search

twtygqyy / pytorch-SRResNet

pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
MIT License
477 stars 131 forks source link

I use my .mat image to test model have error #6

Open ratsuki opened 6 years ago

ratsuki commented 6 years ago

I just export original image to .mat type,and then to test it. here is my error:

Warning: source code of class 'srresnet._Residual_Block' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes. warnings.warn(msg, SourceChangeWarning) Traceback (most recent call last): File "test.py", line 35, in im_gt = sio.loadmat("Set5/" + opt.image + ".mat")['im_gt'] KeyError: 'im_gt'

And is there have any requirements about export image to .mat type? Look forward to your answer!

surajitsaikia27 commented 6 years ago

Did you solve the problem? I am encountering the same problem. The way the author created the testset is different since it has indexes.

twtygqyy commented 6 years ago

@surajitsaikia27 @ratsuki Please refer to the matlab code here