pice35408784b54431987c4d13c457b9cd
/
vit-base-patch32-384_a13570863137681408750282
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
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。
3 Commits 1 Branch 0 Tags 1.3 GiB
Go to file
YYJ-aaaa dc4a998919 first commit 2024-11-12 16:34:25 +08:00
.gitattributes Add .gitattributes 2024-11-12 16:24:29 +08:00
README.md Initial commit 2024-11-12 16:24:29 +08:00
config.json first commit 2024-11-12 16:34:25 +08:00
flax_model.msgpack first commit 2024-11-12 16:34:25 +08:00
model.safetensors first commit 2024-11-12 16:34:25 +08:00
preprocessor_config.json first commit 2024-11-12 16:34:25 +08:00
pytorch_model.bin first commit 2024-11-12 16:34:25 +08:00
tf_model.h5 first commit 2024-11-12 16:34:25 +08:00

README.md

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。