Open shi-yan opened 4 years ago
The images in the paper seem to indicate that the limb width is precisely labeled?
However, looking at the code (function putVecMaps):
https://github.com/CMU-Perceptual-Computing-Lab/caffe_train/blob/master/src/caffe/cpm_data_transformer.cpp
thre seems to be the limb width, and it's hardcoded to 1. isn't 1 too small for limb width? why was one chosen as the width?
The images in the paper seem to indicate that the limb width is precisely labeled?
However, looking at the code (function putVecMaps):
https://github.com/CMU-Perceptual-Computing-Lab/caffe_train/blob/master/src/caffe/cpm_data_transformer.cpp
thre seems to be the limb width, and it's hardcoded to 1. isn't 1 too small for limb width? why was one chosen as the width?