This website requires JavaScript.
Explore
Help
Register
Sign In
pice35408784b54431987c4d13c457b9cd
/
vit-base-patch32-384_a13570863137681408750282
Watch
1
Star
0
Fork
You've already forked vit-base-patch32-384_a13570863137681408750282
0
Code
Issues
Pull Requests
Packages
Projects
Releases
Wiki
Activity
main
vit-base-patch32-384_a13570...
/
README.md
266 B
Raw
Permalink
Blame
History
Unescape
Escape
vit-base-patch32-384_a13570863137681408750282
视觉Transformer
(
ViT
)
是一种类似BERT的变换器编码器模型
,
它在一个大型图像集合上以有监督的方式预训练
,
即在分辨率为224x224像素的ImageNet-21k数据集上进行预训练。