Ming Li

Hi @edgarriba, Any updates on this issue? I also meet the same question that the edge cannot be differentiable

Hi @tancik, How is the project going? Will I be able to use it out of the box?

@tjruwase I have the same issue when I used [this repo](https://github.com/yuvalkirstain/PickScore) to train the model. The only change is set the precision to `FP16`

> The script `browse_dataset.py` has not supported argument `skeleton_style`. Please add `skeleton_style="openpose"` at > > https://github.com/open-mmlab/mmpose/blob/6d10b2ec81da7e252016b3154c7fdb46c403ecd8/tools/misc/browse_dataset.py#L100 > > and > https://github.com/open-mmlab/mmpose/blob/6d10b2ec81da7e252016b3154c7fdb46c403ecd8/tools/misc/browse_dataset.py#L151 > > > manually Thanks for your kindly help!

Hi @Ben-Louis, The instructions work for the COCO dataset. After that, I tried to use the same workflow to browse the HumanArt dataset by replacing configs, but some strange error...

Thanks for your reply. Could you please tell me how I should modify it to visualize these poses in the openpose style? I would appreciate it if you could give...

> Hi all, > Do anyone have password for AgeDB original dataset. i sent a mail to the given email-id but i did not get any reply from them. >...

> Hi, we use `gc` (https://gist.github.com/dojoteef/26cd46f7cc38b38e6f443c5f62411aa3) and `torch.cuda.memory_reserved()` to profile memory usage. HI, @KaiLv69 I tried to use the scripts that you provided above. However, the code example you provided...

> Yes, in order to make the dataset more readable and scalable, we have tidied up the dataset so that it does not directly match the training code. We will...

> We apologize that the update of the training code may be a week or two away as the friend who is responsible for putting this part of the training...