错误：
Traceback (most recent call last):
File "/home/gaoithe/project/python/code/CenterPoint/./tools/dist_test.py", line 415, in <module>
main()
File "/home/gaoithe/project/python/code/CenterPoint/./tools/dist_test.py", line 294, in main
print(next(iter(train_loader)))
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 634, in __next__
data = self._next_data()
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1346, in _next_data
return self._process_data(data)
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1372, in _process_data
data.reraise()
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/torch/_utils.py", line 644, in reraise
raise exception
numba.core.errors.TypingError: Caught TypingError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/gaoithe/project/python/code/CenterPoint/det3d/datasets/nuscenes/nuscenes.py", line 190, in __getitem__
return self.get_sensor_data(idx)
File "/home/gaoithe/project/python/code/CenterPoint/det3d/datasets/nuscenes/nuscenes.py", line 185, in get_sensor_data
data, _ = self.pipeline(res, info)
File "/home/gaoithe/project/python/code/CenterPoint/det3d/datasets/pipelines/compose.py", line 25, in __call__
res, info = t(res, info)
File "/home/gaoithe/project/python/code/CenterPoint/det3d/datasets/pipelines/preprocess.py", line 187, in __call__
mask = prep.filter_gt_box_outside_range(gt_dict["gt_boxes"], bv_range)
File "/home/gaoithe/project/python/code/CenterPoint/det3d/core/sampler/preprocess.py", line 121, in filter_gt_box_outside_range
ret = points_in_convex_polygon_jit(gt_boxes_bv.reshape(-1, 2), bounding_box)
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/numba/core/dispatcher.py", line 468, in _compile_for_args
error_rewrite(e, 'typing')
File "/home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/numba/core/dispatcher.py", line 409, in error_rewrite
raise e.with_traceback(None)
numba.core.errors.TypingError: Failed in nopython mode pipeline (step: nopython frontend)
No implementation of function Function(<built-in function getitem>) found for signature:
>>> getitem(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))
There are 22 candidate implementations:
- Of which 20 did not match due to:
Overload of function 'getitem': File: <numerous>: Line N/A.
With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
No match.
- Of which 2 did not match due to:
Overload in function 'GetItemBuffer.generic': File: numba/core/typing/arraydecl.py: Line 209.
With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
Rejected as the implementation raised a specific error:
NumbaTypeError: Unsupported array index type list(int64)<iv=None> in Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>)
raised from /home/gaoithe/.conda/envs/centerpoint/lib/python3.9/site-packages/numba/core/typing/arraydecl.py:102During: typing of intrinsic-call at /home/gaoithe/project/python/code/CenterPoint/det3d/core/bbox/geometry.py (296)
File "det3d/core/bbox/geometry.py", line 296:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
<source elided>
polygon
- polygon[
^
方法：修改det3d/core/bbox/geometry.py
# if clockwise:# vec1 = (# polygon# - polygon[# :,# [num_points_of_polygon - 1] + list(range(num_points_of_polygon - 1)),# :,# ]# )# else:# vec1 = (# polygon[# :,# [num_points_of_polygon - 1] + list(range(num_points_of_polygon - 1)),# :,# ]# - polygon# )indices = np.array([num_points_of_polygon - 1] + list(range(num_points_of_polygon - 1)))if clockwise:vec1 = polygon[:, indices, :] - polygon[:, np.roll(indices, 1), :]else:vec1 = polygon[:, np.roll(indices, 1), :] - polygon[:, indices, :]
原因：
这个错误是由于在Numba的JIT编译过程中，你试图使用一个不支持的索引类型来索引一个数组。具体来说，你试图使用一个整数列表（list(int64)）作为一个切片操作的一部分来索引一个3D数组。Numba不支持这种索引类型。 在你的代码中，这个错误发生在points_in_convex_polygon_jit函数中，当你试图对polygon数组进行切片操作。这个函数位于geometry.py文件的第296行。 为了解决这个问题，你需要更改你的索引类型。如果你想要使用一个整数列表来索引数组，你可以尝试将这个列表转换为Numpy数组，因为Numba支持使用Numpy数组作为索引。
)
