smanshei

May be there are no objects in the ground truth. Try with the frame which has some cars in it

z is the vertical direction of point cloud, you can set it as z=(-3, 1) for kitti data set, actually it is filtering out the ground truth objects which are...

This architecture will provide you with eight points in the output, you can join the points accordingly to get the bounding box. In some cases neural network will provide with...

While training you dont need to provide the bounding box shape. You have to provide with regression targets for each instance of vehicle, like eight corners with centered zero.

Hi @spbayley I think generator give error when there is no Car in scene. you may reffer to this issue for solution[https://github.com/yukitsuji/3D_CNN_tensorflow/issues/4](url) I hope this will help you

@OneManArmy93 One easiest solution would be to filterout all the files (pointcloud) which do not contain any vehicle in them by using information from ground truth.

1: tries to filter out the pointcloud which are outside the camera field of view. As labels for the vehicles are available in that area only. 2: It is used...

Hi @abhigoku10 here is the function which is used for data augmentation. https://github.com/jeasinema/VoxelNet-tensorflow/blob/d24c3eefc5762e4785ca3be6ca7d1fd0ef16bc61/utils/data_aug.py#L23

@abhigoku10 I do not have any idea about occolusion augmentation, But here are three types of augmentations. For each iteration, one type of augmentation is performed which is selected based...

@traveller59 do you remove occluded or truncated cars while training?