Indraa145

Hello, I was wondering if there's a way to train the model but use x4 upscale factor instead of x8, thank you!

Use of detach

2

Hello, I'm currently learning about PyTorch and GAN, I want to ask about this particular lines from the WGAN implementation here. ```python # Configure input real_imgs = Variable(imgs.type(Tensor)) # ---------------------...

Regarding JointAutoRegressiveHierarchicalPriors implementation (mbt2018)

1

Hello, I have a question regarding the implementation of JointAutoRegressiveHierarchicalPriors. I noticed there is something off in the forward() function. ```python y_hat = self.gaussian_conditional.quantize( # Why do you use this...

Hello, in the CompressAI documentation, it is mentioned that "MS-SSIM optimized networks were fine-tuned from pre-trained MSE networks (with a learning rate of 1e-5 for both optimizers)." I want to...

Google Drive Link is dead

5

Hello, thank you for providing the script to download CelebA_HQ dataset. I'm trying to download the dataset through the google drive link you provided, but it seems that the link...

Auxiliary points confidence and offset prediction

1

Hello, thank you for the great work. I see that the training code is incomplete, so I'm trying to implement it and have a few questions regarding auxiliary points confidence...