运行TANet出现的一些问题及解决方案

1、result type Byte can't be cast to the desired output type Bool(voxelnet.py line993)

opp_labels=(box_preds[...,-1] >0) ^dir_lables.byte()
改为
opp_labels=(box_preds[...,-1] >0) ^dir_lables.to(torch.bool)

2、TypeError: 'numpy.float64' object cannot be interpreted as an integer

To solve it, you can either downgrade your numpy, or modify utils/eval.py, line about 719:

a, b, c = overlap_ranges[:, i, j] #extracting the three numbers
min_overlaps[:, i, j] = np.linspace(a, b, int(c)) #casting to integer