Instructions To Reproduce the Issue:

1. what changes you made (git diff) or what code you wrote using the Ego velocity in every annotations, the other config are same.

# convert velo from global to lidar
for i in range(len(ref_boxes)):
    velo = np.array([*velocity[i], 0.0])
    velo = velo @ np.linalg.inv(e2g_r_mat).T @ np.linalg.inv(
          l2e_r_mat).T
    velocity[i] = velo[:2]
    velocity = velocity.reshape(-1,2)

2. what exact command you run:

python3 -m torch.distributed.launch --nproc_per_node=8 ./tools/train.py examples/cbgs/configs/nusc_all_vfev3_spmiddleresnetfhd_rpn2_mghead_syncbn.py --work_dir=/home/ubuntu/Documents/Det3D/trained_model

3. what you observed:

mAP: 0.3719
mATE: 0.3724
mASE: 0.2661
mAOE: 0.9296
mAVE: 1.3655
mAAE: 0.2684
NDS: 0.4023
Eval time: 140.1s

Per-class results:
Object Class	AP	ATE	ASE	AOE	AVE	AAE
car	0.721	0.219	0.158	0.841	1.116	0.230
truck	0.371	0.426	0.198	0.640	1.155	0.307
bus	0.500	0.439	0.174	1.223	2.171	0.431
trailer	0.213	0.687	0.219	0.670	1.371	0.184
construction_vehicle	0.058	0.798	0.481	1.370	0.157	0.372
pedestrian	0.653	0.165	0.287	1.350	0.869	0.439
motorcycle	0.242	0.223	0.243	1.107	3.192	0.153
bicycle	0.043	0.199	0.264	1.111	0.894	0.031
traffic_cone	0.449	0.170	0.348	nan	nan	nan
barrier	0.470	0.398	0.289	0.056	nan	nan
Evaluation nusc: Nusc v1.0-trainval Evaluation
car Nusc dist [email protected], 1.0, 2.0, 4.0
59.48, 71.97, 77.40, 79.65 mean AP: 0.7212472062431424
truck Nusc dist [email protected], 1.0, 2.0, 4.0
18.48, 36.29, 44.83, 48.91 mean AP: 0.3712787143771077
construction_vehicle Nusc dist [email protected], 1.0, 2.0, 4.0
0.00, 2.09, 8.06, 12.96 mean AP: 0.05777510817362395
bus Nusc dist [email protected], 1.0, 2.0, 4.0
23.60, 47.30, 62.94, 66.32 mean AP: 0.5003920838518946
trailer Nusc dist [email protected], 1.0, 2.0, 4.0
1.66, 13.24, 29.62, 40.49 mean AP: 0.21251682647224052
barrier Nusc dist [email protected], 1.0, 2.0, 4.0
26.14, 46.78, 55.95, 59.13 mean AP: 0.4700045657239055
motorcycle Nusc dist [email protected], 1.0, 2.0, 4.0
20.39, 24.74, 25.62, 26.05 mean AP: 0.24202605811125658
bicycle Nusc dist [email protected], 1.0, 2.0, 4.0
3.93, 4.27, 4.35, 4.58 mean AP: 0.04280152387228541
pedestrian Nusc dist [email protected], 1.0, 2.0, 4.0
62.12, 64.40, 66.13, 68.36 mean AP: 0.6525328516852104
traffic_cone Nusc dist [email protected], 1.0, 2.0, 4.0
40.81, 43.40, 45.49, 49.80 mean AP: 0.44874109465427564

Unable to reproduce the results in model zoo.

Expected behavior:

the score NDS don't reach the number in released paper, and the AVE number is abnormal large than others, this reproduced result even worse than pointpillars. Is the loss compute func exist some problems leading to this result?

Hi @poodarchu Thanks for your great code! I trained pointpillar with default config, while the performance is as follow, which is similar to the results post by @s-ryosky in #18 .

For the category of car, the published mAP of moderate level on kitti 3D test dataset is 74.99, while my trained one is only 75.66 on kitti val dataset. It seems cannot exceed the published one. As far as I konw, other researchers could achieve about 77 on val with pointpillar, I wonder if there exists any problem in the configs? and can you pubulish your results? Thanks a lot!

Comparing to the current master branch, I made two changes in order to fix the NaN training loss.

The first change is described in #46 .

The second change is to add what's below before line 193 in losses.py

# FIX NaN TARGETS 
target_tensor = torch.where(
    torch.isnan(target_tensor), prediction_tensor, target_tensor
)

Besides, I set

norm_cfg = dict(type='SyncBN', eps=1e-3, momentum=0.01)

in examples/cbgs/configs/nusc_all_vfev3_spmiddleresnetfhd_rpn2_mghead_syncbn.py and

torch.backends.cudnn.benchmark = True

in tools/train.py.

