-
when executing
python ./pytorch/train.py train --config_path=/home/ubuntu/LIDAR/Traveller59/second/configs/pointpillars/car/xyres_16.config --model_dir=../model_pytorch,
iam getting nan values b…
-
Hello, I am trying to convert a ONNX file from ONNX v4 to ONNX v3.
I am using this piece of code [here](https://github.com/onnx/onnx/blob/master/docs/PythonAPIOverview.md#converting-version-of-an-o…
-
command:
python tools/deploy.py ./configs/mmdet3d/voxel-detection/voxel-detection_tensorrt_dynamic-kitti.py ../mmdetection3d/configs/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py ..…
-
runtime log:
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from PointPillars
[ RUN ] PointPillars.__build_model__
unknown fi…
-
hello, when I tried to train ssd3d using `python tools/train.py /configs/3dssd/3dssd_4x4_kitti-3d-car.py`, it gives me the CUDA kernel failed: invalid device function. However, I tried using another c…
-
Hi @hova88 , thank you so much for sharing such a nice work.
When I follow your instruction to train a model, I got an error:
`Traceback (most recent call last):
File "/home/avep/rongxuan/Lidard…
-
Is there any plan to support the model deployment of 3D target detection? When deploying monoflex, we encountered many pytorch operations that tensorrt does not support, such as edge_ indices. view(b,…
-
I noticed that there exsit only **single-head** results for **Kitti** dataset and **multi-head** results for **Nuscenes** dataset.
And compared to **Second.git** which clearly assgined **big head**…
-
Hi @speshowBUAA,
Thanks for creating this repo to convert pointpillars pth file to onnx file. I was wondering if you could provide an example of the c++ inference engine code as well. Or, could you…
jb892 updated
2 years ago
-
Hi, I use pointpillars to train on WaymoD5-3class. Performance on Car and Pedestrian is normal while Cyclist has large gap compared to the results you provide.
The following is the results I get:
…