remove float(-inf) as masking value

Image Classification Example

README.md

@@ -1,6 +1,10 @@
+<img src="./vit.png" width="500px"></img>
+
 ## Vision Transformer - Pytorch
 
-Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch. There's really not much to code here, but may as well lay out all the code so we expedite the attention revolution and get everyone on the same page.
+Implementation of <a href="https://openreview.net/pdf?id=YicbFdNTTy">Vision Transformer</a>, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch. Significance is further explained in <a href="https://www.youtube.com/watch?v=TrdevFK_am4">Yannic Kilcher's</a> video. There's really not much to code here, but may as well lay it out for everyone so we expedite the attention revolution.
+
+For a Pytorch implementation with pretrained models, please see Ross Wightman's repository <a href="https://github.com/rwightman/pytorch-image-models">here</a>
 
 ## Install
 
@@ -21,23 +25,126 @@ v = ViT(
     dim = 1024,
     depth = 6,
     heads = 8,
-    mlp_dim = 2048
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
 )
 
 img = torch.randn(1, 3, 256, 256)
-preds = v(img) # (1, 1000)
+mask = torch.ones(1, 8, 8).bool() # optional mask, designating which patch to attend to
+
+preds = v(img, mask = mask) # (1, 1000)
 ```
 
+## Research Ideas
+
+### Self Supervised Training
+
+You can train this with a near SOTA self-supervised learning technique, <a href="https://github.com/lucidrains/byol-pytorch">BYOL</a>, with the following code.
+
+(1)
+```bash
+$ pip install byol-pytorch
+```
+
+(2)
+```python
+import torch
+from vit_pytorch import ViT
+from byol_pytorch import BYOL
+
+model = ViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 8,
+    mlp_dim = 2048
+)
+
+learner = BYOL(
+    model,
+    image_size = 256,
+    hidden_layer = 'to_cls_token'
+)
+
+opt = torch.optim.Adam(learner.parameters(), lr=3e-4)
+
+def sample_unlabelled_images():
+    return torch.randn(20, 3, 256, 256)
+
+for _ in range(100):
+    images = sample_unlabelled_images()
+    loss = learner(images)
+    opt.zero_grad()
+    loss.backward()
+    opt.step()
+    learner.update_moving_average() # update moving average of target encoder
+
+# save your improved network
+torch.save(model.state_dict(), './pretrained-net.pt')
+```
+
+A pytorch-lightning script is ready for you to use at the repository link above.
+
+### Efficient Attention
+
+There may be some coming from computer vision who think attention still suffers from quadratic costs. Fortunately, we have a lot of new techniques that may help. This repository offers a way for you to plugin your own sparse attention transformer.
+
+An example with <a href="https://arxiv.org/abs/2006.04768">Linformer</a>
+
+```bash
+$ pip install linformer
+```
+
+```python
+import torch
+from vit_pytorch.efficient import ViT
+from linformer import Linformer
+
+efficient_transformer = Linformer(
+    dim = 512,
+    seq_len = 4096 + 1,  # 64 x 64 patches + 1 cls token
+    depth = 12,
+    heads = 8,
+    k = 256
+)
+
+v = ViT(
+    dim = 512,
+    image_size = 2048,
+    patch_size = 32,
+    num_classes = 1000,
+    transformer = efficient_transformer
+)
+
+img = torch.randn(1, 3, 2048, 2048) # your high resolution picture
+v(img) # (1, 1000)
+```
+
+Other sparse attention frameworks I would highly recommend is <a href="https://github.com/lucidrains/routing-transformer">Routing Transformer</a> or <a href="https://github.com/lucidrains/sinkhorn-transformer">Sinkhorn Transformer</a>
+
 ## Citations
 
