Xuer0313

**Please detail your questions here : )** Sorry to bother, you said the strategy using VDC to finetune WPDC achieves the best result, I wonder the finetune operation in detail....

Have you ever tried every config in 'trt_pose/tasks/human_pose/experiments/' for training, I trained most of config file, only the 'resnet18' backbone worked. The others' eval AP are all equal to 0,...

I tried to download the videos and annotations of the dataset using the script file you provide, but the downloading speed is just a few KB/s. Is there any other...

关于训练模型的问题

1

小白请问一下训练代码是基于什么模型框架写的？

The backgroud raw images

1

https://github.com/yueyang130/3D-Hand-Shape-and-Pose-from-Images-in-the-Wild/blob/47d1608b68f76f01c29d1f98a25de25e793a6e26/scripts/prepare_background.py#L5 很棒的复现工作，我想知道用来生成预训练数据集的背景图片是从哪里获取的呢？

question about evaluate code of 'Panoptic' dataset

1

I found you used different evaluation metrics in 'MuPoTS-3D' and 'Panoptic' dataset. But you didn't release the evaluate code of 'Panoptic' dataset. Is it convenient for you to release the...