NUAAXQ

@happinesslz The total_cost are always nan during training. Did your meet the same problem?

Add the following code after line 84 in the model.py if np.isnan(vote_reg_loss): vote_reg_loss = tf.constant(zero) Do you mean that? By the way, did you also meet the same problem in...

For the first question, votenet use the same residual (offset) regression strategy in Frustum PointNets. As reported in Frustum PointNets, they follow the idea of Faster R-CNN and 3D-Deepbox. The...

Maybe this [github repository](https://github.com/NUAAXQ/MLCVNet) can help you.

Maybe this [github repository](https://github.com/NUAAXQ/MLCVNet) can help you.

> Hello, may I ask where the PPC module has been added? I didn't see it in the source code Hi, thanks very much for your interest in our paper....