Error in training on my own datasets and kitti datasets

[jiemingcui]

When I run the train.py, the error shows like this: voxel_features = voxel_features.permute(1, 0) RuntimeError: number of dims don't match in permute and self.padding, self.dilation, self.groups) RuntimeError: Calculated padded input size per channel: (0 x 100). Kernel size: (1 x 1). Kernel size can't be greater than actual input size

Is there anything wrong with the input or the network?