ViTPose_pytorch
ViTPose_pytorch copied to clipboard
jaehyunnn
An unofficial implementation of ViTPose [Y. Xu et al., 2022]
Hello author, thank you for your work. I have a question to ask you: The learning rate warms up to the preset value during training and quickly becomes 0，but the...
hello jaehyun, there is simple error that util resize func will return None, may be you missed that
Hello, thanks for your great work! When an image consists multi people, the vit-pose usually detects multi boxes and plot all of their posture. Is there any method to just...
Hi, thanks for your code. In the last few days I worked on a finetuned version on COCO + feet dataset (25 keypoints skeleton like openpose) with easy and fast...
Training preprocessing is missing during inference where images are only set to [0, 1] range but not normalized using mean / std. Inference code: https://github.com/jaehyunnn/ViTPose_pytorch/blob/1bd3cc3982d5b976622df54bcdc2106bb16e6d16/inference.py#L46-L48 Training code: https://github.com/jaehyunnn/ViTPose_pytorch/blob/1bd3cc3982d5b976622df54bcdc2106bb16e6d16/datasets/COCO.py#L119-L122 Reference from...
Hi, thank you for sharing a nice codebase Is there a way to get COCO wholebody keypoints in this repo like original ViTPose?
As far as I understood, all pretrained models are based on 256x192 image resolution. Is it possible to run it on 224x224 image?
#========= [Train Configs] =========# # - Num GPUs: 1 # - Batch size (per gpu): 1 # - LR: 0.000063 # - Num params: 89,994,513 # - AMP: True #===================================#...
