地址链接:https://www.flyai.com/m/RepVGG-A0-train.pth
查看来源:https://drive.google.com/drive/folders/1Avome4KvNp0Lqh2QwhXO6L5URQjzCjUq
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
#次模型pytorch没有进行开源,2021年CVPR对此方法进行开源,开源代码地址:DingXiaoH/RepVGG: RepVGG: Making VGG-style ConvNets Great Again (github.com)
from repvgg import get_RegVGG_func_by_name
repvgg_build_func=get_RegVGG_func_by_name ('RepVGG-A0')
model=repvgg_build_func(deploy=False)
path=remote_get_remote_data("https://www.flyai.com/m/RepVGG-A0-train.pth")
model.loda_state_dict(torch.load(path))
model.fc=nn.Linear(1280,200)#输出节点数可自行定义
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