Here are my results on the validation set after training 20 epochs:

car Nusc dist [email protected], 1.0, 2.0, 4.0
59.25, 71.87, 77.22, 79.63 mean AP: 0.7199402759604012
truck Nusc dist [email protected], 1.0, 2.0, 4.0
17.96, 35.01, 43.00, 47.15 mean AP: 0.357782470829584
construction_vehicle Nusc dist [email protected], 1.0, 2.0, 4.0
0.00, 1.28, 6.75, 13.37 mean AP: 0.05348830261303094
bus Nusc dist [email protected], 1.0, 2.0, 4.0
23.87, 48.49, 62.98, 66.32 mean AP: 0.5041451034213309
trailer Nusc dist [email protected], 1.0, 2.0, 4.0
1.94, 14.27, 30.88, 42.11 mean AP: 0.22300031478924093
barrier Nusc dist [email protected], 1.0, 2.0, 4.0
28.06, 48.97, 57.80, 60.27 mean AP: 0.4877375663669212
motorcycle Nusc dist [email protected], 1.0, 2.0, 4.0
24.97, 29.29, 30.38, 30.99 mean AP: 0.28906646690838084
bicycle Nusc dist [email protected], 1.0, 2.0, 4.0
6.20, 7.36, 7.98, 8.53 mean AP: 0.07516058303100348
pedestrian Nusc dist [email protected], 1.0, 2.0, 4.0
62.82, 64.73, 66.83, 69.03 mean AP: 0.658543997130018
traffic_cone Nusc dist [email protected], 1.0, 2.0, 4.0
42.10, 44.31, 46.23, 50.65 mean AP: 0.4582346501948114

Overall the mean AP is 38.2, which is much lower than what's reported.

Can someone point me to what I might have missed? Thanks!

there are two config file in the dir Det3D/examples/cbgs/configs lyft*.py and nusc*.py when I load the model with the file nusc ,the the model unable get right result and as fllow

