-
Thank you for your work! I am studying 3d semantic segmentation. Since SparseConvNet is so useful.Is it possible to combine SparseConvNet with PointNet?
-
Hi, I'm learning the implementation of the SCN. But I encounter some problems and hope to get some advice from you.
When I see the convolution code, I find the metadata of input is passed directly t…
-
Hello. I'm now using the SparseConvNet for character regconition. And I found when I set the filter size to 1 for the scn.Convolution layer, then the layer had empty output. I did not dive deep into t…
-
`
python3 ./second/pytorch/train.py train --config_path=./second/configs/car.config --model_dir=/media/1t/data/kitti/second_model
`
`Segmentation fault (core dumped)`
seems it core dump at voxel…
-
Hi,
in your Paper "Sparse 3D convolutional neural networks" you stated that you have compared a network with triangular kernels against a kernel with quadric kernels.
Is there any implementation…
-
SparseConvNet/sparseconvnet/metadata.py
Has a problem when running on the gpu. Should the underscore be a slash?
-
Results look excellent however unfortunately I am unable to run.
OS: Ubuntu 18.04
GPU: 1050ti
`python3 ./pytorch/train.py evaluate --config_path=./configs/car.config --model_dir=pretrained_mode…
-
Thank you for your great work!
I now want to use your SparseConvnet to construct a `mobilenetv1` for testing on my own dataset, and the images in this dataset is indeed sparse (in fact it is wafer da…
-
Hi,
Do you think this implementation could be easily adapted to work with sparse permutohedral lattices ? As discussed in [1](https://arxiv.org/pdf/1503.04949.pdf) [2](https://arxiv.org/pdf/1802.0…
-
Hi!
I am a little confused with the following line:
https://github.com/facebookresearch/SparseConvNet/blob/master/examples/3d_segmentation/data.py#L80
> xl=np.floor(resolution*(**4**+xl)).astype…