Gengzigang/PCT
This is an official implementation of our CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)
PythonMIT
Issues
- 0
- 0
Loss of keypoints or joints wasn't stable
#42 opened by Tommy-Hsu - 5
When training a classifier, don't freeze the weights of the decoder and codebook?
#30 opened by epleone - 5
How to inference 3D pose?
#11 opened by jun297 - 16
- 6
Module not found error!
#34 opened by JasOleander - 0
- 3
How much time taken for training of 2D dataset?
#40 opened by JasOleander - 4
Tokens to be integers
#38 opened by Tommy-Hsu - 0
- 2
h36m dataset and result reproduction
#32 opened by henryfungusa - 1
KeyError: 'PCT is not in the models registry'
#33 opened by JasOleander - 0
About MLP-Mixer
#37 opened by graybox123 - 0
I have a question about training on MPII dataset. How to train on this dataset?
#36 opened by hdd0510 - 0
Errors in version package
#35 opened by vanhdz2611 - 5
- 0
How to train and test on an MPII dataset?
#31 opened by abuTICO - 0
FLOPS params
#29 opened by guzejungithub - 0
Question about well-trained checkpoint
#28 opened by imabackstabber - 0
How to make the model work on Windows
#27 opened by triste-hcq - 0
onnx
#26 opened by YueSangShuai - 0
- 0
How to train separately on an MPII dataset? Can you share the configuration file?
#23 opened by Kongnanjun - 0
想问一下stage1的量化误差是多少?
#24 opened by BlueSeaHome - 9
- 0
score of each keypoint is same
#22 opened by HappyFaceFriend - 2
- 0
How to train the classifier model?
#21 opened by SuperJay1996 - 2
Question about the dimension of token feature
#16 opened by PeiChiChen - 0
how to train the classifier model
#20 opened by lidc1004 - 1
add the other dataset to improve the performance
#15 opened by wxhqw - 1
- 0
chumpy installation
#17 opened by grpinto - 2
Questions about codebook implementation
#8 opened by limonan-tal - 0
Question about classifier training
#14 opened by gmk11 - 1
information about the backbone
#10 opened by gmk11 - 1
Upgrade mmcv/mmpose version to newest
#12 opened by tgoncalv - 2
the output score of the keypoint
#13 opened by wxhqw - 1
该项目支持对视频进行推理吗
#9 opened by Yi-Yang355 - 3
what about model's inference
#7 opened by gmk11 - 1
想看一看,环境弄了许久也没成功
#6 opened by qiushanjun - 2
About Ablation
#5 opened by imabackstabber - 0