The model and loaded state dict do not match exactly

unexpected key in source state_dict: model, optimizer, iteration, epoch

missing keys in source state_dict: backbone.middle_conv.8.bn1.running_var, backbone.middle_conv.3.bn2.running_mean, neck.blocks.0.17.bias, backbone.middle_conv.19.bn2.running_mean, backbone.middle_conv.1.running_mean, bbox_head.tasks.2.conv_dir.weight, backbone.middle_conv.4.conv2.bias, backbone.middle_conv.4.conv1.bias, backbone.middle_conv.11.running_mean, backbone.middle_conv.13.conv1.bias, backbone.middle_conv.4.conv2.weight, backbone.middle_conv.1.weight, neck.blocks.0.13.weight, bbox_head.tasks.2.conv_dir.bias, backbone.middle_conv.14.bn1.weight, backbone.middle_conv.5.weight, backbone.middle_conv.6.running_var, backbone.middle_conv.8.conv2.bias, neck.blocks.0.5.weight, backbone.middle_conv.14.bn2.running_mean, backbone.middle_conv.1.bias, backbone.middle_conv.9.bn1.bias, backbone.middle_conv.14.bn2.running_var, backbone.middle_conv.18.bn2.weight, backbone.middle_conv.8.bn1.bias, bbox_head.tasks.3.conv_cls.bias, backbone.middle_conv.16.running_var, backbone.middle_conv.18.bn1.weight, backbone.middle_conv.18.conv1.bias, neck.blocks.1.17.bias, backbone.middle_conv.6.weight, bbox_head.tasks.3.conv_dir.weight, backbone.middle_conv.11.weight, backbone.middle_conv.8.conv1.weight, neck.blocks.0.2.running_mean, backbone.middle_conv.9.conv1.weight, bbox_head.tasks.4.conv_cls.weight, neck.deblocks.0.1.weight, neck.blocks.1.2.running_var, neck.blocks.0.8.bias, backbone.middle_conv.13.bn1.bias, backbone.middle_conv.4.bn2.weight, neck.deblocks.0.1.running_var, backbone.middle_conv.19.bn2.weight, bbox_head.tasks.3.conv_dir.bias, backbone.middle_conv.14.bn2.weight, neck.blocks.1.14.weight, neck.blocks.1.11.weight, backbone.middle_conv.9.conv2.weight, backbone.middle_conv.18.bn2.running_mean, neck.blocks.0.5.running_mean, backbone.middle_conv.3.bn1.bias, neck.deblocks.0.1.running_mean, bbox_head.tasks.1.conv_dir.weight, bbox_head.tasks.5.conv_box.bias, bbox_head.tasks.0.conv_box.weight, backbone.middle_conv.3.bn1.running_mean, neck.blocks.1.8.weight, backbone.middle_conv.4.bn2.bias, neck.blocks.1.8.running_var, neck.blocks.1.2.bias, bbox_head.tasks.0.conv_box.bias, backbone.middle_conv.4.bn1.running_mean, backbone.middle_conv.10.weight, neck.blocks.1.17.running_var, neck.deblocks.1.1.bias, backbone.middle_conv.3.bn1.weight, backbone.middle_conv.9.bn2.weight, bbox_head.tasks.5.conv_dir.bias, backbone.middle_conv.8.bn1.weight, neck.deblocks.1.0.weight, backbone.middle_conv.4.bn2.running_mean, neck.blocks.1.5.bias, backbone.middle_conv.13.bn1.running_var, bbox_head.tasks.4.conv_box.weight, backbone.middle_conv.8.bn2.running_var, neck.blocks.1.2.weight, backbone.middle_conv.11.bias, neck.blocks.1.5.running_var, backbone.middle_conv.19.conv1.bias, backbone.middle_conv.1.running_var, bbox_head.tasks.2.conv_cls.weight, neck.blocks.0.2.weight, backbone.middle_conv.9.bn2.bias, backbone.middle_conv.9.bn1.running_mean, backbone.middle_conv.21.weight, neck.blocks.1.17.running_mean, backbone.middle_conv.8.bn1.running_mean, backbone.middle_conv.13.bn1.weight, bbox_head.tasks.2.conv_cls.bias, backbone.middle_conv.14.bn1.bias, neck.blocks.0.2.bias, neck.blocks.1.16.weight, bbox_head.tasks.5.conv_dir.weight, neck.blocks.1.10.weight, bbox_head.tasks.0.conv_cls.weight, neck.blocks.1.5.weight, bbox_head.tasks.3.conv_box.bias, backbone.middle_conv.14.conv1.weight, backbone.middle_conv.19.bn1.weight, neck.blocks.0.17.running_mean, bbox_head.tasks.4.conv_box.bias, neck.blocks.0.11.bias, neck.blocks.0.17.weight, backbone.middle_conv.3.bn2.running_var, bbox_head.tasks.3.conv_cls.weight, backbone.middle_conv.0.weight, backbone.middle_conv.18.conv1.weight, backbone.middle_conv.18.bn2.running_var, backbone.middle_conv.9.conv1.bias, neck.deblocks.1.1.weight, bbox_head.tasks