new paper suggests image linear attention is more effective without query normalization

denoising_diffusion_pytorch/denoising_diffusion_pytorch.py

@@ -169,7 +169,6 @@ class LinearAttention(nn.Module):
         b, c, h, w = x.shape
         qkv = self.to_qkv(x)
         q, k, v = rearrange(qkv, 'b (qkv heads c) h w -> qkv b heads c (h w)', heads = self.heads, qkv=3)
-        q = q.softmax(dim=-2)
         k = k.softmax(dim=-1)
         context = torch.einsum('bhdn,bhen->bhde', k, v)
         out = torch.einsum('bhde,bhdn->bhen', context, q)

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'denoising-diffusion-pytorch',
   packages = find_packages(),
-  version = '0.3.2',
+  version = '0.4.0',
   license='MIT',
   description = 'Denoising Diffusion Probabilistic Models - Pytorch',
   author = 'Phil Wang',