def resnet152(pretrained=True, root='~/.gluoncvth/models', **kwargs):
"""Constructs a ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained:
d = torch.load(get_model_file('resnet101', root=root))
d = warp_dict_fn(d)
try:
model.load_state_dict(d, strict=True)
except Exception as e:
print(e)
print(
"try load with strict = True failed , load with strict = False"
)
model.load_state_dict(d, strict=False)
return model
def resnet101(pretrained=True, root='~/.gluoncvth/models', **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
se_kwargs = kwargs.pop('se_kwargs')
block = partial(Bottleneck, se_kwargs=se_kwargs)
block.expansion = Bottleneck.expansion
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
d = torch.load(get_model_file('resnet101', root=root))
d = warp_dict_fn(d)
try:
model.load_state_dict(d, strict=True)
except Exception as e:
print(e)
print(
"try load with strict = True failed , load with strict = False"
)
model.load_state_dict(d, strict=False)
return model
