search

Natsu-Akatsuki / RangeNetTrt8

tensorrt8 && cuda && libtorch implementation of rangenet++
MIT License
44 stars 9 forks source link

Ihave three weight files. Do I need to merge these three weight files together first? #13

Closed 1806610292 closed 10 months ago

1806610292 commented 10 months ago

Thank you very much for your work. I've trained using the Python source code of Rangenet++, and I now have three weight files. Do I need to merge these three weight files together first?

Natsu-Akatsuki commented 10 months ago

Thanks for your try.

I have not tried the training phase and used the generated model file (do you mean the file backbone, segmentation_decoder, segmentation_head?) to construct the onnx-format model file.

May be this issue would help you: https://github.com/PRBonn/lidar-bonnetal/issues/32

1806610292 commented 10 months ago

Thanks for your try.

I have not tried the training phase and used the generated model file (do you mean the file backbone, segmentation_decoder, segmentation_head?) to construct the onnx-format model file.

May be this issue would help you: PRBonn/lidar-bonnetal#32

I followed your advice and have resolved the issue. Thank you very much！

Natsu-Akatsuki commented 10 months ago

Get. Valuable feedback.