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

add link to official repo for levit

Browse Source
This commit is contained in:
Phil Wang
2021-05-06 13:12:30 -07:00
parent 74b402377b
commit 7333979e6b
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -271,6 +271,8 @@ preds = v(img) # (1, 1000)
<a href="https://arxiv.org/abs/2104.01136">This paper</a> proposes a number of changes, including (1) convolutional embedding instead of patch-wise projection (2) downsampling in stages (3) extra non-linearity in attention (4) 2d relative positional biases instead of initial absolute positional bias (5) batchnorm in place of layernorm. <a href="https://arxiv.org/abs/2104.01136">This paper</a> proposes a number of changes, including (1) convolutional embedding instead of patch-wise projection (2) downsampling in stages (3) extra non-linearity in attention (4) 2d relative positional biases instead of initial absolute positional bias (5) batchnorm in place of layernorm.
<a href="https://github.com/facebookresearch/LeViT">Official repository</a>
```python ```python
import torch import torch
from vit_pytorch.levit import LeViT from vit_pytorch.levit import LeViT