h w) d s1 s2 -> b d (h s1) (w s2)', h = height // wsz, w = width // wsz)
+        elif self.attn_type == 'long':
+            out = rearrange(out, '(b h w) d l1 l2 -> b d (l1 h) (l2 w)', h = height // wsz, w = width // wsz)
+
+        return out
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        dim,
+        *,
+        local_window_size,
+        global_window_size,
+        depth = 4,
+        dim_head = 32,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+    ):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Attention(dim, attn_type = 'short', window_size = local_window_size, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout),
+                Attention(dim, attn_type = 'long', window_size = global_window_size, dim_head = dim_head, dropout = attn_dropout),
+                FeedForward(dim, dropout = ff_dropout)
+            ]))
+
+    def forward(self, x):
+        for short_attn, short_ff, long_attn, long_ff in self.layers:
+            x = short_attn(x) + x
+            x = short_ff(x) + x
+            x = long_attn(x) + x
+            x = long_ff(x) + x
+
+        return x
+
+# classes
+
+class CrossFormer(nn.Module):
+    def __init__(
+        self,
+        *,
+        dim = (64, 128, 256, 512),
+        depth = (2, 2, 8, 2),
+        global_window_size = (8, 4, 2, 1),
+        local_window_size = 7,
+        cross_embed_kernel_sizes = ((4, 8, 16, 32), (2, 4), (2, 4), (2, 4)),
+        cross_embed_strides = (4, 2, 2, 2),
+        num_classes = 1000,
+        attn_dropout = 0.,
+        ff_dropout = 0.,
+        channels = 3
+    ):
+        super().__init__()
+
+        dim = cast_tuple(dim, 4)
+        depth = cast_tuple(depth, 4)
+        global_window_size = cast_tuple(global_window_size, 4)
+        local_window_size = cast_tuple(local_window_size, 4)
+        cross_embed_kernel_sizes = cast_tuple(cross_embed_kernel_sizes, 4)
+        cross_embed_strides = cast_tuple(cross_embed_strides, 4)
+
+        assert len(dim) == 4
+        assert len(depth) == 4
+        assert len(global_window_size) == 4
+        assert len(local_window_size) == 4
+        assert len(cross_embed_kernel_sizes) == 4
+        assert len(cross_embed_strides) == 4
+
+        # dimensions
+
+        last_dim = dim[-1]
+        dims = [channels, *dim]
+        dim_in_and_out = tuple(zip(dims[:-1], dims[1:]))
+
+        # layers
+
+        self.layers = nn.ModuleList([])
+
+        for (dim_in, dim_out), layers, global_wsz, local_wsz, cel_kernel_sizes, cel_stride in zip(dim_in_and_out, depth, global_window_size, local_window_size, cross_embed_kernel_sizes, cross_embed_strides):
+            self.layers.append(nn.ModuleList([
+                CrossEmbedLayer(dim_in, dim_out, cel_kernel_sizes, stride = cel_stride),
+                Transformer(dim_out, local_window_size = local_wsz, global_window_size = global_wsz, depth = layers, attn_dropout = attn_dropout, ff_dropout = ff_dropout)
+            ]))
+
+        # final logits
+
+        self.to_logits = nn.Sequential(
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(last_dim, num_classes)
+        )
+
+    def forward(self, x):
+        for cel, transformer in self.layers:
+            x = cel(x)
+            x = transformer(x)
+
+        return self.to_logits(x)

vit_pytorch/extractor.py

@@ -0,0 +1,70 @@
+import torch
+from torch import nn
+
+def exists(val):
+    return val is not None
+
+class Extractor(nn.Module):
+    def __init__(
+        self,
+        vit,
+        device = None,
+        layer_name = 'transformer',
+        layer_save_input = False,
+        return_embeddings_only = False
+    ):
+        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_name = layer_name
+        self.layer_save_input = layer_save_input # whether to save input or output of layer
+        self.return_embeddings_only = return_embeddings_only
+
+    def _hook(self, _, inputs, output):
+        tensor_to_save = inputs if self.layer_save_input else output
+        self.latents = tensor_to_save.clone().detach()
+
+    def _register_hook(self):
+        assert hasattr(self.vit, self.layer_name), 'layer whose output to take as embedding not found in vision transformer'
+        layer = getattr(self.vit, self.layer_name)
+        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 = self.latents.to(target_device)
+
+        if return_embeddings_only or self.return_embeddings_only:
+            return latents
+
+        return pred, latents

vit_pytorch/mae.py

@@ -78,12 +78,12 @@ class MAE(nn.Module):
 
