Open Sun-Happy-YKX opened 1 year ago
a mistake occurs when I begin to train, add it for supplement.
I have annoted these codes about "ckpt_path" last training, I think it is the reason of above problem.
but the "ckpt_path" is not provided, could you please give some indications.
@Youncy-Hu
I observe that the quantization loss is expectable, but the reconstruction loss does not decrease any more.
@Youncy-Hu
Hello, I also encountered the same problem. The reconstruction_loss is always very high during the training process of VQ-VAE. Have you solved this problem?
the training of VQ-VAE is ineffective. I have download "Moving MNIST datasets" by the provided code, the final folder is as follows.
But when I execute the VQ-VAE training code, the loss of test does not reduce, it keep stable at a very high level as follow.
I would like you to give me some help, thanks.
Hello, the problem lies in this line of code: "train_dataset = MNIST4VQVAE(args.data_root, 'train', image_transform=transform)". Just change "image_transform=transform" to "image_transform=None". The same is true for "test_dataset = MNIST4VQVAE(args.data_root, 'test', image_transform=None)".
![]()
I have annoted these codes about "ckpt_path" last training, I think it is the reason of above problem.
but the "ckpt_path" is not provided, could you please give some indications.
Follow the code I modified above to train vqvae and save the model weights. Just load the weights of vqvae at this location.
Hello, have you reproduced the results of the paper? Also, how much video memory is needed to run this experiment? Can you please let me know? thank you
the training of VQ-VAE is ineffective. I have download "Moving MNIST datasets" by the provided code, the final folder is as follows.
But when I execute the VQ-VAE training code, the loss of test does not reduce, it keep stable at a very high level as follow.
I would like you to give me some help, thanks.