Why is magvitv2 different from the description in the paper? Am I understanding it wrong? about magvit2-pytorch HOT 7 OPEN

Please refer directly to Tencent’s implementation： https://github.com/TencentARC/Open-MAGVIT2

from magvit2-pytorch.

Why is magvitv2 different from the description in the paper? Am I understanding it wrong?

Hello, have you implemented it? I also noticed that it seems to be different from the content in the paper. So I would like to communicate with you.

from magvit2-pytorch.

Yes. I implemented it described in the paper as much as possible. The effect looks normal

from magvit2-pytorch.

from magvit2-pytorch.

Hello, I'm interested in how you implement the group norm in the MAGVIT-V2 paper. Did you directly apply group norm to a video tensor?

from magvit2-pytorch.

Thanks~

from magvit2-pytorch.

Please refer directly to Tencent’s implementation： https://github.com/TencentARC/Open-MAGVIT2

This implementation still seems to be large different from the original paper, and it only use a small model to train an image tokenizer. As you said you implemented it, how about the evaluation results? i.e. imagenet/ucf101 reconstruction? Is there any chance to communicate with you? @hefeicyp

from magvit2-pytorch.