         # concat the masked tokens to the decoder tokens and attend with decoder
 
-        decoder_tokens = torch.cat((decoder_tokens, mask_tokens), dim = 1)
+        decoder_tokens = torch.cat((mask_tokens, decoder_tokens), dim = 1)
         decoded_tokens = self.decoder(decoder_tokens)
 
         # splice out the mask tokens and project to pixel values
 
-        mask_tokens = decoded_tokens[:, -num_masked:]
+        mask_tokens = decoded_tokens[:, :num_masked]
         pred_pixel_values = self.to_pixels(mask_tokens)
 
         # calculate reconstruction loss

vit_pytorch/mobile_vit.py

@@ -0,0 +1,239 @@
+"""
+An implementation of MobileViT Model as defined in:
+MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
+Arxiv: https://arxiv.org/abs/2110.02178
+Origin Code: https://github.com/murufeng/awesome_lightweight_networks
+"""
+
+import torch
+import torch.nn as nn
+
+from einops import rearrange
+from einops.layers.torch import Reduce
+
+def _make_divisible(v, divisor, min_value=None):
+    if min_value is None:
+        min_value = divisor
+    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
+    if new_v < 0.9 * v:
+        new_v += divisor
+    return new_v
+
+
+def conv_bn_relu(inp, oup, kernel, stride=1):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, kernel_size=kernel, stride=stride, padding=1, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.ReLU6(inplace=True)
+    )
+
+
+def conv_1x1_bn(inp, oup):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.ReLU6(inplace=True)
+    )
+
+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.ffn = 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.ffn(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.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)
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b p h n d -> b p n (h d)')
+        return self.to_out(out)
+
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        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 MV2Block(nn.Module):
+    def __init__(self, inp, oup, stride=1, expand_ratio=4):
+        super(MV2Block, self).__init__()
+        assert stride in [1, 2]
+
+        hidden_dim = round(inp * expand_ratio)
+        self.identity = stride == 1 and inp == oup
+
+        if expand_ratio == 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.identity:
+            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_bn_relu(channel, channel, kernel_size)
+        self.conv2 = conv_1x1_bn(channel, dim)
+
+        self.transformer = Transformer(dim, depth, 1, 32, mlp_dim, dropout)
+
+        self.conv3 = conv_1x1_bn(dim, channel)
+        self.conv4 = conv_bn_relu(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):
+    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_bn_relu(3, init_dim, kernel=3, 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/pit.py

@@ -129,14 +129,15 @@ class PiT(nn.Module):
         mlp_dim,
         dim_head = 64,
         dropout = 0.,
-        emb_dropout = 0.
+        emb_dropout = 0.,
+        channels = 3
     ):
         super().__init__()
         assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
         assert isinstance(depth, tuple), 'depth must be a tuple of integers, specifying the number of blocks before each downsizing'
         heads = cast_tuple(heads, len(depth))
 
-        patch_dim = 3 * patch_size ** 2
+        patch_dim = channels * patch_size ** 2
 
         self.to_patch_embedding = nn.Sequential(
             nn.Unfold(kernel_size = patch_size, stride = patch_size // 2),

vit_pytorch/regionvit.py

@@ -247,11 +247,7 @@ class RegionViT(nn.Module):
             nn.Linear(last_dim, num_classes)
         )
 
-    def forward(
-        self,
-        x,
-        return_local_tokens = False
-    ):
+    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'

vit_pytorch/vit_for_small_dataset.py

@@ -0,0 +1,142 @@
+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.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)
+
+        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)