voxel-r-cnn's People
Forkers
chaomath jlqzzz zaiwangli collector-m zdforient sktz-er feifeizuo wan1995 yeyang1021 niqbal996 nzennnaki hiyyg sidu28 amelia22974 wjc852456 arsalan311 yinggo minho-lidar-detection peryion 3d-object code-roamer masterthesis-2022 vehxianfish enginbozkurt gagnhai hzm8341 guoxs kklgf lecooo lianlau zhukevkesky glory01 douwenhao68 mengxingshifen1218 briandbl mraltria yanlingz seif7666 sebatztian wjmcidi arampuria19 whuhxbvoxel-r-cnn's Issues
Cannot import iou3d_nms_cuda
When I run the following command:
python -m pcdet.datasets.kitti.kitti_dataset create_kitti_infos tools/cfgs/dataset_configs/kitti_dataset.yaml
I get:
File "/usr/lib/python3.8/runpy.py", line 185, in _run_module_as_main mod_name, mod_spec, code = _get_module_details(mod_name, _Error) File "/usr/lib/python3.8/runpy.py", line 111, in _get_module_details __import__(pkg_name) File "/data/Voxel-R-CNN/pcdet/datasets/__init__.py", line 7, in <module> from .dataset import DatasetTemplate File "/data/Voxel-R-CNN/pcdet/datasets/dataset.py", line 8, in <module> from .augmentor.data_augmentor import DataAugmentor File "/data/Voxel-R-CNN/pcdet/datasets/augmentor/data_augmentor.py", line 6, in <module> from . import augmentor_utils, database_sampler File "/data/Voxel-R-CNN/pcdet/datasets/augmentor/database_sampler.py", line 5, in <module> from ...ops.iou3d_nms import iou3d_nms_utils File "/data/Voxel-R-CNN/pcdet/ops/iou3d_nms/iou3d_nms_utils.py", line 9, in <module> from . import iou3d_nms_cuda ImportError: cannot import name 'iou3d_nms_cuda' from 'pcdet.ops.iou3d_nms' (unknown location)
Not sure what's up? Are the paths wrong?
How do I convert the model to tensorRT
How to evaluate my own point cloud
Hello, I was hoping you could give me some guidance on the syntax for evaluating my own set of point clouds. I was not able to figure out how to do this through the files. Thank you!
Can you give some advice if I try voxel r-cnn on nuscenes dataset?
In the paper, I see that your work voxel-rcnn achieved good results on kitti and waymo dataset. Have you tried it on nuscenes datasets? I try this voxel rcnn on nuscenes based on pcdet,but the mAp is just 36%.
When i tested in kitti, i found that only the object in the front view would be detected
what should i config to change to detect the whole view?
I had a problem with numba in the last step of training
Traceback (most recent call last):
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/cudadrv/driver.py", line 2683, in add_ptx
ptxbuf, len(ptx), namebuf, 0, None, None)
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/cudadrv/driver.py", line 319, in safe_cuda_api_call
self._check_ctypes_error(fname, retcode)
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/cudadrv/driver.py", line 384, in _check_ctypes_error
raise CudaAPIError(retcode, msg)
numba.cuda.cudadrv.driver.CudaAPIError: [222] Call to cuLinkAddData results in UNKNOWN_CUDA_ERROR
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "train.py", line 198, in
main()
File "train.py", line 191, in main
dist_test=dist_train
File "/home/zy/program/3D_PD/code/Voxel-R-CNN-main/tools/test.py", line 121, in repeat_eval_ckpt
result_dir=cur_result_dir, save_to_file=args.save_to_file
File "/home/zy/program/3D_PD/code/Voxel-R-CNN-main/tools/eval_utils/eval_utils.py", line 124, in eval_one_epoch
output_path=final_output_dir
File "/home/zy/program/3D_PD/code/Voxel-R-CNN-main/pcdet/datasets/kitti/kitti_dataset.py", line 327, in evaluation
from .kitti_object_eval_python import eval as kitti_eval
File "/home/zy/program/3D_PD/code/Voxel-R-CNN-main/pcdet/datasets/kitti/kitti_object_eval_python/eval.py", line 6, in
