Parth Natekar

Accessing Torch Model

4

Hi, How do I access the base torch model when using the high-level APIs ```pose_model = init_pose_model(pose_config, pose_checkpoint)``` ```pose_model``` is not an instance of ```torch.nn.Module```, is there any way to...

Hi, I'm getting checkerboard artifacts using MS-SSIM as a reconstruction loss but not while using simple SSIM. Any pointers on how I can reduce those? A sample image is below....

Hi, I've trained the VQVAE and the Pixel snail models on a dataset with multiple classes. However when I sample, I always seem to be getting different images of the...

Loss weights for optimal training

1

Hi, I had a question about the optimal weighting of the losses during training. I notice that initially if you weigh the fc loss, vq_loss, and reconstruction loss equally, the...

Installation Errors, glibc incompatibility

16

Hi, I am unable to install using conda. ``` UnsatisfiableError: The following specifications were found to be incompatible with each other: Output in format: Requested package -> Available versions The...

Weighted Loss

1

Hi, I can see an implementation for weighted MSE loss. Can you explain what how you get the weights for this? I cannot find this in your paper either. Thanks