Robert Luo

Really?

Additional complement： The full log: 

I would like to if the evaluation (e.g. FID LPIPS PSNR, etc.) code of VAE can be released?

Hi, @hipudding, Any update now? I have used your draft code for training. I found that although it runs pretty well with minimal changes, the speed is quite slow (910B...

Thanks for your quick reply! I have found something strange when I train the autoencoder, the speed is normal and 2x better than V100. However, when I train the Transformer-based...

Can you show the reconstruction images after training?

@bridenmj How much epochs do you use? Are you working on the ImageNet Pretrain?

Actually I reimplement the model structure to align with the magvit2 paper. But I find that the LFQ Loss is negative and the recon loss will get converage easily with...

Hi, recently we have devoted a lot to training the tokenizer in Magvit2, and now we have open source the tokenizer trained with imagenet. Feel free to use that. The...