.1.conv_cls.bias, bbox_head.tasks.3.conv_box.weight, backbone.middle_conv.4.bn2.running_var, neck.blocks.0.5.running_var, backbone.middle_conv.9.conv2.bias, backbone.middle_conv.4.bn1.weight, neck.blocks.0.5.bias, neck.blocks.1.1.weight, backbone.middle_conv.21.bias, backbone.middle_conv.14.conv1.bias, backbone.middle_conv.8.conv1.bias, backbone.middle_conv.6.running_mean, backbone.middle_conv.13.conv1.weight, backbone.middle_conv.9.bn2.running_var, neck.blocks.1.5.running_mean, neck.blocks.0.11.weight, bbox_head.tasks.4.conv_dir.weight, neck.blocks.1.14.running_var, neck.deblocks.0.1.bias, bbox_head.tasks.2.conv_box.bias, backbone.middle_conv.4.conv1.weight, backbone.middle_conv.19.bn2.bias, neck.blocks.0.11.running_mean, neck.blocks.0.11.running_var, backbone.middle_conv.8.bn2.bias, backbone.middle_conv.19.bn2.running_var, backbone.middle_conv.13.bn2.bias, backbone.middle_conv.8.conv2.weight, neck.blocks.1.14.running_mean, backbone.middle_conv.3.bn2.bias, backbone.middle_conv.18.bn2.bias, backbone.middle_conv.18.bn1.running_var, bbox_head.tasks.0.conv_dir.bias, neck.blocks.1.4.weight, backbone.middle_conv.14.conv2.bias, neck.blocks.0.16.weight, neck.blocks.0.8.weight, backbone.middle_conv.13.bn2.weight, neck.blocks.0.14.running_var, neck.deblocks.0.0.weight, neck.deblocks.1.1.running_var, backbone.middle_conv.13.conv2.bias, neck.blocks.1.11.bias, backbone.middle_conv.13.conv2.weight, neck.blocks.0.17.running_var, backbone.middle_conv.19.bn1.running_mean, neck.blocks.0.14.bias, backbone.middle_conv.3.conv1.bias, backbone.middle_conv.18.bn1.bias, neck.blocks.0.8.running_var, backbone.middle_conv.13.bn1.running_mean, bbox_head.tasks.4.conv_cls.bias, neck.blocks.1.17.weight, neck.blocks.1.14.bias, backbone.middle_conv.14.bn2.bias, bbox_head.tasks.2.conv_box.weight, backbone.middle_conv.18.conv2.weight, backbone.middle_conv.9.bn1.running_var, backbone.middle_conv.3.bn2.weight, bbox_head.tasks.1.conv_box.weight, bbox_head.tasks.0.conv_cls.bias, backbone.middle_conv.19.conv1.weight, backbone.middle_conv.8.bn2.weight, neck.blocks.1.8.bias, bbox_head.tasks.0.conv_dir.weight, bbox_head.tasks.1.conv_cls.weight, bbox_head.tasks.1.conv_box.bias, bbox_head.tasks.4.conv_dir.bias, bbox_head.tasks.5.conv_cls.bias, neck.blocks.1.7.weight, backbone.middle_conv.19.conv2.weight, backbone.middle_conv.3.conv2.weight, neck.blocks.1.2.running_mean, backbone.middle_conv.14.conv2.weight, backbone.middle_conv.20.weight, neck.blocks.1.11.running_var, backbone.middle_conv.16.running_mean, backbone.middle_conv.16.bias, neck.blocks.0.1.weight, backbone.middle_conv.18.conv2.bias, backbone.middle_conv.6.bias, neck.blocks.1.11.running_mean, backbone.middle_conv.21.running_var, neck.blocks.0.2.running_var, backbone.middle_conv.4.bn1.bias, backbone.middle_conv.8.bn2.running_mean, backbone.middle_conv.14.bn1.running_mean, backbone.middle_conv.11.running_var, neck.blocks.0.4.weight, neck.blocks.0.14.weight, bbox_head.tasks.5.conv_box.weight, backbone.middle_conv.21.running_mean, neck.deblocks.1.1.running_mean, backbone.middle_conv.19.bn1.running_var, neck.blocks.0.14.running_mean, backbone.middle_conv.16.weight, backbone.middle_conv.9.bn2.running_mean, backbone.middle_conv.3.conv1.weight, backbone.middle_conv.4.bn1.running_var, backbone.middle_conv.3.bn1.running_var, neck.blocks.1.8.running_mean, bbox_head.tasks.1.conv_dir.bias, backbone.middle_conv.9.bn1.weight, backbone.middle_conv.18.bn1.running_mean, backbone.middle_conv.19.bn1.bias, backbone.middle_conv.14.bn1.running_var, backbone.middle_conv.19.conv2.bias, bbox_head.tasks.5.conv_cls.weight, backbone.middle_conv.3.conv2.bias, backbone.middle_conv.13.bn2.running_mean, backbone.middle_conv.15.weight, neck.blocks.1.13.weight, backbone.middle_conv.13.bn2.running_var, neck.blocks.0.10.weight, neck.blocks.0.8.running_mean, neck.blocks.0.7.weight

