def resnet50(pretrained=True, **kwargs):
model = _resnet50(pretrained=False, **kwargs)
if pretrained:
url = 'https://dl.fbaipublicfiles.com/barlowtwins/ep1000_bs2048_lrw0.2_lrb0.0048_lambd0.0051/resnet50.pth'
state_dict = torch.hub.load_state_dict_from_url(url, map_location='cpu')
model.load_state_dict(state_dict, strict=False)
return model
def resnet50(pretrained=False, *args, **kwargs):
"""
Resnet50 model
pretrained (bool): a recommended kwargs for all entrypoints
args & kwargs are arguments for the function
"""
from torchvision.models.resnet import resnet50 as _resnet50
model = _resnet50(*args, **kwargs)
checkpoint = 'https://download.pytorch.org/models/resnet50-19c8e357.pth'
if pretrained:
model.load_state_dict(model_zoo.load_url(checkpoint, progress=False))
return model
def resnet50(pretrained=True, **kwargs):
"""
ResNet-50 pre-trained with SwAV.
Note that `fc.weight` and `fc.bias` are randomly initialized.
Achieves 75.3% top-1 accuracy on ImageNet when `fc` is trained.
"""
model = _resnet50(pretrained=False, **kwargs)
if pretrained:
state_dict = torch.hub.load_state_dict_from_url(
url="https://dl.fbaipublicfiles.com/deepcluster/swav_800ep_pretrain.pth.tar",
map_location="cpu",
)
# removes "module."
state_dict = {k.replace("module.", ""): v for k, v in state_dict.items()}
# load weights
model.load_state_dict(state_dict, strict=False)
return model