from .rotate_iou import rotate_iou_gpu_eval
File "/home/zy/program/3D_PD/code/Voxel-R-CNN-main/pcdet/datasets/kitti/kitti_object_eval_python/rotate_iou.py", line 263, in
def rotate_iou_kernel_eval(N, K, dev_boxes, dev_query_boxes, dev_iou, criterion=-1):
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/decorators.py", line 99, in _jit
return Dispatcher(func, [func_or_sig], targetoptions=targetoptions)
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/compiler.py", line 805, in init
self.compile(sigs[0])
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/compiler.py", line 1093, in compile
kernel.bind()
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/compiler.py", line 466, in bind
self._codelibrary.get_cufunc()
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/codegen.py", line 201, in get_cufunc
cubin = self.get_cubin(cc=device.compute_capability)
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/codegen.py", line 174, in get_cubin
linker.add_ptx(ptx.encode())
File "/home/zy/anaconda3/envs/VoxelRcnn/lib/python3.7/site-packages/numba-0.55.0rc1-py3.7-linux-x86_64.egg/numba/cuda/cudadrv/driver.py", line 2685, in add_ptx
raise LinkerError("%s\n%s" % (e, self.error_log))
numba.cuda.cudadrv.driver.LinkerError: [222] Call to cuLinkAddData results in UNKNOWN_CUDA_ERROR
ptxas application ptx input, line 9; fatal : Unsupported .version 7.3; current version is '7.2'
How to reproduce the FPS as mentioned in the paper ?
Hi, I am trying to reproduce the FPS for the Voxel-RCNN using the retrained model but I don't see anything relevant metric in the test.py for that. I have also shared my work to reproduce the FPS on OpenPCDet github 1417. I would really appreciate it if I could get help on it. Thanks
What improvements would you look into?
Hi there,
Thanks for all your work -- on research and a clean repository! I was wondering what future directions or areas of improvement you might recommend for others to look into contribute to the work?
e.g. would you consider changes to feature extraction
Thanks and all the best!
cuda error
hi, when i run your train.py, it comes out an error:
2021-08-13 15:43:07,291 INFO Start training voxel_rcnn/voxel_rcnn_car(default)
epochs: 0%| | 0/80 [00:00<?, ?it/sError!: 0%| | 0/3741 [00:00<?, ?it/s]
Error!
epochs: 0%| | 0/80 [01:15<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 198, in
main()
File "train.py", line 170, in main
merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch
File "/data/mc_data/Voxel-R-CNN-main/tools/train_utils/train_utils.py", line 93, in train_model
dataloader_iter=dataloader_iter
File "/data/mc_data/Voxel-R-CNN-main/tools/train_utils/train_utils.py", line 38, in train_one_epoch
loss, tb_dict, disp_dict = model_func(model, batch)
File "/home/mc/Project/OpenPCDet/pcdet/models/init.py", line 42, in model_func
ret_dict, tb_dict, disp_dict = model(batch_dict)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 447, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/mc/Project/OpenPCDet/pcdet/models/detectors/voxel_rcnn.py", line 11, in forward
batch_dict = cur_module(batch_dict)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/mc/Project/OpenPCDet/pcdet/models/roi_heads/voxelrcnn_head.py", line 227, in forward
targets_dict = self.assign_targets(batch_dict)
File "/home/mc/Project/OpenPCDet/pcdet/models/roi_heads/roi_head_template.py", line 104, in assign_targets
targets_dict = self.proposal_target_layer.forward(batch_dict)
File "/home/mc/Project/OpenPCDet/pcdet/models/roi_heads/target_assigner/proposal_target_layer.py", line 33, in forward
