Frustum-Pointpillars icon indicating copy to clipboard operation
Frustum-Pointpillars copied to clipboard

Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection using RGB Camera and LiDAR

Results 10 Frustum-Pointpillars issues
Sort by recently updated
recently updated
newest added

I see the terminal output IOU threshold like '[email protected] 0.5 0.5'、 '[email protected] 0.7 0.7' and '[email protected] 0.25 0.25' ,but the kitti official eval tool only has'[email protected] 0.5 0.5' for car...

Why is the gauss function in \second\data\preprocess.py commented out? Doesn't the paper write the gauss function mask to improve performance? # def gauss_func(x0, y0, h, w, xy): # prob =...

ubuntu@VM-0-11-ubuntu:~/Frustum-Pointpillars/second$ python ./pytorch/train.py evaluate --config_path=./configs/pointpillars/car/xyres_16.proto --model_dir=./model middle_class_name PointPillarsScatter Restoring parameters from model/voxelnet-29503.tckpt remain number of infos: 7518 Generate output labels... Traceback (most recent call last): File "./pytorch/train.py", line 771, in...

Hello I'm trying to reproduce your results of paper in pedestrian detection. but the following results don't get to performance in your paper python: 3.7.3 pytorch: 1.4.0 GPU: TITAN Xp...

Does anyone know why? And when I doing this, it will have some warnings for numba, like this File "core/geometry.py", line 148: def points_in_convex_polygon_jit(points, polygon, clockwise=True): # first convert polygon...

Hi! I try to conduct the training. However, the training is interrupted because of the missing "kitti_val.tfrecord" in eval_input_reader. Can you provide the script for generating this file?