meet an error when load model:
error:
RuntimeError: Error(s) in loading state_dict for VGG:
Missing key(s) in state_dict: "features.0.weight", "features.0.bias", "features.2.weight", "features.2.bias", "features.5.weight", "features.5.bias", "features.7.weight", "features.7.bias", "features.10.weight", "features.10.bias", "features.12.weight", "features.12.bias", "features.14.weight", "features.14.bias", "features.17.weight", "features.17.bias", "features.19.weight", "features.19.bias", "features.21.weight", "features.21.bias", "features.24.weight", "features.24.bias", "features.26.weight", "features.26.bias", "features.28.weight", "features.28.bias".
Unexpected key(s) in state_dict: "features.module.0.weight", "features.module.0.bias", "features.module.2.weight", "features.module.2.bias", "features.module.5.weight", "features.module.5.bias", "features.module.7.weight", "features.module.7.bias", "features.module.10.weight", "features.module.10.bias", "features.module.12.weight", "features.module.12.bias", "features.module.14.weight", "features.module.14.bias", "features.module.17.weight", "features.module.17.bias", "features.module.19.weight", "features.module.19.bias", "features.module.21.weight", "features.module.21.bias", "features.module.24.weight", "features.module.24.bias", "features.module.26.weight", "features.module.26.bias", "features.module.28.weight", "features.module.28.bias".
reason:
used nn.DataParallel to save the model.
solve:
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in self.state_dict.items():
if "module" not in k:
name = k# remove 'module.' of dataparallel
new_state_dict[name]=v
torch.save(new_state_dict,"./model/model.checkpoint_1_261730_smiple")
model.load_state_dict(new_state_dict)