deep-high-resolution-net.pytorch
deep-high-resolution-net.pytorch copied to clipboard
leoxiaobin
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
I am searching for the onnx file of your model, but it seems that there is no ready-made one, can you provide it?
when I run :"python tools/test.py \ --cfg experiments/coco/hrnet/w32_256x192_adam_lr1e-3.yaml \ TEST.MODEL_FILE models/pytorch/pose_coco/pose_hrnet_w32_256x192.pth \ TEST.USE_GT_BBOX False" to test on COCO val2017 dataset using model zoo's models,it occurs the error: => creating output/coco/pose_hrnet/w32_256x192_adam_lr1e-3...
I saw that a six-scale pyramid testing procedure is performed in this paper. But I didn't find the relevant code, where is the code for this? Thank you！
What if I want to replace the coco dataset with my own? What will be changed?
loading annotations into memory... Done (t=0.48s) creating index... index created! => classes: ['__background__', 'person'] => num_images: 5000 => Total boxes: 104125 => Total boxes after fliter low [email protected]: 104125 =>...
i installed MINGW in Win10 to execute commend "make", but it just showed the content of Makefile Just like this: (pytorch) E:\github\deep-high-resolution-net.pytorch-master\lib>make cd nms; python setup_linux.py build_ext --inplace; rm -rf...
**When I follow the guide and train on coco using "python tools/train.py --cfg experiments/coco/hrnet/w32_256x192_adam_lr1e-3.yaml ",there are two errors:** Traceback (most recent call last): File "tools/train.py", line 223, in main() File...
已解决
Now, i want to use your trained network to get my keypoint person in our dataset .but i don't know what parts we should change?
Metadata
Owner
Metadata
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"