second.pytorch

second.pytorch copied to clipboard

Parameter configuration，Can I set x<0

9

Hello, inside the code implementation, there is a parameter that is the point cloud data range, x_min=0, that is, only the target in front of the car is detected. Can...

WSTao

Hi, I have some questions about voxel generation of KITTI. For example, if the the shape of input point clouds is (63082,5) and the voxel size is (0.05 , 0.05,...

Ben940315

Ben940315

How to retrain on my own 16velodyne data

3

Hi, you did a very great job, but when I use your pre-trained model to predict my own 16-vlp data, including retrained kitti data, the result is not good. My...

khanln

pointpillar multiclass object detection

3

Hi there, Is there any config file for multiclass object detection? why the config files of pointpillar are different in following two repos: https://github.com/nutonomy/second.pytorch https://github.com/traveller59/second.pytorch which one is more up-to-date?

kargarisaac

Training on multi-class detection? Config file...

4

Could you please upload sample.config file to train simultaneously for multiclass detection

chowkamlee81

Could not inference using PointPillars model

7

### System information (version) - Ubuntu 16.04 - CUDA 10.0 - PyTorch 1.2.0 - TorchVision 0.4.0 - traveller59/second.pytorch https://github.com/traveller59/second.pytorch/commit/3aba19c9688274f75ebb5e576f65cfe54773c021 - traveller59/spconv https://github.com/traveller59/spconv/commit/6e727bcd17e7d1b72367f664a53f3789f061510e ### Detailed description I trained KITTI dataset and...

atinfinity

how's the performance on 16 beams lidar data?

21

Does there any performance demonstration videos or gif to show detection result on 16 beams data?

lucasjinreal

There is no results show when I test on the testing data?

3

I change the eval_input_reader 'kitti_info_path' with kitti_infos_test.pkl ,then run 'python ./pytorch/train.py evaluate...'，the kitti Viewer can't show any detection results. Why ?

yujianyi

Is anyone evaluate successfully on your custom dataset?

2

I evaluate my custom dataset using `python ./pytorch/train.py evaluate --config_path=./configs/car.fhd.config --model_dir=/path/to/model_dir --measure_time=True --batch_size=1 ` After running, I visualize the results but there are little cars are detected, the 3D bboxes...

KevinDu1