StridedTransformer-Pose3D

StridedTransformer-Pose3D copied to clipboard

HI, I saw your answer in a closed issue. May I ask how can I retrained in casual setting to process real-time video streams?

Allencheng97

I wonder about what parameter of reverse_augmentation and data_augmentation for ?

1

any difference in training phase or testing phase ？

vicentowang

Process of a case when a person keeps the same pose for long time

1

Hello How are you? Thanks for contributing to this project. Even when a person keeps the same pose for long time (ex: for 3~5 seconds), is it possible to estimate...

rose-jinyang

takeyamayuki

multi-GPU for training

3

hello, thank you for your awesome work. I have toubles of using multi-gpus when training: I added "model = nn.DataParallel(model)" before main.py line187: "all_param = []", but it doesn't work...

SleepEarlyLiveLong

After training for several epochs, add refine module?

2

is it refer to Exploiting Spatial-temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks, the refinement module? how many epochs do I need to train to add this module？

haofeng0705

GPU usage when running demo code - low fps

2

Dear author, Thank you for your amazing work. I trying run your demo code with in-the-wild video and I got only about 15fps with 3D pose estimation (with HRnet and...

SonNguyen2510

I am currently working on a project where I aim to use your Colab notebook to process PNG image files, but I’ve noticed that the code expects an MP4 video...

eliflali

im a junior student,i dont have power enough to get attention map.can you give me a example?

kimblaaG