seeing a signal with dual patchnorm in another repository, fully incorporate

vit_pytorch/learnable_memory_vit.py

@@ -118,7 +118,9 @@ class ViT(nn.Module):
 
         self.to_patch_embedding = nn.Sequential(
             Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
+            nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
+            nn.LayerNorm(dim)
         )
 
         self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))