pytorch-SRResNet

pytorch-SRResNet copied to clipboard

@twtygqyy ，Hi, I trained normally but the test showed memory issue error like this. I don't know why it needs so much memory. RuntimeError: cuda runtime error (2) : out...

HPL123

It seems that there is no use for adversarial losses

1

Thank you for your code. I read the code, but can't find the adversarial losses anywhere. The _NetD network is not used, right?

Alxemade

Hello, for training 2x network ,i change your code in self.upscale4x = nn.Sequential( nn.Conv2d(in_channels=64, out_channels=256, kernel_size=3, stride=1, padding=1, bias=False), nn.PixelShuffle(2), nn.LeakyReLU(0.2, inplace=True), #nn.Conv2d(in_channels=64, out_channels=256, kernel_size=3, stride=1, padding=1, bias=False), #nn.PixelShuffle(2), #nn.LeakyReLU(0.2,...

Rainyliuliu

Tips for training

1

Hello, I would like to ask you about your experience in training the dataset. About choosing the iteration 500 (training will take about one week), size_average in MSE_Loss ? Why...

leviethung2103

Change Upscale Value

1

Dear all, this project seems to fix its upscale to 4. When I changed the upscale value to 2 in the generate_train_srresnet.m, it runs into a RunTime Error: RuntimeError: input...

niuqun

UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 918: ordinal not in range(128)

1

I'm getting that when I try to run this in Python 3. I'm able to run demo.py in Python 2. Is it possible to get a pretrained model for Python...

xjdeng

Why vgg19 updates?

2

I'm confused whether we need to update the vgg network. The [example](https://github.com/pytorch/examples/tree/master/fast_neural_style) in pytorch tutorial keeps the parameters in vgg16 untouched. But as far as I understand, your implementation updates...

AlbertZhangHIT

I use my .mat image to test model have error

2

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...

ratsuki

Could you provide some training experience？

1

I spend a lot of time in Keras for SRGAN but got bad results, So I try to use Pytorch for SR. I want to reproduce your work ( the...

SimonFFL

Error Generating HDF5 (Memory Leaked)

1

Hello thank you very much for the work. I have a problem when trying to convert train data to hdf5 I got this message in matlab. ``` Requested 96x96x3x38234 (7.9GB)...

herleeyandi