tjpulkl / cdgnet Goto Github PK

C:\Users\Rania\Documents\Human-Parsing-PyTorch>python evaluate_multi.py
Traceback (most recent call last):
File "C:\Users\Rania\Documents\Human-Parsing-PyTorch\evaluate_multi.py", line 254, in
main()
File "C:\Users\Rania\Documents\Human-Parsing-PyTorch\evaluate_multi.py", line 221, in main
model.load_state_dict(state_dict)
File "C:\Users\Rania\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\torch\nn\modules\module.py", line 2189, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for ResNet:

I am unable to resolve this error since the new version of the LIP model with all the weights is not available now. Please help me out.

Can you please update the license of this repo (like MIT or Apache) so that other people can try it out? Thanks!

Thanks for sharing the codes.

I have a minor question.

In the experiments, does the model converges enough for 150 epochs and there is no significant performance improvement if you train the model more? If not, is there any reason you trained your model for 150 epochs?

Congrats on your great work! Do you plan to add a single image inference script?

Hi, I'm trying to access the LIP_epoch_149.pth, but I cannot download it from baidu link, can you please provide Google disc link.

Can you provide a simply script to get the visualization result？ thanks you！

I have a issue when i use pretrained LIP_epoch_149.pth

Thank you for your outstanding work. Can you provide the model pre-trained on the CIHP dataset?

Hello, I appreciate your awesome work.
I want to try evaluation, but there's an error while calling load_state_dict() in evaluate.py
the error message is as below:

size mismatch for layer6.conv2.0.weight: copying a param with shape torch.Size([48, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([48, 256, 3, 3]).

It seems that the dimensions in the pretrained model 'LIP_epoch_149.pth' and the constructed model from LIPDataSet() are different in some layers. Could you check this issue?

Thank you!