address #352

Author: lucidrains

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "vit-pytorch"
-version = "1.16.1"
+version = "1.16.2"
 description = "Vision Transformer (ViT) - Pytorch"
 readme = { file = "README.md", content-type = "text/markdown" }
 license = { file = "LICENSE" }

vit_pytorch/na_vit_nested_tensor_3d.py

@@ -176,7 +176,7 @@ def __init__(
 
         self.channels = channels
         self.patch_size = patch_size
-        self.to_patches = Rearrange('c (f pf) (h p1) (w p2) -> f h w (c p1 p2 pf)', p1 = patch_size, p2 = patch_size, pf = frame_patch_size)
+        self.to_patches = Rearrange('c (f pf) (h p1) (w p2) -> f h w (c pf p1 p2)', p1 = patch_size, p2 = patch_size, pf = frame_patch_size)
 
         self.to_patch_embedding = nn.Sequential(
             nn.LayerNorm(patch_dim),

vit_pytorch/simple_flash_attn_vit_3d.py

@@ -146,7 +146,7 @@ def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, nu
         patch_dim = channels * patch_height * patch_width * frame_patch_size
 
         self.to_patch_embedding = nn.Sequential(
-            Rearrange('b c (f pf) (h p1) (w p2) -> b f h w (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f h w (pf p1 p2 c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
             nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
             nn.LayerNorm(dim),

vit_pytorch/simple_vit_3d.py

@@ -103,7 +103,7 @@ def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, nu
         patch_dim = channels * patch_height * patch_width * frame_patch_size
 
         self.to_patch_embedding = nn.Sequential(
-            Rearrange('b c (f pf) (h p1) (w p2) -> b f h w (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f h w (pf p1 p2 c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
             nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
             nn.LayerNorm(dim),

vit_pytorch/vit_3d.py

@@ -89,7 +89,7 @@ def __init__(self, *, image_size, image_patch_size, frames, frame_patch_size, nu
         assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
 
         self.to_patch_embedding = nn.Sequential(
-            Rearrange('b c (f pf) (h p1) (w p2) -> b (f h w) (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            Rearrange('b c (f pf) (h p1) (w p2) -> b (f h w) (pf p1 p2 c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
             nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
             nn.LayerNorm(dim),

vit_pytorch/vivit.py

@@ -141,7 +141,7 @@ def __init__(
         self.global_average_pool = pool == 'mean'
 
         self.to_patch_embedding = nn.Sequential(
-            Rearrange('b c (f pf) (h p1) (w p2) -> b f (h w) (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f (h w) (pf p1 p2 c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
             nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
             nn.LayerNorm(dim)