loveSnowBest
loveSnowBest
Any plans for Range-View 3D detection models? such as RCD, RangeDet, RSN(CVPR2021), ToThePoint(CVPR2021).
> > Any plans for Range-View 3D detection models? such as RCD, RangeDet, RSN(CVPR2021), ToThePoint(CVPR2021). > > We are actually planning for it. Do you have any recommendations? I think...
Hi, I am interested in this work. However, I can not align the performance on CenterPoint. Could you provide some advice? Perhaps about whether I should change the yaw angle...
@HuangJunJie2017 In this codebase https://github.com/WangYueFt/detr3d.
[UPDATE] This error only occurs using torch>=1.6, where torch.cuda.amp is used for fp16 training. I've tested it can be successfully run with torch==1.5.0, where mmcv-style mix-precision training is adopted here.
Another question about dynamic voxelization with FP16. I am trying to reimplement dv with SECOND based on mix-precision training. However, I found that the scatter(perhaps c++ implementation) only supports float...
可以看下文章里面的ablation~
maybe you can add a if-else clause here to decide whether to save it or not :) https://github.com/TuSimple/simpledet/blob/bcccd77d5c763901a90afe4bb503849bb7ee4dbc/core/detection_module.py#L185
You may handle with ignore annnotations when creating .roidb file by modifying `create_coco_roidb.py` or `create_voc_roidb.py`.
You can write code to convert this log.txt with regex to json format so that one can directly plot loss(or other metrics) through json format files.