batch_dict=batch_dict
File "/home/mc/Project/OpenPCDet/pcdet/models/roi_heads/target_assigner/proposal_target_layer.py", line 101, in sample_rois_for_rcnn
gt_boxes=cur_gt[:, 0:7], gt_labels=cur_gt[:, -1].long()
File "/home/mc/Project/OpenPCDet/pcdet/models/roi_heads/target_assigner/proposal_target_layer.py", line 223, in get_max_iou_with_same_class
iou3d = iou3d_nms_utils.boxes_iou3d_gpu(cur_roi, cur_gt) # (M, N)
File "/home/mc/Project/OpenPCDet/pcdet/ops/iou3d_nms/iou3d_nms_utils.py", line 71, in boxes_iou3d_gpu
overlaps_h = torch.clamp(min_of_max - max_of_min, min=0)
RuntimeError: CUDA error: invalid device function
Traceback (most recent call last):
File "/opt/anaconda3/envs/objfuse/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/distributed/launch.py", line 263, in
main()
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/distributed/launch.py", line 259, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/opt/anaconda3/envs/objfuse/bin/python', '-u', 'train.py', '--local_rank=0', '--launcher', 'pytorch', '--cfg_file', 'cfgs/voxel_rcnn/voxel_rcnn_car.yaml', '--epochs', '80', '--workers', '8']' died with <Signals.SIGSEGV: 11>.
i use pytorch1.4,cudatoolkit=10.1,gpu is 2080ti. canyou give me some advice?
Config file different from the one on openpcdet
How can I train model by transfer learning?
I want to train model using my own dataset.
But my dataset is so small, so I want to know how to do transfer learning with freezing backbone layer.
Is there any function to train network by transfer learning?
training environment
What is the minimum training environment requirement( the required gpus)?
Experimental setup issues
Hi,If I want to train three categories with voxel_rcnn, how should I set the parameters。
Pickle file errors
On Ubunut 18.04. I am a bit unsure as to why this might be happening-it happens when I run the train shell script:
Traceback (most recent call last): File "<string>", line 1, in <module> File "/usr/lib/python3.8/multiprocessing/spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "/usr/lib/python3.8/multiprocessing/spawn.py", line 126, in _main self = reduction.pickle.load(from_parent) _pickle.UnpicklingError: pickle data was truncated Traceback (most recent call last): File "<string>", line 1, in <module> File "/usr/lib/python3.8/multiprocessing/spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "/usr/lib/python3.8/multiprocessing/spawn.py", line 126, in _main self = reduction.pickle.load(from_parent) _pickle.UnpicklingError: pickle data was truncated
After this error shows up, I get a key error for road planes:
Original Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/data/Voxel-R-CNN/pcdet/datasets/kitti/kitti_dataset.py", line 380, in __getitem__ data_dict = self.prepare_data(data_dict=input_dict) File "/data/Voxel-R-CNN/pcdet/datasets/dataset.py", line 121, in prepare_data data_dict = self.data_augmentor.forward( File "/data/Voxel-R-CNN/pcdet/datasets/augmentor/data_augmentor.py", line 94, in forward data_dict = cur_augmentor(data_dict=data_dict) File "/data/Voxel-R-CNN/pcdet/datasets/augmentor/database_sampler.py", line 197, in __call__ data_dict = self.add_sampled_boxes_to_scene(data_dict, sampled_gt_boxes, total_valid_sampled_dict) File "/data/Voxel-R-CNN/pcdet/datasets/augmentor/database_sampler.py", line 125, in add_sampled_boxes_to_scene sampled_gt_boxes, data_dict['road_plane'], data_dict['calib'] KeyError: 'road_plane'
Debuging the backward method
I use Pycharm IDE. I add a breakpoint in backward function and wanted to debug the script , then I found the program did not stop at the breakpoint . I do not know why.
