地址链接:https://www.flyai.com/m/coat_lite_small-fea1d5a1.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
def coat_lite_small(pretrained=False, num_classes=9): model_cfg = dict( patch_size=4, embed_dims=[64, 128, 320, 512], serial_depths=[3, 4, 6, 3], parallel_depth=0, num_heads=8, mlp_ratios=[8, 8, 4, 4]) model =CoaT(**model_cfg) if pretrained: from flyai.utils import remote_helper path = remote_helper.get_remote_data(upload_url) model.load_state_dict(torch.load(path) ) model.head = nn.Linear(in_features=512, out_features=num_classes, bias=True) model.head = nn.Linear(in_features=512, out_features=num_classes, bias=True) return model
tf_efficientnetv2_s_21k-6337ad01.pth
查看来源:https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-effv2-weights/tf_efficientnetv2_s_21k-6337ad01.pthtf_efficientnetv2_l_21k-91a19ec9.pth
查看来源:https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-effv2-weights/tf_efficientnetv2_l_21k-91a19ec9.pthmobilenetv3-large-1cd25616.pth
查看来源:https://github.com/bubbliiiing/mobilenet-yolov4-lite-pytorch#%E6%96%87%E4%BB%B6%E4%B8%8B%E8%BD%BDinception_v3_google-0cc3c7bd.pth
查看来源:https://download.pytorch.org/models/inception_v3_google-0cc3c7bd.pthdeit_base_patch16_224-b5f2ef4d.pth
查看来源:https://dl.fbaipublicfiles.com/deit/deit_base_patch16_224-b5f2ef4d.pthswin_large_patch4_window12_384_22k.pth
查看来源:https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22k.pth