Bi-box_Regression icon indicating copy to clipboard operation
Bi-box_Regression copied to clipboard

Pytorch implementation of Bi-box Regression for Pedestrian Detection and Occlusion Estimation (ECCV2018)

Results 8 Bi-box_Regression issues
Sort by recently updated
recently updated
newest added

请问train.txt和val.txt文件格式是怎么样的?

hi~the result of this project can be presented in the command?i have very bad result but i dont konw why

![image](https://user-images.githubusercontent.com/23293902/53930766-7bbd7d00-40cd-11e9-8ee0-8a84facc6be2.png) 这个结果和Repulsion loss一样都变差了,也是奇怪的很!希望作者贴出他的实验结果!

I want to use a Caltech Pedestrian dataset for training, but for the transformation of the data set don't correspond with code format and don't know you is how to...

Hi, I just found the mAP is very low when testing on Caltech Dataset, it is around 0.03 The code is optimizer = optim.Adam(retinanet.parameters(), lr=1e-5) scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=3, verbose=True)...

Is there any python code or instruction to test already exist pre-train model? Thank you~