Empty SparseTensor convolution segfault

[francois-drielsma]

Describe the bug
When passing an empty SparseTensor object through a MinkowskiConvolution, MinkowskiEngine throws a segfault.

---

To Reproduce
Docker image: deeplearnphysics/larcv2:ub20.04-cuda12.1-pytorch2.2.1-larndsim

Code snippet

import torch
import MinkowskiEngine as ME

input = ME.SparseTensor(coordinates=torch.empty(0,4).to(dtype=torch.int), features=torch.empty(0,1))
conv = ME.MinkowskiConvolution(in_channels=1, out_channels=3, dimension=3, kernel_size=3)
conv(input)

---

Expected behavior
Would hope for an empty output with the appropriate number of features, e.g.:

SparseTensor(
  coordinates=tensor([], size=(0, 4), dtype=torch.int32)
  features=tensor([], size=(0, 3), grad_fn=<MinkowskiConvolutionFunctionBackward>)
  coordinate_map_key=coordinate map key:[1, 1, 1]
  coordinate_manager=CoordinateMapManagerCPU(
	[1, 1, 1, ��]:	CoordinateMapCPU:0x4
	algorithm=MinkowskiAlgorithm.DEFAULT
  )
  spatial dimension=3)

---

Desktop (please complete the following information):

• OS: Ubuntu 20.04
• Python version: 3.8.10
• Pytorch version: 2.2.1
• CUDA version: 12.1
• NVIDIA Driver version: 535.161.07
• Minkowski Engine version: 0.5.4
• Output of the following command. (If you installed the latest MinkowskiEngine, paste the output of python -c "import MinkowskiEngine as ME; ME.print_diagnostics()". Otherwise, paste the output of the following command.)

/usr/local/lib/python3.8/dist-packages/MinkowskiEngine/__init__.py:36: UserWarning: The environment variable `OMP_NUM_THREADS` not set. MinkowskiEngine will automatically set `OMP_NUM_THREADS=16`. If you want to set `OMP_NUM_THREADS` manually, please export it on the command line before running a python script. e.g. `export OMP_NUM_THREADS=12; python your_program.py`. It is recommended to set it below 24.
 warnings.warn(
==========System==========
Linux-4.18.0-372.32.1.el8_6.x86_64-x86_64-with-glibc2.29
DISTRIB_ID=Ubuntu
DISTRIB_RELEASE=20.04
DISTRIB_CODENAME=focal
DISTRIB_DESCRIPTION="Ubuntu 20.04.6 LTS"
3.8.10 (default, Nov 22 2023, 10:22:35) 
[GCC 9.4.0]
==========Pytorch==========
2.2.1+cu121
torch.cuda.is_available(): True
==========NVIDIA-SMI==========
/usr/bin/nvidia-smi
Driver Version 535.161.07
CUDA Version 12.2
VBIOS Version 92.00.19.00.13
Image Version G506.0202.00.02
GSP Firmware Version 535.161.07
==========NVCC==========
/usr/local/cuda/bin/nvcc
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Mon_Apr__3_17:16:06_PDT_2023
Cuda compilation tools, release 12.1, V12.1.105
Build cuda_12.1.r12.1/compiler.32688072_0
==========CC==========
/usr/bin/c++
c++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Copyright (C) 2019 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

==========MinkowskiEngine==========
0.5.4
MinkowskiEngine compiled with CUDA Support: True
NVCC version MinkowskiEngine is compiled: 12010
CUDART version MinkowskiEngine is compiled: 12010

---

Additional context
I did not do extensive version testing, but this seems to work for torch 1.13 in an older container: deeplearnphysics/larcv2:ub20.04-cuda11.6-pytorch1.13-larndsim

[francois-drielsma]

Having a similar issue with MinkowskiConvolutionTranspose, even with the older version of PyTorch. This:

import torch
import MinkowskiEngine as ME

input = ME.SparseTensor(coordinates=torch.empty(0,4).to(dtype=torch.int), features=torch.empty(0,1))
conv = ME.MinkowskiConvolution(in_channels=1, out_channels=4, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1], dimension=3)
conv_t = ME.MinkowskiConvolutionTranspose(in_channels=4, out_channels=4, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1], dimension=3)
x = conv(input)
x = conv_t(x)

throws a segfault on the last line.