部分输入网页直接开始下载,一些是自己训练后的模型。
https://download.pytorch.org/models/resnet18-5c106cde.pth
https://download.pytorch.org/models/resnet34-333f7ec4.pth
https://download.pytorch.org/models/resnet50-19c8e357.pth
https://download.pytorch.org/models/resnet101-5d3b4d8f.pth
https://download.pytorch.org/models/resnet152-b121ed2d.pth
https://drive.google.com/u/0/uc?id=1BOdAkUbD7sqihaDJekB4XJMqB2fE6aNc&export=download
resnet34_6种花分类:数据集如图
resnet50_5Celebruty_Faces_dataset:
pytorch框架下训练后的权重文件下载后可以直接识别,无须训练。
(下载地址包含了自己经常使用的权重文件,以后会有更新关于resnet的相关文件。)
下载地址:
链接:https://pan.baidu.com/s/1SxPcuWd1yZctecgT3279aw
提取码:summ
https://dl.fbaipublicfiles.com/convnext/convnext_tiny_1k_224_ema.pth
https://dl.fbaipublicfiles.com/convnext/convnext_small_1k_224_ema.pth
https://dl.fbaipublicfiles.com/convnext/convnext_base_1k_224_ema.pth
https://dl.fbaipublicfiles.com/convnext/convnext_base_22k_224.pth
https://dl.fbaipublicfiles.com/convnext/convnext_large_1k_224_ema.pth
https://dl.fbaipublicfiles.com/convnext/convnext_large_22k_224.pth
https://dl.fbaipublicfiles.com/convnext/convnext_xlarge_22k_224.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22k.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22k.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22k.pth
https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22k.pth
【1】GitHub - pytorch/pytorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration
【2】pytorch 中pkl和pth的区别?_AI界扛把子的博客-CSDN博客_pkl和pth