Wazaki-Ou

I am also facing the same issue with yolov7-e6. Did anyone find the reason ? Edit: Apparently the solution is to use train_aux.py instead of train.py. It's specified in the...

@marcoramosh Could you please give more details about how we can load just the `state_dict()` when using detect.py? I have trained a custom model and took the `best.pt` to use...

As long as you load the "checkpoint.pt" file as your weight, it should be all good. The epochs concern the actual training you are running, so it's normal that they...

@amaze567 I'm not sure if that's an incorrect behavior to be honest. I hope someone else who has a better understanding of how resume works can help.

I am interested in the same thing. It's nice to have spatial labeling, but I am interested in the action as well and I wonder if UltimateLabeling allows adding behavior...

@vivek87799 I am currently using ViTBAT to do that, but it does not include some options like object tracking, so you need to specify the spatial annotation in the whole...

@mynameisvinn I'm not an expert (in fact, I just got the code today) but I think this line in the code here makes sure it does not extract the output...

@XXXXRT666 thanks for the answer (I'm also interested in other languages). I have a question about this. When we train on a new language, does voice cloning from another language...

> > > As others mentioned you can get multi gpu working with accelerate. I posted how I got it working with 5090s here: > > > https://github.com/thad0ctor/unsloth-5090-multiple > >...

@lipku Thanks a lot for the reply. I actually tried wav2lip as well before posting, but the lip movement seemed asymmetrical and awkward. For Musetalk, you mentioned gpu computation. I...