allow for training on different image sizes, provided images are smaller than what was passed as image_size keyword on init

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.2.3',
+  version = '0.2.6',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',

vit_pytorch/efficient.py

@@ -30,10 +30,11 @@ class ViT(nn.Module):
 
         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 = self.cls_token.expand(img.shape[0], -1, -1)
+        cls_tokens = self.cls_token.expand(b, -1, -1)
         x = torch.cat((cls_tokens, x), dim=1)
-        x += self.pos_embedding
+        x += self.pos_embedding[:, :(n + 1)]
         x = self.transformer(x)
 
         x = self.to_cls_token(x[:, 0])

vit_pytorch/vit_pytorch.py

@@ -47,8 +47,8 @@ class Attention(nn.Module):
 
     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
 
@@ -105,8 +105,7 @@ class ViT(nn.Module):
             nn.Linear(dim, mlp_dim),
             nn.GELU(),
             nn.Dropout(dropout),
-            nn.Linear(mlp_dim, num_classes),
-            nn.Dropout(dropout)
+            nn.Linear(mlp_dim, num_classes)
         )
 
     def forward(self, img, mask = None):
@@ -114,10 +113,11 @@ class ViT(nn.Module):
 
         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 = self.cls_token.expand(img.shape[0], -1, -1)
+        cls_tokens = self.cls_token.expand(b, -1, -1)
         x = torch.cat((cls_tokens, x), dim=1)
-        x += self.pos_embedding
+        x += self.pos_embedding[:, :(n + 1)]
         x = self.dropout(x)
 
         x = self.transformer(x, mask)