KPConv
KPConv copied to clipboard
HuguesTHOMAS
Kernel Point Convolutions
Hello, Thank you for sharing your KPCONV code! I'd like to ask if it is possible to add more features to the computation (i.e., XYZ, RGB, intensity or reflectance, no....
Hi @HuguesTHOMAS , Impressive work!! Do you think we can build GAN for cloud segmentation based on KPConv? What do you suggest?
I would like to test the KPConv on the pertrained model of Semntic3D dataset (any of semantic8 or reduced-8). Could you please share if you have the pretrained model? Thanks
 Can you help me?
Hi Hugues, I am trying to train KPConv with the ModelNet40 dataset, but after the message "Dataset Preparation * * * * * * * * * * * *...
Hi @HuguesTHOMAS During training, an error was reported here: ``` InternalError (see above for traceback): Blas GEMM launch failed : a.shape=(2054, 256), b.shape=(2054, 128), m=256, n=128, k=2054 [[node optimizer/gradients/KernelPointNetwork/layer_2/resnetb_deformable_0/conv1/MatMul_grad/MatMul_1 (defined...
hi! I want to make my own segmentation datasets like S3DIS or Paris-Lille-3D. As the description in the paper " The 3D scenes in these datasets are too big to...
how can i visualize the test results?my task is scene segmentation,but the results point cloud has the same color.How can have the results which different object or area has different...
Traceback (most recent call last): File "train_ModelNet40.py", line 283, in trainer.train(net, training_loader, test_loader, config) File "/home/ubuntu/src/KPConv-PyTorch/utils/trainer.py", line 188, in train outputs = net(batch, config) File "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__...
