SC-shendazt

> > > > After struggling for almost a week, I successfully run RandLA-Net on my computer by docker, and my environment is RTX3070 + cuda11.1 + cudnn8.0.4 + python3.6.9...

> Hi, have you tried to modify the code to adapt MinkowskiEngine 0.5? I have tried the modify the segmentation code. But I found the mIoU drops 3% on S3DIS...

> 是可以使用的，已经在点云分割任务使用过了。 > > 关于维度报错的问题，这里建议都拉成一维再使用，eg:[B,n]。 点云中有效果吗，如果做语义分割

Hello, Dr.HuguesTHOMAS, I verified ‘def prepare_NPM3D_ply(self): ’function as you said, and generated two .ply files Vaihingen3D_train.ply and Vaihingen3D_test.ply in the train_folder.But there was a mistake at the end of round...

The error message is the same： ![Uploading 5.png…]() Traceback (most recent call last): File "/media/zt/D/PycharmProjects/KPConv-PyTorch-master/train_NPM3D.py", line 304, in trainer.train(net, training_loader, test_loader, config) File "/media/zt/D/PycharmProjects/KPConv-PyTorch-master/utils/trainer.py", line 274, in train self.validation(net, val_loader,...

yes，Vaihingen3D_test.ply have labels


Thank you for your reply. I will try to trace the cause

When I printed ‘self.min_potentials’, I found that ‘self.min_potentials’ was empty inside and that the set validation was also empty，Perhaps I have set self.validation_split incorrectly?  

Hi Dr.HuguesTHOMAS, I have successfully run the Vaihingen _3D dataset, I set self.validation_split=1 and then added a '[ ]' at line 432 in the util\trainer.py module