search

loicland / superpoint_graph

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
MIT License
745 stars 214 forks source link

ModuleNotFoundError: No module named 'torchnet' #282

Closed whuhxb closed 1 year ago

whuhxb commented 1 year ago

Hi @loicland ,

I have run the learning code of SPG on S3DIS dataset, and I have installed torchnet with pip install torchnet or pip install git+https://github.com/pytorch/tnt.git@master , but when running this code, the error occurs that no module named 'torchnet'. Have you ever met this error? How to solve? Thanks a lot.

File "./learning/s3dis_dataset.py", line 15, in import torchnet as tnt ModuleNotFoundError: No module named 'torchnet'

loicland commented 1 year ago

have you tried installing torchnet?

whuhxb commented 1 year ago

have you tried installing torchnet?

Yes. I have installed torchnet. Pytorch version is 0.4.0. I have no idea why this bug occur. Have you ever met this bug?

loicland commented 1 year ago

Hi!

We are releasing a new version of SuperPoint Graph called SuperPoint Transformer (SPT).

https://github.com/drprojects/superpoint_transformer

It is better in any way:

✨ SPT in numbers ✨
📊 SOTA results: 76.0 mIoU S3DIS 6-Fold, 63.5 mIoU on KITTI-360 Val, 79.6 mIoU on DALES
🦋 212k parameters only!
⚡ Trains on S3DIS in 3h on 1 GPU
⚡ Preprocessing is x7 faster than SPG!
🚀 Easy install (no more boost!)

If you are interested in lightweight, high-performance 3D deep learning, you should check it out. In the meantime, we will finally retire SPG and stop maintaining this repo.