Closed niujiaxing closed 3 years ago
Sorry for the late reply. I am also a freshman at numba. I guess [] used here is the configuration for the kernel function rotate_iou_kernel_eval
, which points out how many blocks and threads per grid and block respectively. This is similar to <<<>>> used in CUDA. Now you have encountered this problem, I am worried whether you have installed numba correctly.
You could open an issue in traveller59/kitti-object-eval-python, If you have more questions about rotate_iou_cpu.py
.
Xiwu, thank u very much for u reply, I reinstalled numba and now this problem is solved. But I still have a question. When I verify the epoch, iou and acc are both 0. When I print the variables, I find that the tensor of seg_rusult is all 0. Do you know what the problem is?
It is hard to detect problems from such little information you provided. I don't know how you get this output. I think you can first use our provided pre-trained model to test and then check whether this problem is caused by the training step or evaluation function.
hello,i have a question in EPNet\tools\kitti_object_eval_python\rotate_iou_cpu.py line 329
When I run the program, it prompts me that there is an error in this line。
TypeError: 'function' object is not subscriptable
I want to know what the [] after the function means and whether there is a problem with this usage。
thank u !