RON

RON copied to clipboard

@taokong @taokongcn 1. 在test.py文件和paper中指出： 　　`scores = np.tile(scores[:, 0], (imdb.num_classes, 1)).transpose() * scores` 　　相当于**给＂分类（21分类）得分＂乘以了＂其属于物体的概率＂**．为什么采用这种得分形式？为什么要进行这样的处理？ 2. 在anchor_target_layer.py和det_target_layer.py中， ``` 　　if len(fg_inds) > 0: num_bg = len(fg_inds) * (1.0 - cfg.TRAIN.FG_FRACTION) / (cfg.TRAIN.FG_FRACTION) else:...

foralliance

Train on other dataset?

10

First of all, thanks for sharing the great work! I am working on object detection on my own dataset but struggle a bit with some dimension parameter in .prototxt. Is...

TCforgood

Some questions about paper

8

Hey, much thanks for your great work. About the paper, I have some questions if you don't mind. 1. For each scale feature maps, there is a seperated classifier and...

DuinoDu

@taokong Hi, professor kong, recently I changed your RON project for training detector on KITTI, when I started to train, the output of pycharm run would stop after 100 iters,...

peyer

What is the normal train loss

1

hi, @taokong ,great work! I want to re-implement your experiment, and I have three small issues? 1. What is the normal train loss when the model converge well? mark: When...

zjuDebug