RTM3D

RTM3D copied to clipboard

Hello Mr. Peixuan Li. First of all, congratulations about the Time3D paper accepted at CVPR 2022. I also read that paper recently and could learn many things about monocular based...

cijj

can the KM3D model be converted to tensorrt model and run in xavier？

2

如题。

likegogogo

the code cannot run on RTX2080TI

2

i dont know why, and i tried many combinations of ubuntu version+cuda and cudnn, all failed... i only have 2080TI ...

Light--

根据dim, keypoints, orientation等计算depth的这部分模块，部署推理时该怎么实现呢？

1

 训练时depth的计算目测是耦合在Position_loss 中的。 但部署推理时，不需要算loss，只需要算出depth即可。 请问下，怎么推理实现怎么搞比较好呢？ 我看depth计算这一块挺复杂的。 直接用c++手写？还是把Position_loss 的forward部分封装成torch script 独立运行? 有建议吗？

likegogogo

how to solve it? i have no idea Traceback (most recent call last): File "./src/main.py", line 111, in main(opt) File "./src/main.py", line 73, in main log_dict_train, _ = trainer.train(epoch, train_loader)...

fgqile

Pytorch cuda error assertion failed

1

Thank you for your great work! I was trying out your work in a newer version of pytorch (1.5.1 to be exact). I have updated the operations of iou3d and...

Owen-Liuyuxuan

编译失败

3

DCN和iou3d都无法编译成功，把pytorch换成1.7，DCN也换成适合1.7的版本后，可以编译，但是iou3d还是无法编译。 但是iou3d不编译也能正常运行，请问iou3d在哪起作用呢？ 另外可以更新一下版本吗，pytorch1.0有点低了...

SEUvictor

python ./src/faster.py --demo ./kitti_format/kitti/val.txt --data_dir ./kitti_format --calib_dir ./kitti_format/data/kitti/calib/ --load_model ./kitti_format/exp/KM3D_res18/Model_rtm3d_epoch_300.pth --gpus 0 --arch res_18

3

Fix size testing. training chunk_sizes: [32] The output will be saved to ./kitti_format/exp/default heads {'hm': 3, 'wh': 2, 'hps': 18, 'rot': 8, 'dim': 3, 'prob': 1, 'reg': 2, 'hm_hp': 9,...

kwl11556

About the robustness and portability of monocular 3D models

14

Monocular 3D depends on camera parameters. If you change a different camera or installation method, the original DataSet training model will not work. So how can you solve this difference

WSTao

Hello, Apperaciate your excellent work. I found a semi-supervised training process mentioned in the paper. Do you have any plan to release the code?

TommyAnqi