Then I set num_workers=0
,but it doesn't work for me.
I beg you can help me to solve this problem. Thank you!
eval result of models trained with voxel_rcnn_3classes.yaml
Hello, thanks for your great work. I have trained voxel-rcnn with voxel_rcnn_3class.yaml, but the result is worse than voxel_rcnn_car.yaml. Is that right? How can I get the result of pedestrain and cyclist in KITTI dataset? thanks!
results are as follows:
2022-03-07 20:27:15,298 INFO Car [email protected], 0.70, 0.70:
bbox AP:95.3898, 83.2715, 77.2035
bev AP:89.3690, 76.6368, 75.2530
3d AP:87.9943, 72.9119, 67.3161
aos AP:95.29, 82.68, 76.53
Car [email protected], 0.70, 0.70:
bbox AP:97.2515, 83.4524, 81.0170
bev AP:94.2792, 79.8192, 75.6973
3d AP:90.7316, 72.6871, 69.4763
aos AP:97.16, 82.88, 80.15
Car [email protected], 0.50, 0.50:
bbox AP:95.3898, 83.2715, 77.2035
bev AP:95.3354, 83.3392, 82.9096
3d AP:95.2646, 83.1027, 77.0240
aos AP:95.29, 82.68, 76.53
Car [email protected], 0.50, 0.50:
bbox AP:97.2515, 83.4524, 81.0170
bev AP:97.1493, 84.8501, 82.5885
3d AP:97.1129, 84.7085, 80.8528
aos AP:97.16, 82.88, 80.15
Pedestrian [email protected], 0.50, 0.50:
bbox AP:48.4417, 43.1507, 42.1027
bev AP:48.4228, 41.3880, 40.1097
3d AP:46.5401, 39.7380, 38.7178
aos AP:44.54, 39.19, 37.68
Pedestrian [email protected], 0.50, 0.50:
bbox AP:46.3712, 41.4821, 39.3516
bev AP:46.6629, 39.1686, 37.5176
3d AP:44.6500, 37.2929, 35.4425
aos AP:41.86, 36.81, 34.38
Pedestrian [email protected], 0.25, 0.25:
bbox AP:48.4417, 43.1507, 42.1027
bev AP:53.0485, 47.6899, 47.0767
3d AP:52.9010, 47.4667, 46.8729
aos AP:44.54, 39.19, 37.68
Pedestrian [email protected], 0.25, 0.25:
bbox AP:46.3712, 41.4821, 39.3516
bev AP:52.9300, 45.9471, 44.6889
3d AP:52.6937, 45.7476, 44.4331
aos AP:41.86, 36.81, 34.38
Cyclist [email protected], 0.50, 0.50:
bbox AP:86.7945, 74.1553, 72.5625
bev AP:85.1334, 70.5727, 66.6534
3d AP:85.0664, 67.6590, 65.3969
aos AP:85.57, 72.61, 70.92
Cyclist [email protected], 0.50, 0.50:
bbox AP:89.4240, 74.4265, 72.4647
bev AP:87.7896, 70.5118, 67.8602
3d AP:87.0270, 68.8757, 65.8546
aos AP:88.12, 72.82, 70.74
Cyclist [email protected], 0.25, 0.25:
bbox AP:86.7945, 74.1553, 72.5625
bev AP:85.1736, 70.7908, 68.8701
3d AP:85.1736, 70.7908, 68.8701
aos AP:85.57, 72.61, 70.92
Cyclist [email protected], 0.25, 0.25:
bbox AP:89.4240, 74.4265, 72.4647
bev AP:87.8156, 71.3646, 68.7342
3d AP:87.8156, 71.3646, 68.7342
aos AP:88.12, 72.82, 70.74
docker using
hi, i am confused about how to use a docker. what should i do after i docker pull...?
How to evaluate the performance of the model according to the segmentation distance on Kitti?
How to evaluate the performance of the model according to the segmentation distance on Kitti? Such as 0-30m,30-50,50-70.4.
