second.pytorch icon indicating copy to clipboard operation
second.pytorch copied to clipboard

SECOND for KITTI/NuScenes object detection

Results 121 second.pytorch issues
Sort by recently updated
recently updated
newest added

Anyone has a similar problem? Been looking for a solution but seems like none of the tickets are closed ![nms](https://user-images.githubusercontent.com/55087987/107977372-f69bac00-6ff5-11eb-871f-7aa0f118975e.PNG)

Hi, I am working with my own custom LiDAR data. However, the filter algorithm delete all label data that I have: middle_class_name PointPillarsScatter num_trainable parameters: 66 {'Pedestrian': 5} [-1] load...

When I run the command**:python ./pytorch/train.py train --config_path=./configs/car.fhd.config --model_dir=/path/to/model_dir** An error occurred。How can I solve this problem? ---------------------------------------------------------------- Traceback (most recent call last): File "./pytorch/train.py", line 16, in from second.builder...

Hello! I am currently trying to implement SECOND with PointPillars support. I successfully installed spconv, but when I try to `python create_data.py kitti_data_prep --data_path=KITTI_DATASET_ROOT`, I get the following error: $...

Hello, Thanks for this great job. I would like to make a comment on PointPillars repo forked from this source repo. In pointpillars I see it is used point pillar...

Because car.lite.config use SpMiddleFHDLite network, how can I convert SpMiddleFHDLite to ONNX, I try to convert but failed, ---------------------------------------------------------------------------------------------------------- elif ndim == 3: /home/cxhpc/zhouzhou/project_envs/P16_second_169/lib/python3.6/site-packages/spconv/ops.py:116: TracerWarning: Converting a tensor to a...

I ran into an issue similar to others but I don't know how to fix it. I'm using sever PC (ip: xxx.xxx.xxx.xxx) I wanna show the trained results with my...

Hi, I might find a bug here, https://github.com/traveller59/second.pytorch/blob/3aba19c9688274f75ebb5e576f65cfe54773c021/second/data/nuscenes_dataset.py#L185 Why you concatenate timestamp channel instead of reflectance?

Hi can someone help me understanding the different evaluations? There is one "[email protected], 0.70, 0.70" and one "[email protected], 0.50, 0.50" ans also a "Car coco..." And which of the contents...

`ERROR: The function received no value for the required argument: root_path Usage: create_data.py kitti_data_prep ROOT_PATH `