Jia Li

Is the performance you reported obtained on COCO2017 or COCO2014?

Hi everyone. I run the test model on COCO 2017 test-dev subset, only 0.52 AP was achieved which is far from the performance on COCO validation subset. What about your...

@tugumi911 Hi, may I ask you have you figured out the meaning of mapidx?

@lzyyzlwsldx Hi, on multi-scale or single-scale in your test?

@stefanopini Great! Dose 3fps include flip test?

@stefanopini Yes, I agree. Thank you for answering!

@BobDL I have tried the PAF-like (proposed by OpenPose) grouping method and pre-trained HRNet-w48 with Focal L2 loss based on this repo [Simple Pose](https://github.com/jialee93/Improved-Body-Parts) but only get 63 AP on...

@anewell Thank you for your kind replying! I'm not familiar with lua. Do you simply find the max response (regarded as a pixel value, let's denote it **P**) on the...

Hi, @xingyizhou So, the FPS metrics claimed in the original paper of CenterNet are obtained without batch testing, right?

@dong-x16 How do you evaluate on 2017 test dataset?