Where should I change the evaluation code to control the evaluation metric ?
Config on waymo dataset
Thanks for your sharing. Can you supply the config of voxel r-cnn on waymo dataset?
pre-trained model for testing
Hi,
I can't find your pre-trained mode, I wish to use it for testing.
can you please share it?
thanks,
Ofer
trainning batch size
Thank you for your wonderful work. The paper you published is trained with batch_size16. But when I train on a single 2080Ti with batch_size =2, the performance is better than on four cards. So your batch_size =16 is trained on a single card or on multi-cards. And I submit the result to the Kitti test server, the moderate level is only 80.04 . It confused me for about two months. So can you give a solution? Thank you very much.
Best regards!
python train.py ......./voxel_rcnn_car.yaml --batch_size 4 --epochs 5 An error occurred。
The problem of evaluation in voxelrcnn
Hi,Recently, when I was training three classes of voxel-rcnn。The result of running locally is normal,but when running on the server, the accuracy of the pedestrian and cyclist categories is much worse than that of the local,The category of car is normal,The experimental parameter settings are exactly the same。How should i solve this problem,it bothered me for a long time,Hope to find help here!thanks
About the eval result
Hi @djiajunustc .Thank you for your great work!
I have trained your project about 120epoch. But the result was not so good as our article showed. I don't know what's the problem?
Car [email protected], 0.70, 0.70:
bbox AP:97.5955, 88.4117, 88.2141
bev AP:89.6285, 86.6193, 85.4555
3d AP:87.7399, 76.9524, 76.1327
aos AP:97.39, 88.01, 87.65
Car [email protected], 0.70, 0.70:
bbox AP:98.3861, 91.5014, 91.3330
bev AP:94.9682, 87.8349, 85.8327
3d AP:90.7695, 78.6636, 76.6187
aos AP:98.19, 91.05, 90.69
Car [email protected], 0.50, 0.50:
bbox AP:97.5955, 88.4117, 88.2141
bev AP:97.7538, 88.7638, 88.6693
3d AP:97.6798, 88.6881, 88.5662
aos AP:97.39, 88.01, 87.65
Car [email protected], 0.50, 0.50:
bbox AP:98.3861, 91.5014, 91.3330
bev AP:98.5041, 93.9677, 93.9661
3d AP:98.4636, 93.8064, 93.6006
aos AP:98.19, 91.05, 90.69
Pedestrian [email protected], 0.50, 0.50:
bbox AP:67.7471, 61.2331, 59.2942
bev AP:61.3480, 55.2211, 51.6408
3d AP:58.0767, 51.3151, 48.2123
aos AP:63.95, 56.94, 54.73
Pedestrian [email protected], 0.50, 0.50:
bbox AP:67.9662, 61.7473, 58.9460
bev AP:61.5746, 54.5980, 50.8662
3d AP:57.2521, 50.3834, 46.4734
aos AP:63.70, 56.80, 53.80
Pedestrian [email protected], 0.25, 0.25:
bbox AP:67.7471, 61.2331, 59.2942
bev AP:70.3663, 65.6778, 63.1834
3d AP:70.3604, 65.6465, 63.0975
aos AP:63.95, 56.94, 54.73
Pedestrian [email protected], 0.25, 0.25:
bbox AP:67.9662, 61.7473, 58.9460
bev AP:71.4780, 65.7675, 62.9850
3d AP:71.4710, 65.7332, 62.9239
aos AP:63.70, 56.80, 53.80
Cyclist [email protected], 0.50, 0.50:
bbox AP:91.2968, 75.3031, 73.5625
bev AP:84.3340, 70.1275, 67.9271
3d AP:82.7952, 67.5019, 63.0085
aos AP:89.38, 71.15, 69.25
Cyclist [email protected], 0.50, 0.50:
bbox AP:92.9363, 77.8973, 74.7406
bev AP:88.1583, 70.3173, 66.9044
3d AP:86.1416, 67.1941, 63.7919
aos AP:90.91, 73.02, 69.94
Cyclist [email protected], 0.25, 0.25:
bbox AP:91.2968, 75.3031, 73.5625
bev AP:89.5904, 72.3610, 70.6035
3d AP:89.5904, 72.3610, 70.6035
aos AP:89.38, 71.15, 69.25
Cyclist [email protected], 0.25, 0.25:
bbox AP:92.9363, 77.8973, 74.7406
bev AP:91.3753, 74.4753, 71.2521
3d AP:91.3753, 74.4753, 71.2521
aos AP:90.91, 73.02, 69.94
Multi-gpu training error: semaphore_tracker
Thank you for your contribution. When I used 4 GPUs to train, I encountered the following error:
UserWarning: semaphore_tracker: There appear to be 65 leaked semaphores to clean up at shutdown
My environment is rtx 2080ti 11G*4
code of voxel roi pooling
hi, i can't find your code about voxel roi pooling, can you tell me where is it?
