Error while running train_SemanticKITTI.py

[bymbhaskar]

Error log:

python train_SemanticKITTI.py
train_SemanticKITTI.py
Namespace(check_iter=4000, data_dir='data', grid_size=[480, 360, 32], model='polar', model_save_path='./SemKITTI_PolarSeg.pt', train_batch_size=2, val_batch_size=2)
0%| | 0/9565 [00:00<?, ?it/s]Traceback (most recent call last):
File "train_SemanticKITTI.py", line 197, in
main(args)
File "train_SemanticKITTI.py", line 107, in main
for i_iter,(,train_vox_label,train_grid,,train_pt_fea) in enumerate(train_dataset_loader):
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1111, in process_data
data.reraise()
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils.py", line 428, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.python train_SemanticKITTI.py
train_SemanticKITTI.py
Namespace(check_iter=4000, data_dir='data', grid_size=[480, 360, 32], model='polar', model_save_path='./SemKITTI_PolarSeg.pt', train_batch_size=2, val_batch_size=2)
0%| | 0/9565 [00:00<?, ?it/s]Traceback (most recent call last):
File "train_SemanticKITTI.py", line 197, in
main(args)
File "train_SemanticKITTI.py", line 107, in main
for i_iter,(,train_vox_label,train_grid,,train_pt_fea) in enumerate(train_dataset_loader):
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data
data.reraise()
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/home/lidar/bhaskar/polarenv/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 "/home/lidar/bhaskar/polarenv/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/lidar/bhaskar/PolarSeg/dataloader/dataset.py", line 238, in getitem
processed_label = nb_process_label(np.copy(processed_label),label_voxel_pair)
TypeError: expected dtype object, got 'numpy.dtype[uint8]'

0%| | 0/9565 [00:01<?, ?it/s]

Original Traceback (most recent call last):
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/home/lidar/bhaskar/polarenv/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 "/home/lidar/bhaskar/polarenv/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/lidar/bhaskar/PolarSeg/dataloader/dataset.py", line 238, in getitem
processed_label = nb_process_label(np.copy(processed_label),label_voxel_pair)
TypeError: expected dtype object, got 'numpy.dtype[uint8]'

0%| | 0/9565 [00:01<?, ?it/s]

[edwardzhou130]

Looks like a numba problem. Maybe switch to another numba version will fix it?

[bymbhaskar]

I downgraded the numba version to 0.39.0 (tried with 0.40.0). Now following error is coming:

python train_SemanticKITTI.py
Traceback (most recent call last):
File "train_SemanticKITTI.py", line 13, in
from network.ptBEV import ptBEVnet
File "/home/lidar/bhaskar/PolarSeg/network/ptBEV.py", line 155, in
@nb.jit('b1:',nopython=True,cache=True)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/decorators.py", line 189, in wrapper
**dispatcher_args)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/dispatcher.py", line 537, in init
self.targetctx = self.targetdescr.target_context
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/targets/registry.py", line 54, in target_context
return self._toplevel_target_context
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/utils.py", line 283, in get
res = instance.dict[self.name] = self.func(instance)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/targets/registry.py", line 38, in _toplevel_target_context
return cpu.CPUContext(self.typing_context)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/targets/base.py", line 247, in init
self.init()
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/targets/cpu.py", line 42, in init
self._internal_codegen = codegen.JITCPUCodegen("numba.exec")
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/targets/codegen.py", line 601, in init
self._init(self._llvm_module)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/numba/targets/codegen.py", line 610, in _init
tm = target.create_target_machine(**tm_options)
TypeError: create_target_machine() got an unexpected keyword argument 'jitdebug'

[edwardzhou130]

This error comes from the llvmlite package. You can try this fix first: rapidsai/cuml#2389.
If it does not work either, you can use the same version in my environment:

numpy 1.18.2
numba 0.39.0
llvmlite 0.24.0

[bymbhaskar]

I downgraded the llvmlite to

Now following error is coming:

python train_SemanticKITTI.py
train_SemanticKITTI.py
Namespace(check_iter=4000, data_dir='data', grid_size=[480, 360, 32], model='polar', model_save_path='./SemKITTI_PolarSeg.pt', train_batch_size=2, val_batch_size=2)
0%| | 0/9565 [00:00<?, ?it/s]Traceback (most recent call last):
File "train_SemanticKITTI.py", line 197, in
main(args)
File "train_SemanticKITTI.py", line 107, in main
for i_iter,(,train_vox_label,train_grid,,train_pt_fea) in enumerate(train_dataset_loader):
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data
data.reraise()
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/lidar/bhaskar/polarenv/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/home/lidar/bhaskar/polarenv/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 "/home/lidar/bhaskar/polarenv/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/lidar/bhaskar/PolarSeg/dataloader/dataset.py", line 239, in getitem
processed_label = nb_process_label(np.copy(processed_label),label_voxel_pair)
TypeError: expected dtype object, got 'numpy.dtype[uint8]'

0%|

[bymbhaskar]

I tried the version specified by you
numpy 1.18.2
numba 0.39.0
llvmlite 0.24.0

now its showing

python train_SemanticKITTI.py
Segmentation fault (core dumped)

[bymbhaskar]

I found that error is coming in importing that is :

from network.ptBEV import ptBEVnet

is this required if I want to work on KITTI only?

[edwardzhou130]

Yes, it is required. It's the feature encoder in our model.

[wfs123456]

Segmentation fault (core dumped)

Segmentation fault (core dumped),
Hello, how to fix this error, hope to your reply, thanks!

[Sylva-Lin]

Segmentation fault (core dumped)

Segmentation fault (core dumped), Hello, how to fix this error, hope to your reply, thanks!

Hello, I also met this problem, how to fix this error, hope to your reply, thanks!