can i add labeling function by your trained model?

2014gaokao / pedestrian-attribute-recognition-with-GCN

Pytorch implementation of pedestrian attribute recognition with graph convolutional network

78 stars 17 forks source link

Open BinchaoPeng opened 4 years ago

BinchaoPeng commented 4 years ago

标注的行人属性包括性别、头发长度和上下身衣着、鞋子及包的种类和颜色，并提供图像中行人头部、上身、下身、脚、帽子、包位置的标注。

2014gaokao commented 4 years ago

这些可以在transform_rap2.py里添加的

BinchaoPeng commented 4 years ago

就是说，你的模型是有返回属性坐标的是吗？

2014gaokao commented 4 years ago

哦，没有，不好意思。

BinchaoPeng commented 4 years ago

那确定不了位置吧，只有有位置才能画框确定哪里是头，哪里是鞋之类的，是吗

2014gaokao commented 4 years ago

是吖

abhigoku10 commented 2 years ago

@BinchaoPeng did get try to get the location of the attributes of a given person @2014gaokao is there any way to obtain the attributes location ?