pose-residual-network
pose-residual-network copied to clipboard
mkocabas
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (ECCV 2018)' paper
Given that the full network & training flow is not released by the authors, did anyone actually fully succeed in reproducing the results written in the paper (both the accuracy...
Hi, Thank you very much for your amazing job. I've used `python main.py` to train the model. How can i use the weights to infer my own images? I do...
i use the input heatmap for instance , crop from global heatmaps .resized to 1*K*36*56, when i vislized the output of the PRN,is not right
in your paper's abstract ,"the fastest real time system with ∼23 frames/sec". And we can find "Keypoint and person detections take 35 ms while PRN takes 2 ms per instance"...
I have my own dataset which similar to coco which includes keypoint and segmentation, so i was wondering if i can get the result which output keypoint and body segmentation
Start from Line [#140](https://github.com/mkocabas/pose-residual-network/blob/749cba142e9e2581bb10710067f9e6d8ebbb7c96/src/evaluate.py#L140) in evaluation.py, it seems to me that you are using the groundtruth keypoints to obtain you keypoint estimation, which should not happen when you evaluate your...
HI, How to evaluate the human segmentation part as paper described? just using last channel of (K+1) keypoints heatmap? How to extract the segmentation from PRN network. Any post-processing op...
@mkocabas Hey, Thanks for the interesting paper. I am reviewing the code and I am wondering if there is a function that can return directly the 2D joints. I need...
