地址链接：https://www.flyai.com/m/skresnext50_ra-f40e40bf.pth
确定自己使用的框架并导入对应的库。导入库实现样例代码可参考 文档中心-预训练模型使用教程
在代码中实现加载预训练模型地址
import timm
pretrain_path = remote_helper.get_remote_date('https://www.flyai.com/m/resnet50-19c8e357.pth')
model = timm.create_model("skresnext50_32x4d",pretrained=False)
model.load_state_dict(torch.load(pretrain_path))
resnext101_64x4d-ee2c6f71.pth
查看来源：https://download.openmmlab.com/pretrain/third_party/resnext101_64x4d-ee2c6f71.pthgluon_seresnext50_32x4d-90cf2d6e.pth
查看来源：https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_seresnext50_32x4d-90cf2d6e.pthgluon_seresnext101_64x4d-f9926f93.pth
查看来源：https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_seresnext101_64x4d-f9926f93.pthgluon_seresnext101_32x4d-cf52900d.pth
查看来源：https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_seresnext101_32x4d-cf52900d.pthresnext101_ibn_a-6ace051d.pth
查看来源：https://github.com/XingangPan/IBN-Net/releases/download/v1.0/resnext101_ibn_a-6ace051d.pthskresnext50_ra-f40e40bf.pth
查看来源：https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/skresnext50_ra-f40e40bf.pthsemi_weakly_supervised_resnext101_32x16-f3559a9c.pth
查看来源：https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnext101_32x16-f3559a9c.pth