TypeError: tuple indices must be integers or slices, not str

[azooz95]

Thank you for your remarkable efforts.

I am running the test file for inference, however i am getting typeError as following:
Traceback (most recent call last):
File "/home/azooz/Downloads/PointPillars/test.py", line 138, in
main(args)
File "/home/azooz/Downloads/PointPillars/test.py", line 83, in main
result_filter = keep_bbox_from_lidar_range(result_filter, pcd_limit_range)
File "/home/azooz/Downloads/PointPillars/utils/process.py", line 592, in keep_bbox_from_lidar_range
lidar_bboxes = result['lidar_bboxes']
TypeError: tuple indices must be integers or slices, not str

Thank you in advance.

[RunTian1]

Thank you for your remarkable efforts.

I am running the test file for inference, however i am getting typeError as following: Traceback (most recent call last): File "/home/azooz/Downloads/PointPillars/test.py", line 138, in main(args) File "/home/azooz/Downloads/PointPillars/test.py", line 83, in main result_filter = keep_bbox_from_lidar_range(result_filter, pcd_limit_range) File "/home/azooz/Downloads/PointPillars/utils/process.py", line 592, in keep_bbox_from_lidar_range lidar_bboxes = result['lidar_bboxes'] TypeError: tuple indices must be integers or slices, not str

Thank you in advance.

I have encountered this problem before. The main reason is that the pillars returned by PillarsLayer had a value of 0, which was later used as the denominator when computing the center point in PillarEncoder, resulting in nan results. Find the part of pillars with a value of 0 to solve it

[zhulf0804]

Hello @azooz95,

Did you modify the original code? I find line 592 in file "PointPillars/utils/process.py" is not lidar_bboxes = result['lidar_bboxes'].

Could you show me the complete code here ? Thanks.

[ye12121]

Hello @azooz95,

Did you modify the original code? I find line 592 in file "PointPillars/utils/process.py" is not lidar_bboxes = result['lidar_bboxes'].

Could you show me the complete code here ? Thanks.

我也遇到这个问题，报错也是在这行代码 lidar_bboxes = result['lidar_bboxes']，原因是result不是dict，返回的是一个空的tuple。应该是模型推理过程中没有检测到物体。对应的代码应该是 pointpillars.py中337行 return [], [], []。评估函数里没有对异常值做处理所以报错了。

[quliang93]

Hello @azooz95,

Did you modify the original code? I find line 592 in file "PointPillars/utils/process.py" is not lidar_bboxes = result['lidar_bboxes'].

Could you show me the complete code here ? Thanks.

Thank you for your reply !
Great Job !
This problem didn't happen in official KITTI dataset. But after I tested it in my custom dataset. I also met this error.
I did some test in a special scene. If the scene didn't contain any objects like Car, Pedestrian or Cyclist or the model output ([], [], []). And I got the same error like @azooz95 mentioned.

Can you give me some advice? Thank you very much

[Fudidii]

我也遇到了这个问题,后来发现是改了之后就不能用原来的训练出来的文件,改成自己的文件就好了,特别感谢@ye12121的评论启发