ED-Pose
ED-Pose copied to clipboard
[ICLR 2023] Official implementation of the paper "Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation "
is there the code to run the model on custom images or video?
Can you please make device=cpu version for macbook users
如果没有target标签数据,想单独跑前向推理怎么操作
The model and dataset is complex, i just want to run the model on some specific images, can you provide an inference scripts to get the human skeleton result.
What tools should I use and what should I pay attention to?
https://github.com/IDEA-Research/ED-Pose/blob/f44b3f220d5671f07805d1e5bbb9acc2afac275c/models/edpose/edpose.py#L419 Should this be an AND statement because when targets are None (inference time), this code fails ? And can you explain dn_number and dn_training ?