V2AI / Det3D

World's first general purpose 3D object detection codebse.
https://arxiv.org/abs/1908.09492
Apache License 2.0
1.48k stars 299 forks source link

Error in Nuscenes data preprocess #85

Closed chanyn closed 4 years ago

chanyn commented 4 years ago

When I run pointpillars or cbgs on nuscenes, I met following mistakes: It happens at data preprocess, seems no point be sampled. If anyone meet this error before??

Original Traceback (most recent call last): File "/home/xuhang/anaconda3/envs/pointpillars/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/home/xuhang/anaconda3/envs/pointpillars/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/xuhang/anaconda3/envs/pointpillars/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/xuhang/green_zone_code/Det3D-master/det3d/datasets/nuscenes/nuscenes.py", line 177, in getitem return self.get_sensor_data(idx) File "/home/xuhang/green_zone_code/Det3D-master/det3d/datasets/nuscenes/nuscenes.py", line 172, in get_sensordata data, = self.pipeline(res, info) File "/home/xuhang/green_zone_code/Det3D-master/det3d/datasets/pipelines/compose.py", line 23, in call res, info = t(res, info) File "/home/xuhang/green_zone_code/Det3D-master/det3d/datasets/pipelines/preprocess.py", line 160, in call calib=calib, File "/home/xuhang/green_zone_code/Det3D-master/det3d/core/sampler/sample_ops.py", line 220, in sample_all "points": np.concatenate(s_points_list, axis=0), ValueError: need at least one array to concatenate

poodarchu commented 4 years ago

please insert a breakpoint to see what's going wrong at line 220.

XiaomuWang commented 4 years ago

Is it resolved? I also have this problem.

ConanCui commented 3 years ago

same problem, any solution?

Linkon87 commented 1 year ago

Has anyone solved it? I had the same problem