Try to train this CBGS in single GPU, after modified some params, occur this error:

it looks like when trained with Nuscenes dataset, setting the Range [-50.4, -50.4, 50.4, 50,4], and voxels_size[0.1, 0.1], it will generate [1008, 1008] array -> 1008 * 1008 * 2 = 2032128 anchors per class, but the box_preds output is [1, 126, 126, 18] per class -> 126 * 126 * 2 = 31752.

def add_sin_difference(boxes1, boxes2):
    rad_pred_encoding = torch.sin(boxes1[..., -1:]) * torch.cos(boxes2[..., -1:])
    rad_tg_encoding = torch.cos(boxes1[..., -1:]) * torch.sin(boxes2[..., -1:])
    boxes1 = torch.cat([boxes1[..., :-1], rad_pred_encoding], dim=-1)
    boxes2 = torch.cat([boxes2[..., :-1], rad_tg_encoding], dim=-1)
    return boxes1, boxes2

Hopefully for any advice @a157801 @poodarchu

Kindly help all values are naN . Iam using single GPU

2020-01-07 17:22:53,040 - INFO - task : ['car'], loss: nan, cls_pos_loss: nan, cls_neg_loss: nan, dir_loss_reduced: nan, cls_loss_reduced: nan, loc_loss_reduced: nan, loc_loss_elem: ['nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan'], num_pos: 26.6600, num_neg: 31688.8400 2020-01-07 17:22:53,040 - INFO - task : ['truck', 'construction_vehicle'], loss: nan, cls_pos_loss: nan, cls_neg_loss: nan, dir_loss_reduced: nan, cls_loss_reduced: nan, loc_loss_reduced: nan, loc_loss_elem: ['nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan'], num_pos: 40.4800, num_neg: 63408.1400 2020-01-07 17:22:53,040 - INFO - task : ['bus', 'trailer'], loss: nan, cls_pos_loss: nan, cls_neg_loss: nan, dir_loss_reduced: nan, cls_loss_reduced: nan, loc_loss_reduced: nan, loc_loss_elem: ['nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan'], num_pos: 58.1800, num_neg: 63362.3000 2020-01-07 17:22:53,040 - INFO - task : ['barrier'], loss: nan, cls_pos_loss: nan, cls_neg_loss: nan, dir_loss_reduced: nan, cls_loss_reduced: nan, loc_loss_reduced: nan, loc_loss_elem: ['nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan'], num_pos: 7.8600, num_neg: 31742.0200 2020-01-07 17:22:53,040 - INFO - task : ['motorcycle', 'bicycle'], loss: nan, cls_pos_loss: nan, cls_neg_loss: nan, dir_loss_reduced: nan, cls_loss_reduced: nan, loc_loss_reduced: nan, loc_loss_elem: ['nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan'], num_pos: 11.8800, num_neg: 63486.6800 2020-01-07 17:22:53,040 - INFO - task : ['pedestrian', 'traffic_cone'], loss: nan, cls_pos_loss: nan, cls_neg_loss: nan, dir_loss_reduced: nan, cls_loss_reduced: nan, loc_loss_reduced: nan, loc_loss_elem: ['nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan', 'nan'], num_pos: 13.6200, num_neg: 63489.2200

How to solve this problem? FileNotFoundError: [Errno 2] No such file or directory: '/media/jsu/F81CA38A1CA3430C/nuScences/NUSCENES_TRAINVAL_DATASET_ROOT/infos_train_10sweeps_withvelo.pkl'

I ran this command ‘python tools/create_data.py nuscenes_data_prep --root_path='/media/jsu/F81CA38A1CA3430C/nuScences/NUSCENES_TRAINVAL_DATASET_ROOT/' --version="v1.0-trainval" --nsweeps=10’。 The error is as follows： FileNotFoundError: [Errno 2] No such file or directory: '/media/jsu/F81CA38A1CA3430C/nuScences/NUSCENES_TRAINVAL_DATASET_ROOT/infos_train_10sweeps_withvelo.pkl'

when I use 4 gpus to train a model, the training process always wait something suddenly. Do nothing, and take up the gpu resources. When I forcibly stop the process, It shows:

File "/opt/conda/lib/python3.6/runpy.py" , line 193, in _run_module_as_main
  "__main__", mod_spec)
File "/opt/conda/lib/python3.6/runpy.py" , line 85, in _run_code
  exec(code, run_globals)
File "/opt/conda/lib/python3.6/site-packages/torch/distributed/launch.py" , line 235, in <module>
  main()
File "/opt/conda/lib/python3.6/site-packages/torch/distributed/launch.py" , line 228, in main
  process.wait()
File "/opt/conda/lib/python3.6/subprocess.py" , line 1477, in wait
  (pid, sts) = self._try_wait(0)
File "/opt/conda/lib/python3.6/subprocess.py", line 1424, in _try_wait
  (pid, sts) = os.waitpid(self.pid, wait_flags)

Even after half a day, the process do nothing but wait. Can you explain this? How to continue the training process or aviod the endless waiting?

Sometimes my program is terminated by "CUDA error: an illegal memory acess was encountered" in the training process. I used official code and default config setting, only changing the data_root and work_dir, the bug occured in the training in both cases of single gpu and distributed multiple gpus. The picture below shows the error infomation:

Sometimes the training on a single gpu could also be terminated as below:

While this problems seems can be ignored in multi-gpu training:

The envrionment of my server includes:

- OS: Ubuntu 16.04
- Python:  3.7.3
- CUDA: 10.1
- CUDNN: 7.4.1
- pytorch: 1.3.1
- gcc: 5.5.0
- cmake: 3.16.0
- nvidia driver version: 418.40.04
- gpu: 8 TITAN Xp

Really weird! How can i solve the problems as they usually occurs? Could anyone provide some information on these problems? Thanks a lot！

Does it normal that several numbawarning happens when I train PointPillars on the nuscenes mini? whereas it produce the final result. what I observed:

