handong1587

> This is the updated version of this repo: https://github.com/tyagi-iiitv/PointPillars. Have you ever evaluates the model after training? Can you give a results on KTTI (valset)?

> Working on it will update it as soon as it's done. This code has some missing components that I'm trying to complete. Okay thanks! Looking forward to it.

@YYfangzi I think the maximum iterations is set to be 2500K. You can check it here: https://github.com/CharlesShang/FastMaskRCNN/blob/fe9c0dc3ec487aa032f57cadb68b5514b285ed46/libs/configs/config_v1.py#L70 Up to now I have trained about 180K, still far from be completed.

@boycebai I just use the github code, didn't modify any code lines. What errors did you encounter?

@hulaifeng http://www.ee.cuhk.edu.hk/~xgwang/PS/dataset.html "Dataset is available upon request (sli [at] ee.cuhk.edu.hk)." You can contact him for request for the dataset.

Actually I have already done some translatings based on @manutdzou 's Chinese version README. Perhaps I can submit a PR on this?

I think this project is not well docmented and arranged because it contains so many dependencies that would probably confuse users.

I cannot get any correct detection results using this demo, it seems that it just produced some random bboxes. I was running this demo on Ubuntu 14.04. Does anyone have...

@zhanglaplace Hi, I was running this demo on Ubuntu 14.04. Actually I once ported py-faster-rcnn to Windows, but got similar results. I am very confused why this happen :-(

@zhanglaplace After made some modifications, I think I corrected the defects, now it can detect object correctly. One of the modificaiton I made is the 'class_num' in faster_rcnn.hpp: `const int...