more efficient

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.2.2',
+  version = '0.2.5',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',

vit_pytorch/vit_pytorch.py

@@ -3,6 +3,8 @@ import torch.nn.functional as F
 from einops import rearrange
 from torch import nn
 
+MIN_NUM_PATCHES = 16
+
 class Residual(nn.Module):
     def __init__(self, fn):
         super().__init__()
@@ -45,8 +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
 
@@ -85,6 +87,7 @@ 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. try decreasing your patch size'
 
         self.patch_size = patch_size
 
@@ -102,8 +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):