ZF/vit-pytorch
1
0
Fork 0
mirror of https://github.com/lucidrains/vit-pytorch.git synced 2025-12-30 08:02:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

address https://github.com/lucidrains/vit-pytorch/issues/352

Browse Source
This commit is contained in:
lucidrains
2025-12-02 05:21:52 -08:00
parent fdaf7f92b9
commit 3cff5e547a
6 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@@ -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" }

2
vit_pytorch/na_vit_nested_tensor_3d.py
View File

@@ -176,7 +176,7 @@ class NaViT(Module):
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),

2
vit_pytorch/simple_flash_attn_vit_3d.py
View File

@@ -146,7 +146,7 @@ class SimpleViT(Module):
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),

2
vit_pytorch/simple_vit_3d.py
View File

@@ -103,7 +103,7 @@ class SimpleViT(nn.Module):
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),

2
vit_pytorch/vit_3d.py
View File

@@ -89,7 +89,7 @@ class ViT(nn.Module):
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),

2
vit_pytorch/vivit.py
View File

@@ -141,7 +141,7 @@ class ViT(nn.Module):
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)