UniAD

UniAD copied to clipboard

I use the script 'uni_dist_train.sh' and try to train the stage1(track and map) model, but I encounter the error of 'OUT OF MEMORY'. I use four 3090 GPUs, the total...

stevenk12

For some reasons, the process fail when I run ./tools/uniad_dist_eval.sh ./projects/configs/stage2_e2e/base_e2e.py ./ckpts/uniad_base_e2e.pth 1 It fail when it is trying to evaluate on class bus, giving me a TypeError: can only...

BenLJM

Error with command: "pip install -v -e ."

1

I have followed the instruction written in docs/INSTALL.md. "step a ~ f" were processed successfully, except that I use cuda 11.3 and conduct "step b" with following command: ```shell conda...

heesungsung

Question: Reference point update strategy

1

Great work, congratulations on receiving the best paper award! I have a question about the reference point update strategy. ``` velo = output_coords[-1, 0, :, -2:] # [num_query, 3] if...

serend1p1ty

How to test the model on other datasets?

1

Thank you for your awesome work! I would like to take some pictures to test the model. Besides six images taken from cam_front_left, cam_front, cam_front_right, cam_back_right, cam_back, cam_back_left, what else...

181860153

RuntimeError: cusolver error: CUSOLVER_STATUS_INTERNAL_ERROR, when calling `cusolverDnCreate(handle)`

3

Exception has occurred: RuntimeError cusolver error: CUSOLVER_STATUS_INTERNAL_ERROR, when calling `cusolverDnCreate(handle)` File "/workspaces/UniAD-main/projects/mmdet3d_plugin/uniad/detectors/uniad_track.py", line 270, in velo_update g2l_r = torch.linalg.inv(l2g_r2).type(torch.float) File "/workspaces/UniAD-main/projects/mmdet3d_plugin/uniad/detectors/uniad_track.py", line 643, in _forward_single_frame_inference ref_pts = self.velo_update( File "/workspaces/UniAD-main/projects/mmdet3d_plugin/uniad/detectors/uniad_track.py",...

86kkd

Thanks for your work! It seems that the scene_level_offset_embed is used to represent the tranj. position, thus when the rotation transform is performed, which coordinate system is it in? Meanwhile,...

panpp-git

Dataloader worker killed with runtime error.

4

Hello, While training stage to network, im seeing the following error. Is anyone seeing the same error? Traceback (most recent call last): File "./tools/train.py", line 256, in main() File "./tools/train.py",...

vgudapati

Thank your for your work. when I read the code and the paper, I find out that there is some differences between the figure 5 in the paper with the...

ilzkl1991

Can I use single_gpu_test in the test.py file to generate result.pkl? I tried, but the GPU RAM usage will exceed 48G, unlike custom_multi_gpu_test which will be controlled at around 8G...

Alex-fishred