ubuntu16.04安装detectron教程

2023年2月9日 215次阅读 来源: 唐尼

ubuntu16.04安装detectron教程

系统环境要求：

  • NVIDIA GPU, Linux, Python2
  • Caffe2, 部分Python包, COCO API

1. python2.7

Detectron必须在python2环境，python3不支持， 推荐使用conda 创建一个新的环境python27，并且切换到新环境

conda create -n python27 python=2.7
conda activate python27

以下所有操作都在python2.7下执行

2. 安装 CUDA 8 + CuDNN 7 + NCCL

2.1 CUDA8安装

安装过程略

验证安装：nvcc –version

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2016 NVIDIA Corporation
Built on Tue_Jan_10_13:22:03_CST_2017
Cuda compilation tools, release 8.0, V8.0.61

2.2 从Debian文件安装CuDNN 7

下载地址：https://developer.nvidia.com/cudnn

# 1.Install the runtime library, for example:
sudo dpkg -i libcudnn7_7.0.3.11-1+cuda9.0_amd64.deb
# 2.Install the developer library, for example:
sudo dpkg -i libcudnn7-devel_7.0.3.11-1+cuda9.0_amd64.deb
# 3.Install the code samples and the cuDNN Library User Guide, for example:
sudo dpkg -i libcudnn7-doc_7.0.3.11-1+cuda9.0_amd64.deb

2.3 测试CuDNN 7

样例在/usr/src/cudnn_samples_v7路径下

1.Copy the cuDNN sample to a writable path.
$cp -r /usr/src/cudnn_samples_v7/ $HOME
2.Go to the writable path.
$ cd  $HOME/cudnn_samples_v7/mnistCUDNN
3.Compile the mnistCUDNN sample.
$make clean && make
4.Run the mnistCUDNN sample.
$ ./mnistCUDNN

显示如下，表示安装成功： Test passed!

2.4 cuDNN从v6升级到v7

cuDNN v7可以与之前版本的cuDNN共存，例如v5或v6。 cuDNN v7 can coexist with previous versions of cuDNN, such as v5 or v6.

2.5 NCCL安装

下载安装包并安装

sudo dpkg -i nccl-repo-ubuntu1604-2.2.13-ga-cuda8.0_1-1_amd64.deb

3. 安装Caffe2

官网：https://caffe2.ai/docs/getting-started.html?platform=ubuntu&configuration=prebuilt

3.1 conda安装Caffe2

使用Anaconda在GPU + CUDA8 + CuDNN7环境下

conda install pytorch-nightly cuda80 -c pytorch

3.2 验证Caffe2

检查Caffe2的GPU依赖是否正确，下面命令输出的GPU卡的数量必须要大于0 ,否则不能使用Detectron

# To check if Caffe2 build was successful
python -c 'from caffe2.python import core' 2>/dev/null && echo "Success" || echo "Failure"

# To check if Caffe2 GPU build was successful
# This must print a number > 0 in order to use Detectron
python -c 'from caffe2.python import workspace; print(workspace.NumCudaDevices())'

验证过程显示Failure，terminal重新输入 python -c ‘from caffe2.python import core’，可以显示错误信息

错误1： No module named google.protobuf.internal 解决方法：pip install protobuf

错误2： no moudle named past.builtins 解决方法：pip install future

4. 安装COCO API

# COCOAPI=/path/to/clone/cocoapi
git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
cd $COCOAPI/PythonAPI
# Install into global site-packages
make install
# Alternatively, if you do not have permissions or prefer
# not to install the COCO API into global site-packages
python setup.py install --user

在make install 如出现错误error: pycocotools/_mask.c: No such file or directory：

解决方法：pip install cython

5. 安装Detectron

5.1 安装

官网教程：https://github.com/facebookresearch/Detectron/blob/master/INSTALL.md

Clone the Detectron repository:

# DETECTRON=/path/to/clone/detectron
git clone https://github.com/facebookresearch/detectron $DETECTRON
Install Python dependencies:

pip install -r $DETECTRON/requirements.txt
Set up Python modules:

cd $DETECTRON && make
Check that Detectron tests pass (e.g. for SpatialNarrowAsOp test):

python $DETECTRON/detectron/tests/test_spatial_narrow_as_op.py

5.2 运行Detectron

官方网址： https://github.com/facebookresearch/Detectron/blob/master/GETTING_STARTED.md

可以使用tools目录下内置的infer_simple.py 来使用预训练的模型来预测实际的照片，infer_simple.py里面调用的是detectron封装的vis_utils.vis_one_image API。

python tools/infer_simple.py \
    --cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml \
    --output-dir /tmp/detectron-visualizations \
    --image-ext jpg \
    --wts https://dl.fbaipublicfiles.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
    demo

最终，检测结果就以pdf的格式输出到了/tmp/detectron-visualizations目录下

    原文作者：唐尼
    原文地址: https://zhuanlan.zhihu.com/p/58149921
    本文转自网络文章，转载此文章仅为分享知识，如有侵权，请联系博主进行删除。
点赞