OwalnutO
OwalnutO
I also got stuck in this problem and solved it in another way. My tensorflow version is '0.12.1'. I replace the batch_norm class code in ops.py. with the code from...
Oh yeah, I have solved it. Thanks!
Hi, thanks for your wonderful code~ One problem. I find that the image naming format is different between your work and PG2 (https://arxiv.org/pdf/1705.09368.pdf), you name the images as 'fashion+men/women+cloth+id+view.jpg', but...
Is there anyone figure out how to make these csv file? Thanks~
> @forever208 thanks, I do. For my application I had to retrain though since I'm using more channels. Hi~I also try to train the AE on my own dataset but...
Set `--scale_lr=False`, then the learning rate will not be modified.
hah, same question. I guess, that this version is not a complete version. Hope the author can provide the full training code.
Same problem. The inference pipeline may contain some crop and padding operations. I guess this is the main reason.
For the first question, It seems that, for I2V model, the input image condition should not multiply the scale. Therefore, during training, the video latent should multiply the scale, but...
> When fine-tuning CogVideoX-5B on my own dataset, I've also encountered the same problem where the loss is noisy and doesn't go down. Have you discovered what the issue might...