闵可夫斯基引擎Minkowski Engine
闵可夫斯基引擎Minkowski Engine
Minkowski引擎是一个用于稀疏张量的自动微分库。它支持所有标准神经网络层,例如对稀疏张量的卷积,池化,解池和广播操作。有关更多信息,请访问文档页面。
pip install git+https://github.com/NVIDIA/MinkowskiEngine.git
稀疏张量网络:空间稀疏张量的神经网络
压缩神经网络以加快推理速度并最小化内存占用已被广泛研究。用于模型压缩的流行技术之一是修剪卷积网络中的权重,也被称为稀疏卷积网络。用于模型压缩的这种参数空间稀疏性压缩在密集张量上运行的网络,并且这些网络的所有中间激活也是密集张量。
但是,在这项工作中,专注于空间稀疏的数据,尤其是空间稀疏的高维输入。还可以将这些数据表示为稀疏张量,并且这些稀疏张量在3D感知,配准和统计数据等高维问题中很常见。将专门用于这些输入的神经网络定义为稀疏张量网络,这些稀疏张量网络处理并生成稀疏张量作为输出。为了构建稀疏张量网络,建立了所有标准的神经网络层,例如MLP,非线性,卷积,规范化,池化操作,就像在密集张量上定义,并在Minkowski引擎中实现的方法一样。
在下面的稀疏张量卷积上可视化了一个稀疏张量网络操作。稀疏张量上的卷积层与密集张量上的卷积层相似。但是,在稀疏张量上,在一些指定点上计算卷积输出,这些点可以在广义卷积中进行控制。
特征
- 无限的高维稀疏张量支持
- 所有标准神经网络层(卷积,池化,广播等)
- 动态计算图
- 自定义内核形状
- 多GPU训练
- 多线程内核映射
- 多线程编译
- 高度优化的GPU内核
Requirements
- Ubuntu >= 14.04
- 11.1 > CUDA >= 10.1.243
- pytorch >= 1.5
- python >= 3.6
- GCC >= 7
Pip
MinkowskiEngine是通过PyPI MinkowskiEngine分发的,可以使用简单安装pip
。按照说明安装pytorch 。接下来,安装openblas
。
sudo apt install libopenblas-dev
pip install torch
pip install -U MinkowskiEngine --install-option="--blas=openblas" -v
# For pip installation from the latest source
# pip install -U git+https://github.com/NVIDIA/MinkowskiEngine
If you want to specify arguments for the setup script, please refer to the following command.
# Uncomment some options if things don't work
pip install -U git+https://github.com/NVIDIA/MinkowskiEngine \
# \ # uncomment the following line if you want to force cuda installation
# --install-option="--force_cuda" \
# \ # uncomment the following line if you want to force no cuda installation. force_cuda supercedes cpu_only
# --install-option="--cpu_only" \
# \ # uncomment the following line when torch fails to find cuda_home.
# --install-option="--cuda_home=/usr/local/cuda" \
# \ # uncomment the following line to override to openblas, atlas, mkl, blas
# --install-option="--blas=openblas" \
快速启动
要使用Minkowski引擎,首先需要导入引擎。然后,将需要定义网络。如果没有量化数据,则需要将(空间)数据体素化或量化为稀疏张量。幸运的是,Minkowski引擎提供了量化功能(MinkowskiEngine.utils.sparse_quantize
)。
Anaconda
We recommend python>=3.6
for installation. First, follow the anaconda documentation to install anaconda on your computer.
sudo apt install libopenblas-dev
conda create -n py3-mink python=3.8
conda activate py3-mink
conda install numpy mkl-include pytorch cudatoolkit=11.0 -c pytorch
pip install -U git+https://github.com/NVIDIA/MinkowskiEngine
System Python
Like the anaconda installation, make sure that you install pytorch with the same CUDA version that nvcc
uses.
# install system requirements
sudo apt install python3-dev libopenblas-dev
# Skip if you already have pip installed on your python3
curl https://bootstrap.pypa.io/get-pip.py | python3
# Get pip and install python requirements
python3 -m pip install torch numpy
git clone https://github.com/NVIDIA/MinkowskiEngine.git
cd MinkowskiEngine
python setup.py install
# To specify blas, CUDA_HOME and force CUDA installation, use the following command
# python setup.py install --blas=openblas --cuda_home=/usr/local/cuda --force_cuda
Creating a Network
import torch.nn as nn
import MinkowskiEngine as ME
class ExampleNetwork(ME.MinkowskiNetwork):
def __init__(self, in_feat, out_feat, D):
super(ExampleNetwork, self).__init__(D)
self.conv1 = nn.Sequential(
ME.MinkowskiConvolution(
in_channels=in_feat,
out_channels=64,
kernel_size=3,
stride=2,
dilation=1,
has_bias=False,
dimension=D),
ME.MinkowskiBatchNorm(64),
ME.MinkowskiReLU())
self.conv2 = nn.Sequential(
ME.MinkowskiConvolution(
in_channels=64,
out_channels=128,
kernel_size=3,
stride=2,
dimension=D),
ME.MinkowskiBatchNorm(128),
ME.MinkowskiReLU())
self.pooling = ME.MinkowskiGlobalPooling()
self.linear = ME.MinkowskiLinear(128, out_feat)
def forward(self, x):
out = self.conv1(x)
out = self.conv2(out)
out = self.pooling(out)
return self.linear(out)
Forward and backward using the custom network
# loss and network
criterion = nn.CrossEntropyLoss()
net = ExampleNetwork(in_feat=3, out_feat=5, D=2)
print(net)
# a data loader must return a tuple of coords, features, and labels.
coords, feat, label = data_loader()
input = ME.SparseTensor(feat, coords=coords)
# Forward
output = net(input)
# Loss
loss = criterion(output.F, label)