resnet50_v1c weight not match

[wangziyukobe]

Thanks to your great work!
I tried to run pspnet according to your instructions. I downloaded 'resnet50_v1c' from gluon and converted it to pytorch model by running 'python gluon2pytorch.py -m 'resnet50_v1c'. But when I tried to run the pspnet by command 'python train.py -d 0-7', it shows that the weight of the checkpoint does not match that of the current model. The log is as following:
RuntimeError: Error(s) in loading state_dict for ResNet:
size mismatch for conv1.0.weight: copying a param with shape torch.Size([32, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3]).
size mismatch for conv1.1.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.1.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.1.running_mean: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.1.running_var: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.3.weight: copying a param with shape torch.Size([32, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for conv1.4.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.4.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.4.running_mean: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.4.running_var: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for conv1.6.weight: copying a param with shape torch.Size([64, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 64, 3, 3]).
size mismatch for bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 128, 1, 1]).
size mismatch for layer1.0.downsample.0.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 128, 1, 1]).
Could you help me find out where it goes wrong? Thanks very much!

[ycszen]

Hi, thanks for your attention. I have checked the pre-trained model in Gluon. Now the pre-trained model in Gluon has changed some setting in the model. Therefore, if you have to use the converted model, you need to change the resnet code in the base_model folder correspondingly. Or I will publish the pre-trained model recently.

[Dorispaopao]

when will you publish the pre-trained model ?and where can I download the resnet101_v1c.pth?

[timehasspeed]

i have the same problem ,if you have solved , can you tell me how to do ?
thanks very much

[timehasspeed]

when will you publish the pre-trained model ?and where can I download the resnet101_v1c.pth?

you can find urls on the pyt_utils.py ,

[danny95333]

when will you publish the pre-trained model ?and where can I download the resnet101_v1c.pth?

you can find urls on the pyt_utils.py ,

I think the .pth in pyt_utils.py are original Resnet101's weight which is different with Resnet101_v1c.

[ycszen]

I have released the pre-trained models.
Welcome to using them~