Iris

as leejiajun said, in `tf sampling compile.sh` file, change your tensorflow path. for example, I am using virtual env, so I change `/usr/local/lib/python2.7/dist-packages/tensorflow/include` to `/....../py2/venv_python2.7/lib/python2.7/site-packages/tensorflow/include`(my tensorflow path) such changes will...

when I run 'sh download.sh' it shows >HTTP request sent, awaiting response... 403 Forbidden >2018-11-23 08:54:52 ERROR 403: Forbidden. maybe it shows the URL is invalid @heiheiya ?

thx, i have downloaded it~

Hi @coronax1016, If you just test the pre-trained model provided by the author, you don't have to deal with raw KITTI data, because the python library imported in the 'kitti_predict.py'...

`pip install torch-encoding --pre` solve this problem

Hi, @yxlao , What do you mean `Train on Semantic3D (with no color), can run inference on KITTI: ` ? Are they not two different data sets? Are you training...

@sjtuytc hi, Thanks for your sharing the code. but I found the loss stopped decreasing at about 11. Could you tell me how you set the parameters? such as how...

@sjtuytc thank you !

thank you, I solved this problem by replacing `py_function` with `py_func `

Hey @huixiancheng, can you share the detailed training log and setting?