search

HRNet / HigherHRNet-Human-Pose-Estimation

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)
MIT License
1.35k stars 272 forks source link

Cannot evaluate results on CrowdPose datatset #102

Open calmiLovesAI opened 2 years ago

calmiLovesAI commented 2 years ago

hello, Thanks for your work. I've trained HigherHRNet on CrowdPose dataset, but when I evaluate my model on the test set by using the command python tools/valid.py --cfg xxx.xml TEST.MODEL_FILE xx.pth.tar, The program seems to be stuck.

Number of Layers
Conv2d : 302 layers   BatchNorm2d : 301 layers   ReLU : 270 layers   Bottleneck : 4 layers   BasicBlock : 108 layers   Upsample : 28 layers   HighResolutionModule : 8 layers   ConvTranspose2d : 1 layers   
=> loading model from models/model_best.pth.tar
loading annotations into memory...
Done (t=0.55s)
creating index...
index created!
=> classes: ['__background__', 'person']
yyruby commented 1 year ago

hello, Thanks for your work. I've trained HigherHRNet on CrowdPose dataset, but when I evaluate my model on the test set by using the command python tools/valid.py --cfg xxx.xml TEST.MODEL_FILE xx.pth.tar, The program seems to be stuck.

Number of Layers
Conv2d : 302 layers   BatchNorm2d : 301 layers   ReLU : 270 layers   Bottleneck : 4 layers   BasicBlock : 108 layers   Upsample : 28 layers   HighResolutionModule : 8 layers   ConvTranspose2d : 1 layers   
=> loading model from models/model_best.pth.tar
loading annotations into memory...
Done (t=0.55s)
creating index...
index created!
=> classes: ['__background__', 'person']

make the cfg.TEST.LOG_PROGRESS to be ture, and you can see the progress bar.