2020-02-26 18:17:27,109 - INFO - Start running, host: root@d4488fc27a4d, work_dir: /workspace/det3d_requirement/Det3D/data/Outputs/Det3D_Outputs/PointPillars_lucky_jupyter_20200226-181359
2020-02-26 18:17:27,110 - INFO - workflow: [('train', 1), ('val', 1)], max: 20 epochs
/workspace/det3d_requirement/Det3D/det3d/core/sampler/preprocess.py:464: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  points[i : i + 1, :3] = points[i : i + 1, :3] @ rot_mat_T[j]
/workspace/det3d_requirement/Det3D/det3d/core/sampler/preprocess.py:464: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  points[i : i + 1, :3] = points[i : i + 1, :3] @ rot_mat_T[j]
/workspace/det3d_requirement/Det3D/det3d/core/sampler/preprocess.py:464: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  points[i : i + 1, :3] = points[i : i + 1, :3] @ rot_mat_T[j]
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/npydecl.py:958: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  warnings.warn(NumbaPerformanceWarning(msg))
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/npydecl.py:958: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  warnings.warn(NumbaPerformanceWarning(msg))
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/npydecl.py:958: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  warnings.warn(NumbaPerformanceWarning(msg))
/workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py:279: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: Invalid use of Function(<built-in function getitem>) with argument(s) of type(s): (array(float32, 3d, C), Tuple(slice<a:b>, list(int64), slice<a:b>))
 * parameterized
In definition 0:
    All templates rejected with literals.
In definition 1:
    All templates rejected without literals.
In definition 2:
    All templates rejected with literals.
In definition 3:
    All templates rejected without literals.
In definition 4:
    All templates rejected with literals.
In definition 5:
    All templates rejected without literals.
In definition 6:
    All templates rejected with literals.
In definition 7:
    All templates rejected without literals.
In definition 8:
    All templates rejected with literals.
In definition 9:
    All templates rejected without literals.
In definition 10:
    All templates rejected with literals.
In definition 11:
    All templates rejected without literals.
In definition 12:
    TypeError: unsupported array index type list(int64) in Tuple(slice<a:b>, list(int64), slice<a:b>)
    raised from /opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/arraydecl.py:71
In definition 13:
    TypeError: unsupported array index type list(int64) in Tuple(slice<a:b>, list(int64), slice<a:b>)
    raised from /opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/arraydecl.py:71
This error is usually caused by passing an argument of a type that is unsupported by the named function.
[1] During: typing of intrinsic-call at /workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py (298)

File "det3d/core/bbox/geometry.py", line 298:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
                :,
                [num_points_of_polygon - 1] + list(range(num_points_of_polygon - 1)),
                ^

  @numba.jit
/workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py:279: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: Invalid use of Function(<built-in function getitem>) with argument(s) of type(s): (array(float32, 3d, C), Tuple(slice<a:b>, list(int64), slice<a:b>))
 * parameterized
In definition 0:
    All templates rejected with literals.
In definition 1:
    All templates rejected without literals.
In definition 2:
    All templates rejected with literals.
In definition 3:
    All templates rejected without literals.
In definition 4:
    All templates rejected with literals.
In definition 5:
    All templates rejected without literals.
In definition 6:
    All templates rejected with literals.
In definition 7:
    All templates rejected without literals.
In definition 8:
    All templates rejected with literals.
In definition 9:
    All templates rejected without literals.
In definition 10:
    All templates rejected with literals.
In definition 11:
    All templates rejected without literals.
In definition 12:
    TypeError: unsupported array index type list(int64) in Tuple(slice<a:b>, list(int64), slice<a:b>)
    raised from /opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/arraydecl.py:71
In definition 13:
    TypeError: unsupported array index type list(int64) in Tuple(slice<a:b>, list(int64), slice<a:b>)
    raised from /opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/arraydecl.py:71
This error is usually caused by passing an argument of a type that is unsupported by the named function.
[1] During: typing of intrinsic-call at /workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py (298)

File "det3d/core/bbox/geometry.py", line 298:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
                :,
                [num_points_of_polygon - 1] + list(range(num_points_of_polygon - 1)),
                ^

  @numba.jit
/workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py:279: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: Invalid use of Function(<built-in function getitem>) with argument(s) of type(s): (array(float32, 3d, C), Tuple(slice<a:b>, list(int64), slice<a:b>))
 * parameterized
In definition 0:
    All templates rejected with literals.
In definition 1:
    All templates rejected without literals.
In definition 2:
    All templates rejected with literals.
In definition 3:
    All templates rejected without literals.
In definition 4:
    All templates rejected with literals.
In definition 5:
    All templates rejected without literals.
In definition 6:
    All templates rejected with literals.
In definition 7:
    All templates rejected without literals.
In definition 8:
    All templates rejected with literals.
In definition 9:
    All templates rejected without literals.
In definition 10:
    All templates rejected with literals.
In definition 11:
    All templates rejected without literals.
In definition 12:
    TypeError: unsupported array index type list(int64) in Tuple(slice<a:b>, list(int64), slice<a:b>)
    raised from /opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/arraydecl.py:71
In definition 13:
    TypeError: unsupported array index type list(int64) in Tuple(slice<a:b>, list(int64), slice<a:b>)
    raised from /opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/typing/arraydecl.py:71
This error is usually caused by passing an argument of a type that is unsupported by the named function.
[1] During: typing of intrinsic-call at /workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py (298)

