地址链接:https://www.flyai.com/m/semi_weakly_supervised_resnet50-16a12f1b.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
from flyai.utils import remote_helper
from torchvision.models.resnet import resnext50_32x4d
path = remote_helper.get_remote_date('https://www.flyai.com/m/semi_weakly_supervised_resnet50-16a12f1b.pth')
weight = torch.load(path)
model = resnext50_32x4d(pretrained = False)
model.load_state_dict(weight)
se_resnet101_ibn_a-fabed4e2.pth
查看来源:https://github.com/XingangPan/IBN-Net/releases/download/v1.0/se_resnet101_ibn_a-fabed4e2.pthresnet50_ibn_a-d9d0bb7b.pth
查看来源:https://github.com/XingangPan/IBN-Net/releases/download/v1.0/resnet50_ibn_a-d9d0bb7b.pthresnet101_ibn_a-59ea0ac6.pth
查看来源:https://github.com/XingangPan/IBN-Net/releases/download/v1.0/resnet101_ibn_a-59ea0ac6.pthsemi_weakly_supervised_resnet50-16a12f1b.pth
查看来源:https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnet50-16a12f1b.pthfcn_resnet101_coco-7ecb50ca.pth
查看来源:https://download.pytorch.org/models/fcn_resnet101_coco-7ecb50ca.pth