commit 1907ff1a797af41b189ee89eb3cdd5935cf447d5 Author: pice35408784b54431987c4d13c457b9cd Date: Thu Dec 5 14:03:00 2024 +0800 Initial commit diff --git a/README.md b/README.md new file mode 100644 index 0000000..c898f63 --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +# vit-base-patch16-224-cifar10_a13830216739319808912711 + +Vision Transformer (ViT) 模型在 ImageNet-21k(1400 万张图像,21843 个类别)上进行预训练,并在 CIFAR10 上以 224x224 的分辨率进行微调。 \ No newline at end of file