remove patch size from T2TViT

README.md

@@ -117,6 +117,30 @@ v = v.to_vit()
 type(v) # <class 'vit_pytorch.vit_pytorch.ViT'>
 ```
 
+## Token-to-Token ViT
+
+<img src="./t2t.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2101.11986">This paper</a> proposes that the first couple layers should downsample the image sequence by unfolding, leading to overlapping image data in each token as shown in the figure above. You can use this variant of the `ViT` as follows.
+
+```python
+import torch
+from vit_pytorch.t2t import T2TViT
+
+v = T2TViT(
+    dim = 512,
+    image_size = 224,
+    depth = 5,
+    heads = 8,
+    mlp_dim = 512,
+    num_classes = 1000,
+    t2t_layers = ((7, 4), (3, 2), (3, 2)) # tuples of the kernel size and stride of each consecutive layers of the initial token to token module
+)
+
+img = torch.randn(1, 3, 224, 224)
+v(img) # (1, 1000)
+```
+
 ## Research Ideas
 
 ### Self Supervised Training
@@ -173,23 +197,22 @@ A pytorch-lightning script is ready for you to use at the repository link above.
 
 There may be some coming from computer vision who think attention still suffers from quadratic costs. Fortunately, we have a lot of new techniques that may help. This repository offers a way for you to plugin your own sparse attention transformer.
 
-An example with <a href="https://arxiv.org/abs/2006.04768">Linformer</a>
+An example with <a href="https://arxiv.org/abs/2102.03902">Nystromformer</a>
 
 ```bash
-$ pip install linformer
+$ pip install nystrom-attention
 ```
 
 ```python
 import torch
 from vit_pytorch.efficient import ViT
-from linformer import Linformer
+from nystrom_attention import Nystromformer
 
-efficient_transformer = Linformer(
+efficient_transformer = Nystromformer(
     dim = 512,
-    seq_len = 4096 + 1,  # 64 x 64 patches + 1 cls token
     depth = 12,
     heads = 8,
-    k = 256
+    num_landmarks = 256
 )
 
 v = ViT(
@@ -274,6 +297,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{yuan2021tokenstotoken,
+      title     = {Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet},
+      author    = {Li Yuan and Yunpeng Chen and Tao Wang and Weihao Yu and Yujun Shi and Francis EH Tay and Jiashi Feng and Shuicheng Yan},
+      year      = {2021},
+      eprint    = {2101.11986},
+      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 = '0.6.8',
+  version = '0.7.2',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',

vit_pytorch/distill.py

@@ -15,10 +15,8 @@ def exists(val):
 
 class DistillMixin:
     def forward(self, img, distill_token = None, mask = None):
-        p, distilling = self.patch_size, exists(distill_token)
-
-        x = rearrange(img, 'b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = p, p2 = p)
-        x = self.patch_to_embedding(x)
+        distilling = exists(distill_token)
+        x = self.to_patch_embedding(img)
         b, n, _ = x.shape
 
         cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)

vit_pytorch/efficient.py

@@ -1,6 +1,7 @@
 import torch
-from einops import rearrange, repeat
 from torch import nn
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
 
 class ViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, transformer, pool = 'cls', channels = 3):
@@ -10,10 +11,12 @@ class ViT(nn.Module):
         num_patches = (image_size // patch_size) ** 2
         patch_dim = channels * patch_size ** 2
 
-        self.patch_size = patch_size
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.Linear(patch_dim, dim),
+        )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
-        self.patch_to_embedding = nn.Linear(patch_dim, dim)
         self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
         self.transformer = transformer
 
@@ -26,10 +29,7 @@ class ViT(nn.Module):
         )
 
     def forward(self, img):
-        p = self.patch_size
-
-        x = rearrange(img, 'b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = p, p2 = p)
-        x = self.patch_to_embedding(x)
+        x = self.to_patch_embedding(img)
         b, n, _ = x.shape
 
         cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)

vit_pytorch/t2t.py

@@ -0,0 +1,74 @@
+import math
+import torch
+from torch import nn
+
+from vit_pytorch.vit_pytorch import Transformer
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# classes
+
+def conv_output_size(image_size, kernel_size, stride, padding):
+    return int(((image_size - kernel_size + (2 * padding)) / stride) + 1)
+
+class RearrangeImage(nn.Module):
+    def forward(self, x):
+        return rearrange(x, 'b (h w) c -> b c h w', h = int(math.sqrt(x.shape[1])))
+
+# main class
+
+class T2TViT(nn.Module):
+    def __init__(
+        self, *, image_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., t2t_layers = ((7, 4), (3, 2), (3, 2))):
+        super().__init__()
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        layers = []
+        layer_dim = channels
+        output_image_size = image_size
+
+        for i, (kernel_size, stride) in enumerate(t2t_layers):
+            layer_dim *= kernel_size ** 2
+            is_first = i == 0
+            output_image_size = conv_output_size(output_image_size, kernel_size, stride, stride // 2)
+
+            layers.extend([
+                RearrangeImage() if not is_first else nn.Identity(),
+                nn.Unfold(kernel_size = kernel_size, stride = stride, padding = stride // 2),
+                Rearrange('b c n -> b n c'),
+                Transformer(dim = layer_dim, heads = 1, depth = 1, dim_head = layer_dim, mlp_dim = layer_dim, dropout = dropout),
+            ])
+
+        layers.append(nn.Linear(layer_dim, dim))
+        self.to_patch_embedding = nn.Sequential(*layers)
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, output_image_size ** 2 + 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_pytorch.py

@@ -1,9 +1,10 @@
+import math
 import torch
+from torch import nn, einsum
 import torch.nn.functional as F
-from einops import rearrange, repeat
-from torch import nn
 
-MIN_NUM_PATCHES = 16
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
 
 class Residual(nn.Module):
     def __init__(self, fn):
@@ -51,7 +52,7 @@ class Attention(nn.Module):
         qkv = self.to_qkv(x).chunk(3, dim = -1)
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
 
-        dots = torch.einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+        dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
         mask_value = -torch.finfo(dots.dtype).max
 
         if mask is not None:
@@ -63,13 +64,13 @@ class Attention(nn.Module):
 
         attn = dots.softmax(dim=-1)
 
-        out = torch.einsum('b h i j, b h j d -> b h i d', attn, v)
+        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)')
         out =  self.to_out(out)
         return out
 
 class Transformer(nn.Module):
-    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
         super().__init__()
         self.layers = nn.ModuleList([])
         for _ in range(depth):
@@ -89,13 +90,14 @@ class ViT(nn.Module):
         assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
         num_patches = (image_size // patch_size) ** 2
         patch_dim = channels * patch_size ** 2
-        assert num_patches > MIN_NUM_PATCHES, f'your number of patches ({num_patches}) is way too small for attention to be effective (at least 16). Try decreasing your patch size'
         assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
 
-        self.patch_size = patch_size
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            nn.Linear(patch_dim, dim),
+        )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
-        self.patch_to_embedding = nn.Linear(patch_dim, dim)
         self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
         self.dropout = nn.Dropout(emb_dropout)
 
@@ -110,10 +112,7 @@ class ViT(nn.Module):
         )
 
     def forward(self, img, mask = None):
-        p = self.patch_size
-
-        x = rearrange(img, 'b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = p, p2 = p)
-        x = self.patch_to_embedding(x)
+        x = self.to_patch_embedding(img)
         b, n, _ = x.shape
 
         cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)