LeViT-128S 模型在 ImageNet-1k 上以 224x224 的分辨率进行预训练。Graham 等人在论文 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference 中介绍了它。
Go to file
YYJ-aaaa 121e26a188 first commit 2024-11-06 17:06:29 +08:00
.gitattributes Add .gitattributes 2024-11-06 16:58:30 +08:00
README.md Initial commit 2024-11-06 16:58:29 +08:00
config.json first commit 2024-11-06 17:06:29 +08:00
model.safetensors first commit 2024-11-06 17:06:29 +08:00
preprocessor_config.json first commit 2024-11-06 17:06:29 +08:00
pytorch_model.bin first commit 2024-11-06 17:06:29 +08:00

README.md

levit-128S_a13503182913400832692277

LeViT-128S 模型在 ImageNet-1k 上以 224x224 的分辨率进行预训练。Graham 等人在论文 LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference 中介绍了它。