mc171819

> We trained the AdaBins[https://github.com/shariqfarooq123/AdaBins] using sparse depth maps generated by point clouds as ground truth. Since we focus on the 3d detection in our paper, the depth estimation and...

> i also have the same problem and the same question. why does everyone not tell where to do the setting. did you solve this?

> Hi @mc171819 , > > This error hasn't occurred to me. > I suggest you run the code with the docker image I provide. hi， i tried using the...

hi, i wonder how the train_dataset is obtained. whatever change i make in build_dataloader in pcdet/dataset/__init__, or kitti/processor/data_processor it doesn't work, even if i make a bug. can you tell...

> > So why use velocity head in you model > > It is only for tracking. It won't improve detection. > > > Can these models work when handling...

> > So why use velocity head in you model > > It is only for tracking. It won't improve detection. > > > Can these models work when handling...

> > So why use velocity head in you model > > It is only for tracking. It won't improve detection. > > > Can these models work when handling...

> Hi, I wanted to use the SIDE_LEFT and SIDE_RIGHT Lidar range images and get the poincloud from them seperately. However, the tfrecord data I tested displays range image output...

> you should not change anything in the centerpoint repo. > > We generate the detection file using the standard pipeline and computed this range breakdown by hacking into the...

I can't get into verbosity in netTensorRT.cpp and can't output Setting verbosity to:XXX