yuk

Hi @cagis2019, Have you successfully trained the pointnet2_sem_seg model? Could you please share it with us? My email is **[email protected]** Thank you very much!

> Hey there! I did not try that yet but you can try this link, where they re-organized the way to utilize pointnet2. https://github.com/intel-isl/Open3D-PointNet2-Semantic3D (dataset and results refer to http://www.semantic3d.net/view_method_detail.php?method=PointNet2_Demo)...

@cagis2019 , Yes!!! We are trying to use transfer learning. If you can share the pre-trained model with us, it would be great. We will try it based on kitti...

Hi @Coastline2018, Could you please share the trained model pointnet2_sem_seg with us? We would appreciate it. My email is **[email protected]** Thanks very much.

Hi @anjingde , I have done this. Origin kitti dataset looks like below: ``` gt [[-6.50606757e-01 -7.71165091e-03 -3.62864930e-02] [-6.50809720e-01 -7.30375763e-03 -3.70871616e-02] [-6.50674281e-01 -7.18719799e-03 -3.67654337e-02] ... [-6.55581403e-01 8.44116230e-04 -3.59173445e-02] [-6.55385991e-01 5.79053468e-04...

@fferroni Thanks very much for your comments. As is known, the topology of VGG and resnet are different from each other, and their output convolution tensors are not the same....

Hi @gcucurull , Thanks for your comments. If prior_boxes_ssd300.pkl are the default bounding boxes used by SSD, could I set prior_boxes_ssd300.pkl any value if I want to train the SSD...

@rykov8 Thanks for your response and and great work. I try to run forward code on theano, it seems that something wrong. I can run the forward by the keras...

@arunreddy I can also get the same result as you. But that's not right. You can check your code, you will find that it still runs on the tensorflow, not...

@rykov8 Thanks for your valuable input. If you could finish the theano version, that would be better. Let me summarize the work if we want to enable the **foward(aka: inference)**...