traveller59 / second.pytorch

SECOND for KITTI/NuScenes object detection

traveller59/second.pytorch Issues

pretrained second v1.6 for nuscenes
Updated 24 days ago
About gt_sampling
Updated a month ago1
有人试过把这个代码在windows上运行吗
Updated 8 months ago
Input only the desired scene
Updated 8 months ago
second.data
Updated 10 months ago2
Is the sparse library writed by the autuor?
Updated a year ago
I would like to know how many samples should be used for validation if 3517 samples are used for training?
Updated a year ago
ModuleNotFoundError: No module named 'second'
Closed 2 years ago1
About kitti viewer
Updated 2 years ago
train.py----->"TypeError: 'numpy.float64' object cannot be interpreted as an integer" and "TypeError: Object of type 'ndarray' is not JSON serializable "
Updated 2 years ago12
OSS License compatibility question
Updated 2 years ago
Source of torchplus package
Updated 2 years ago
Need suggestions on how to generate onnx files using this repo
Updated 2 years ago
Need tips on improving performance on custom dataset
Updated 2 years ago
Issues while using Kitti viewer.
Updated 2 years ago1
cannot import name 'non_max_suppression' from 'spconv.utils' even after successfully install spconv
Closed 3 years ago11
Summary name eval.kitti/official/Car/3d@0.70/1 is illegal; using eval.kitti/official/Car/3d_0.70/1 instead.
Updated 2 years ago
ValueError: file not exist: training/velodyne/000000.bin
Closed 4 years ago2
Train and evaluate without image, calib files
Updated 2 years ago16
Convert custom Lidar point cloud data to KITTI format
Closed 2 years ago1
second.pytorch 1.6.0 Alpha and spconv 2.1
Updated 2 years ago2
Kitti web viewer backend issue
Closed 2 years ago1
OSError: libtorch.so.1: cannot open shared object file: No such file or directory
Updated 3 years ago2
KeyError: 'annotations' when using nuscenes dataset
Closed 3 years ago3
How to start training from interrupted step
Closed 3 years ago1
KeyError: 'annotations' when using nuscenes dataset
Closed 3 years ago
Pointpillars
Updated 3 years ago
second SpMiddleFHDLite network how to convert to ONNX
Updated 3 years ago
Performance degradation on Pytorch 1.10 / Torchvision 0.11.0
Closed 3 years ago1
ERROR: The function received no value for the required argument: root_path Usage: create_data.py kitti_data_prep ROOT_PATH
Updated 3 years ago2
config files - need explanation (fhd vs largea vs lowa vs mhead vs mida), differences between config files, how to choose, etc.
Updated 3 years ago1
max_num_epchs and steps in config
Updated 3 years ago
No such directory /KITTI_DATASER_ROOT/training/ver..._reduce/xxxxxx.bin when trianing
Updated 3 years ago
Visualization of BEV
Updated 3 years ago
Why all AP are zero??
Updated 3 years ago2
Train with own dataset
Updated 3 years ago
sparse_shape = np.array(output_shape[1:4]) + [1, 0, 0]
Updated 3 years ago
Why not add the class of background in training?
Updated 3 years ago
Kitti viewer: Meaning of inputs
Updated 3 years ago
How to train dataset without camera data?
Updated 3 years ago1
Control Z axis for custom dataset
Updated 3 years ago1
RPN? RPNV2?
Updated 3 years ago
How to use Original VoxelNet
Updated 3 years ago
About `direction_offset`
Updated 4 years ago
Second Net? Point Pillar Net?
Updated 4 years ago7
I try to test second with my custom dataset
Updated 4 years ago6
It seems that `num_points_in_gt` is not correctly calculated in create_data.py
Updated 4 years ago
different result between kitti viewer and simple-inference
Updated 4 years ago1
Alternative dataset, changing point cloud range?
Updated 4 years ago
map_func float(info) for info in lines[6].split(' ')[1:13] IndexError: list index out of range
Updated 4 years ago1