File "det3d/core/bbox/geometry.py", line 298:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
                :,
                [num_points_of_polygon - 1] + list(range(num_points_of_polygon - 1)),
                ^

  @numba.jit
2020-02-26 18:17:36,478 - INFO - finding looplift candidates
2020-02-26 18:17:36,478 - INFO - finding looplift candidates
2020-02-26 18:17:36,478 - INFO - finding looplift candidates
/workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py:279: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: cannot determine Numba type of <class 'numba.dispatcher.LiftedLoop'>

File "det3d/core/bbox/geometry.py", line 315:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    cross = 0.0
    for i in range(num_points):
    ^

  @numba.jit
/workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py:279: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: cannot determine Numba type of <class 'numba.dispatcher.LiftedLoop'>

File "det3d/core/bbox/geometry.py", line 315:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    cross = 0.0
    for i in range(num_points):
    ^

  @numba.jit
/workspace/det3d_requirement/Det3D/det3d/core/bbox/geometry.py:279: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: cannot determine Numba type of <class 'numba.dispatcher.LiftedLoop'>

File "det3d/core/bbox/geometry.py", line 315:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    cross = 0.0
    for i in range(num_points):
    ^

  @numba.jit
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "det3d/core/bbox/geometry.py", line 290:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "det3d/core/bbox/geometry.py", line 290:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "det3d/core/bbox/geometry.py", line 290:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit http://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "det3d/core/bbox/geometry.py", line 290:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit http://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "det3d/core/bbox/geometry.py", line 290:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/opt/conda/lib/python3.6/site-packages/numba-0.48.0-py3.6-linux-x86_64.egg/numba/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit http://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "det3d/core/bbox/geometry.py", line 290:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
2020-02-26 18:17:43,102 - INFO - Epoch [1/20][5/318]	lr: 0.00010, eta: 5:38:43, time: 3.198, data_time: 2.711, transfer_time: 0.027, forward_time: 0.171, loss_parse_time: 0.001 memory: 2501, 
2020-02-26 18:17:43,102 - INFO - task : ['car'], loss: 485.3806, cls_pos_loss: 0.0385, cls_neg_loss: 240.4097, dir_loss_reduced: 0.8125, cls_loss_reduced: 480.8579, loc_loss_reduced: 4.3603, loc_loss_elem: ['0.2031', '0.1620', '0.6211', '0.2591', '0.1530', '0.2292', '0.8962', '1.4495', '0.3871'], num_pos: 23.0000, num_neg: 19952.0000
2020-02-26 18:17:43,102 - INFO - task : ['truck', 'construction_vehicle'], loss: 1176.6788, cls_pos_loss: 550.3410, cls_neg_loss: 311.2071, dir_loss_reduced: 0.6776, cls_loss_reduced: 1172.7551, loc_loss_reduced: 3.7882, loc_loss_elem: ['0.3187', '0.2664', '0.5612', '0.3263', '0.5586', '0.3248', '0.5465', '0.5400', '0.3458'], num_pos: 24.4000, num_neg: 39932.0000
2020-02-26 18:17:43,102 - INFO - task : ['bus', 'trailer'], loss: 396.4121, cls_pos_loss: 179.8583, cls_neg_loss: 106.0010, dir_loss_reduced: 0.7220, cls_loss_reduced: 391.8602, loc_loss_reduced: 4.4075, loc_loss_elem: ['0.3016', '0.1981', '0.3558', '0.4285', '1.6443', '0.2680', '0.4065', '0.3449', '0.4598'], num_pos: 72.8000, num_neg: 39916.2000
2020-02-26 18:17:43,102 - INFO - task : ['barrier'], loss: 1901.0528, cls_pos_loss: 0.0422, cls_neg_loss: 948.9933, dir_loss_reduced: 0.7667, cls_loss_reduced: 1898.0289, loc_loss_reduced: 2.8706, loc_loss_elem: ['0.1731', '0.1723', '0.6855', '0.2647', '0.2434', '0.3112', '0.2356', '0.2740', '0.5107'], num_pos: 14.2000, num_neg: 19984.2000
2020-02-26 18:17:43,102 - INFO - task : ['motorcycle', 'bicycle'], loss: 2253.0825, cls_pos_loss: 1050.6371, cls_neg_loss: 598.2773, dir_loss_reduced: 0.7013, cls_loss_reduced: 2247.1917, loc_loss_reduced: 5.7506, loc_loss_elem: ['0.2719', '0.3527', '0.6125', '0.3074', '0.3881', '0.2621', '1.1131', '1.9434', '0.4993'], num_pos: 8.2000, num_neg: 39990.4000
2020-02-26 18:17:43,103 - INFO - task : ['pedestrian', 'traffic_cone'], loss: 2289.1748, cls_pos_loss: 1212.1962, cls_neg_loss: 536.2855, dir_loss_reduced: 0.7453, cls_loss_reduced: 2284.7673, loc_loss_reduced: 4.2585, loc_loss_elem: ['0.3888', '0.3689', '0.6287', '0.3924', '0.3640', '0.3956', '0.4584', '0.6679', '0.5938'], num_pos: 19.6000, num_neg: 39978.6000