Split training set
Hi, ‘we randomly select 80% samples from the training point clouds for training, and use the remaining 20% samples for validation' is mentioned in your paper, can you share these files? Thanks very much
AP@recall 40 vs AP@recall 11
Where should I change the evaluation code to control the evaluation metric ?
keyerror:'road_plane'
hi, when i run your sh scripts/train_voxel_rcnn.sh,it occurs this error:
2021-08-13 09:57:11,365 INFO Start training voxel_rcnn/voxel_rcnn_car(default)
epochs: 0%| | 0/80 [01:05<?, ?it/s]
Traceback (most recent call last): | 0/3741 [00:00<?, ?it/s]
File "train.py", line 198, in
main()
File "train.py", line 170, in main
merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch
File "/data/mc_data/Voxel-R-CNN-main/tools/train_utils/train_utils.py", line 93, in train_model
dataloader_iter=dataloader_iter
File "/data/mc_data/Voxel-R-CNN-main/tools/train_utils/train_utils.py", line 19, in train_one_epoch
batch = next(dataloader_iter)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/_utils.py", line 394, in reraise
raise self.exc_type(msg)
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/mc/Project/OpenPCDet/pcdet/datasets/kitti/kitti_dataset.py", line 424, in getitem
data_dict = self.prepare_data(data_dict=input_dict)
File "/home/mc/Project/OpenPCDet/pcdet/datasets/dataset.py", line 129, in prepare_data
'gt_boxes_mask': gt_boxes_mask
File "/home/mc/Project/OpenPCDet/pcdet/datasets/augmentor/data_augmentor.py", line 112, in forward
data_dict = cur_augmentor(data_dict=data_dict)
File "/home/mc/Project/OpenPCDet/pcdet/datasets/augmentor/database_sampler.py", line 197, in call
data_dict = self.add_sampled_boxes_to_scene(data_dict, sampled_gt_boxes, total_valid_sampled_dict)
File "/home/mc/Project/OpenPCDet/pcdet/datasets/augmentor/database_sampler.py", line 125, in add_sampled_boxes_to_scene
sampled_gt_boxes, data_dict['road_plane'], data_dict['calib']
KeyError: 'road_plane'
Traceback (most recent call last):
File "/opt/anaconda3/envs/objfuse/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/distributed/launch.py", line 263, in
main()
File "/opt/anaconda3/envs/objfuse/lib/python3.7/site-packages/torch/distributed/launch.py", line 259, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/opt/anaconda3/envs/objfuse/bin/python', '-u', 'train.py', '--local_rank=0', '--launcher', 'pytorch', '--cfg_file', 'cfgs/voxel_rcnn/voxel_rcnn_car.yaml', '--epochs', '80', '--workers', '8']' died with <Signals.SIGSEGV: 11>.
do you have any advices?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.