 ```bibtex
-@inproceedings{
-    anonymous2021an,
-    title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
-    author={Anonymous},
-    booktitle={Submitted to International Conference on Learning Representations},
-    year={2021},
-    url={https://openreview.net/forum?id=YicbFdNTTy},
-    note={under review}
+@misc{dosovitskiy2020image,
+    title   = {An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
+    author  = {Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby},
+    year    = {2020},
+    eprint  = {2010.11929},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
+```bibtex
+@misc{vaswani2017attention,
+    title   = {Attention Is All You Need},
+    author  = {Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin},
+    year    = {2017},
+    eprint  = {1706.03762},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CL}
 }
 ```

setup.py

@@ -2,8 +2,8 @@ from setuptools import setup, find_packages
 
 setup(
   name = 'vit-pytorch',
-  packages = find_packages(),
-  version = '0.0.2',
+  packages = find_packages(exclude=['examples']),
+  version = '0.2.7',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',
@@ -25,4 +25,4 @@ setup(
     'License :: OSI Approved :: MIT License',
     'Programming Language :: Python :: 3.6',
   ],
-)
+)

vit_pytorch/efficient.py

@@ -0,0 +1,41 @@
+import torch
+from einops import rearrange, repeat
+from torch import nn
+
+class ViT(nn.Module):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, transformer, channels = 3):
+        super().__init__()
+        assert image_size % patch_size == 0, 'image dimensions must be divisible by the patch size'
+        num_patches = (image_size // patch_size) ** 2
+        patch_dim = channels * patch_size ** 2
+
+        self.patch_size = patch_size
+
+        self.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
+
+        self.to_cls_token = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, dim * 4),
+            nn.GELU(),
+            nn.Linear(dim * 4, num_classes)
+        )
+
+    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)
+        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.transformer(x)
+
+        x = self.to_cls_token(x[:, 0])
+        return self.mlp_head(x)

vit_pytorch/vit_pytorch.py

@@ -1,48 +1,65 @@
 import torch
-from einops import rearrange
 import torch.nn.functional as F
+from einops import rearrange, repeat
 from torch import nn
 
+MIN_NUM_PATCHES = 16
+
 class Residual(nn.Module):
     def __init__(self, fn):
         super().__init__()
         self.fn = fn
-    def forward(self, x):
-        return self.fn(x) + x
+    def forward(self, x, **kwargs):
+        return self.fn(x, **kwargs) + x
 
 class PreNorm(nn.Module):
     def __init__(self, dim, fn):
         super().__init__()
         self.norm = nn.LayerNorm(dim)
         self.fn = fn
-    def forward(self, x):
-        return self.fn(self.norm(x))
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
 
 class FeedForward(nn.Module):
-    def __init__(self, dim, hidden_dim):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
         super().__init__()
         self.net = nn.Sequential(
             nn.Linear(dim, hidden_dim),
             nn.GELU(),
-            nn.Linear(hidden_dim, dim)
+            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):
+    def __init__(self, dim, heads = 8, dropout = 0.):
         super().__init__()
         self.heads = heads
         self.scale = dim ** -0.5
 
         self.to_qkv = nn.Linear(dim, dim * 3, bias = False)
-        self.to_out = nn.Linear(dim, dim)
-    def forward(self, x):
+        self.to_out = nn.Sequential(
+            nn.Linear(dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, mask = None):
         b, n, _, h = *x.shape, self.heads
-        qkv = self.to_qkv(x)
-        q, k, v = rearrange(qkv, 'b n (qkv h d) -> qkv b h n d', qkv = 3, h = h)
+        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('bhid,bhjd->bhij', q, k) * self.scale
+        mask_value = -torch.finfo(dots.dtype).max
+
+        if mask is not None:
+            mask = F.pad(mask.flatten(1), (1, 0), value = True)
+            assert mask.shape[-1] == dots.shape[-1], 'mask has incorrect dimensions'
+            mask = mask[:, None, :] * mask[:, :, None]
+            dots.masked_fill_(~mask, mask_value)
+            del mask
+
         attn = dots.softmax(dim=-1)
 
         out = torch.einsum('bhij,bhjd->bhid', attn, v)
@@ -51,45 +68,60 @@ class Attention(nn.Module):
         return out
 
 class Transformer(nn.Module):
-    def __init__(self, dim, depth, heads, mlp_dim):
+    def __init__(self, dim, depth, heads, mlp_dim, dropout):
         super().__init__()
-        layers = []
+        self.layers = nn.ModuleList([])
         for _ in range(depth):
-            layers.extend([
-                Residual(PreNorm(dim, Attention(dim, heads = heads))),
-                Residual(PreNorm(dim, FeedForward(dim, mlp_dim)))
-            ])
-        self.net = nn.Sequential(*layers)
-    def forward(self, x):
-        return self.net(x)
+            self.layers.append(nn.ModuleList([
+                Residual(PreNorm(dim, Attention(dim, heads = heads, dropout = dropout))),
+                Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout)))
+            ]))
+    def forward(self, x, mask = None):
+        for attn, ff in self.layers:
+            x = attn(x, mask = mask)
+            x = ff(x)
+        return x
 
 class ViT(nn.Module):
-    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dropout = 0., emb_dropout = 0.):
         super().__init__()
         assert image_size % patch_size == 0, 'image dimensions must be divisible by the patch size'
         num_patches = (image_size // patch_size) ** 2
         patch_dim = channels * patch_size ** 2
+        assert num_patches > MIN_NUM_PATCHES, f'your number of patches ({num_patches}) is way too small for attention to be effective. try decreasing your patch size'
 
         self.patch_size = patch_size
 
         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(dim, depth, heads, mlp_dim)
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.transformer = Transformer(dim, depth, heads, mlp_dim, dropout)
+
+        self.to_cls_token = nn.Identity()
 
         self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
             nn.Linear(dim, mlp_dim),
             nn.GELU(),
+            nn.Dropout(dropout),
             nn.Linear(mlp_dim, num_classes)
         )
 
-    def forward(self, img):
+    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 = torch.cat((self.cls_token, x), dim=1)
-        x += self.pos_embedding
-        x = self.transformer(x)
+        b, n, _ = x.shape
 
-        return self.mlp_head(x[:, 0])
+        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, mask)
+
+        x = self.to_cls_token(x[:, 0])
+        return self.mlp_head(x)