I don't know what the normal result should be. Could you give a tutorial please? Maybe a jupyter notebook? Thank you very much.

Error when I install the nuscenes-devkit. The detail error is : error in nuscenes-zbj setup command: "values of 'package_data' dict" must be a list of strings (got '*.json')

Hello, I'm trying to get the SSD repo (https://github.com/Vegeta2020/SE-SSD) working which depends on yours but has some slightly different dependency requirements. I've set up a system from scratch several times trying to Install Det3D but keep running into issues and I'm not sure how to debug from here. These are the instructions I'm using to setup the environment.

Install and Update Ubuntu 18.04 (On Windows can use Rufus to create a bootable flashdrive) Software Updater Restart

Install Development Tools Code (Optional) https://code.visualstudio.com/download sudo dpkg -i xxx.deb Git sudo apt --yes install git CMake sudo snap install cmake --classic Conda https://docs.conda.io/projects/conda/en/latest/user-guide/install/linux.html bash Miniconda3-py39_4.12.0-Linux-x86_64.sh conda update conda

Install Graphics Driver sudo ubuntu-drivers autoinstall sudo shutdown -r now nvidia-smi

Create Virtual Environment (pycocotools did not install on Python 3.6.5) git clone https://github.com/Vegeta2020/SE-SSD.git && cd SE-SSD conda create --yes --name SE-SSD python==3.7 conda activate SE-SSD conda install --yes pytorch==1.5.0 torchvision==0.6.0 cudatoolkit=10.1 cudnn -c pytorch sudo add-apt-repository ppa:graphics-drivers/ppa sudo apt-get update conda install --yes cuda -c nvidia pip install -r requirements.txt

Install nuscenes-devkit pip install nuscenes-devkit

Install ifp-sample git clone https://github.com/jackd/ifp-sample.git pip install -e ifp-sample

Install spconv git clone https://github.com/poodarchu/spconv --recursive && cd spconv sudo apt-get install libboost-all-dev conda install libboost python setup.py bdist_wheel

At this point I get the output in the attached file, seems related to boost but I'm not sure. I've searched through the issues and it seems like others may be experiencing similar problems although I didn't see any descriptions on how to reproduce them so hopefully many of them can be addressed here. Cheers.

output.txt

In file included from det3d/ops/pointnet2/src/interpolate.cpp:7: det3d/ops/pointnet2/src/interpolate.cpp: In function ‘std::vectorat::Tensor three_nn(at::Tensor, at::Tensor)’: det3d/ops/pointnet2/src/utils.h:17:5: error: ‘TORCH_CHECK’ was not declared in this scope

pytorch version 1.1 python 3.6 cuda 11.4

refactoring code with Assign Multiple Targets which is more pythonic, concise, readable and efficient;how do think this change which has practical value？

Hi, when i was using your codebase, i came across such error:

 File "/root/11/centerpoint/det3d/torchie/utils/config.py", line 95, in fromfile
    import torchie
ModuleNotFoundError: No module named 'torchie'

could you give me some ideas to fix it? thanks! :)

I run : ./tools/scripts/train.sh train1 I get error: /spconv/src/spconv/indice.cu 125 cuda execution failed with error 2

My PC have only 1 GPU NVIDIA GeForce RTX 2080 SUPER - 8GB My software : CUDA Version 10.0.130 cudnn : 7603 pytorch : 1.3.0 spconv : 1.0 Cmake: cmake version 3.21.3 ninjia: 1.9.0 Python 3.6.8

I installed without docker or with docker , I got the same error /spconv/src/spconv/indice.cu 125 cuda execution failed with error 2 DO you have idea to resolve error above ? Thank you !