commit 3ada665c2dbd24dc8f1b4314ce0b15926d0106c4 Author: pice35408784b54431987c4d13c457b9cd Date: Tue Nov 12 16:24:29 2024 +0800 Initial commit diff --git a/README.md b/README.md new file mode 100644 index 0000000..f316ca7 --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +# 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。 \ No newline at end of file