Zhuoheng Li
Zhuoheng Li
泪目啊，啥时候能开源
@RobertLuo1 @Jihun999 @lucidrains If you successfully trained this model, would you like to share the pretrained weights and the modified model code?
Hi @vincentcartillier, Please check Tencent's https://github.com/TencentARC/Open-MAGVIT2, which is based on this implementation but modify some parts
@vincentcartillier Oh yes but they are developing a video tokenizer... They had the same problem during training the image tokenizer and finally fixed it. I guess @RobertLuo1 can answer your...
> have you been able to finetune using their own implementation?? Not yet. I have no experience on finetuning diffusion models before...I usually finetune LLM. I am not sure whether...
Perhaps you can also print the config at the beginning of training/eval. Currently you are using hydra and different config files may override each other. Sometimes a user may not...
@Cadene: Re progressbar: you are right, I will not make it as an option. I still suggest to enable both progress bars (i.e., the progress bar for episodes and the...
As a side note, now it logs this at the beginning of training, which is very easy to read: ``` INFO 2024-08-14 13:15:24 :1 {'dataset_repo_id': 'lerobot/pusht', 'device': 'cuda', 'env': {'action_dim':...
@Cadene You are right! I explain it here: ### What this does 1. Enable progress bar for evaluation by default, except in slurm 2. Enable asynchronized env by default, except...
Just out of curiosity, does LeRobot support multi-gpu training now? (you just mentioned slurm ^^