search

yangyuke001 / FIIQA-PyTorch

face image illumination quality assessment implement by pytorch
351 stars 35 forks source link

RuntimeError: Error(s) in loading state_dict for ShuffleNetV2: #7

Open BarryKCL opened 4 years ago

BarryKCL commented 4 years ago

[root@e31325cc657e FIIQA-PyTorch]# python3 test.py Traceback (most recent call last): File "test.py", line 48, in net.load_state_dict(checkpoint['net']) File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 1045, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for ShuffleNetV2: size mismatch for classifier.0.weight: copying a param with shape torch.Size([200, 1024]) from checkpoint, the shape in current model is torch.Size([160, 1024]). size mismatch for classifier.0.bias: copying a param with shape torch.Size([200]) from checkpoint, the shape in current model is torch.Size([160]).

rocinant commented 4 years ago

change inputSize to 200, and transforms.Resize(224), take some time to read original repo and paper anyway, after pillow load the image with face = Image.open(image_path), resize it to (224, 224), then transforms.Resize(224), load model with net = ShuffleNetV2(200), shold be okay now.