深度学习（一）：ubuntu18.04配置fcn网络并训练

        ubuntu18.04  cpu版本  pytorch

        选择python3.6版本进行配置，利用anaconda创建python=3.6的环境fcn,参考：https://github.com/wkentaro/pytorch-fcnhttps://github.com/wkentaro/pytorch-fcn

pytorch >= 0.2.0torchvision >= 0.1.8fcn >= 6.1.5Pillowscipytqdm 1.1 安装fcn包：

pip install fcn
#pip install --default-timeout=100 -i https://pypi.tuna.tsinghua.edu.cn/simple fcn

        进入PyTorch官网，下载cpu版本：

Start Locally | PyTorchhttps://pytorch.org/get-started/locally/

        复制网页的命令，我的如下： 

conda install pytorch torchvision torchaudio cpuonly -c pytorch

#或者pip
pip3 install torch==1.10.2+cpu torchvision==0.11.3+cpu torchaudio==0.10.2+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html

         验证安装：

 clash$ conda activate py36
(py36)  clash$ python
Python 3.6.13 |Anaconda, Inc.| (default, Jun  4 2021, 14:25:59) 
[GCC 7.5.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> torch.cuda.is_available()
False
>>> 

pip install pillow
pip install scipy
pip install tqdm

      下载 https://github.com/wkentaro/pytorch-fcnhttps://github.com/wkentaro/pytorch-fcn 的代码并解压,pip install .后出现下面一堆successfully。

(py36)  paper1$ cd pytorch-fcn-main/
(py36)  pytorch-fcn-main$ pip install .     ######安装torchfcn
Processing /home/elfoot/paper1/pytorch-fcn-main
  Preparing metadata (setup.py) ... done
--------------------------------

Requirement already satisfied: idna<4,>=2.5 in /home/elfoot/anaconda3/envs/py36/lib/python3.6/site-packages (from requests[socks]->gdown->fcn>=6.1.5->torchfcn==1.9.7) (3.3)
Requirement already satisfied: PySocks!=1.5.7,>=1.5.6 in /home/elfoot/anaconda3/envs/py36/lib/python3.6/site-packages (from requests[socks]->gdown->fcn>=6.1.5->torchfcn==1.9.7) (1.7.1)
Building wheels for collected packages: torchfcn
  Building wheel for torchfcn (setup.py) ... done
  Created wheel for torchfcn: filename=torchfcn-1.9.7-py3-none-any.whl size=137110 sha256=0e0a02e7459ab0c07e029ccefb4d80959a61ee28a9d4a052ea8574855f7c488f
  Stored in directory: /home/elfoot/.cache/pip/wheels/c9/60/99/c1bd09fc67e214cb878410d34a27c1a3ac13a0e4f22bddbadf
Successfully built torchfcn
Installing collected packages: torchfcn
Successfully installed torchfcn-1.9.7

        正在下载数据集-----很慢----不知有没有快的方法

        运行xxx/paper1/pytorch-fcn-main/examples/voc/download_dataset.sh脚本下载数据集，脚本内容如下，主要下载两个内容，并把他们放到DIR目录处：

#!/bin/bash

DIR=~/data/datasets/VOC

mkdir -p $DIR
cd $DIR

if [ ! -e benchmark_RELEASE ]; then
  wget http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz -O benchmark.tar
  tar -xvf benchmark.tar
fi

if [ ! -e VOCdevkit/VOC2012 ]; then
  wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
  tar -xvf VOCtrainval_11-May-2012.tar
fi

        关于直接在终端下载很慢，由于使用了科学上网，我直接把链接放到网页下载----贼快：

         创建文件夹~/data/datasets/VOC，并把下载的文件分别解压到文件夹内：

        接着如下图，分别将benchmark文件夹内的benchmark_RELEASE、VOCtrainval_11-May-2012内的VOCdevkit提到VOC目录中来。

        因为xxx/pytorch-fcn-main/examples/voc/train_fcn32s.py中提到了git log以及结合报错，如下，故先配置一下git

//xxx/pytorch-fcn-main/examples/voc/train_fcn32s.py截取
def git_hash():
    cmd = 'git log -n 1 --pretty="%h"'
    ret = subprocess.check_output(shlex.split(cmd)).strip()
    if isinstance(ret, bytes):
        ret = ret.decode()
    return ret

        先在自己的github创建一个repository，其链接为：https://github.com/menghxz/fcn-pytorch-cpu.git

       在~/.bashrc配置科学上网（可能需要，现在还没弄清需不需要），格式参考如下

export HTTP_PROXY="http://127.0.0.1:7890"
export HTTPS_PROXY="http://127.0.0.1:7890"

         终端配置git：

cd /home/elfoot/paper1/pytorch-fcn-main/examples/voc
git init
git add README.md
git commit -m "first commit"
git branch -M main
git remote add origin https://github.com/menghxz/fcn-pytorch-cpu.git  #你的链接
git push -u origin main

        终端进入voc目录，训练如下：

cd /home/elfoot/paper1/pytorch-fcn-main/examples/voc
./train_fcn32s.py 

Ubuntu18.04安装cpu版pytorch环境 - 简书https://www.jianshu.com/p/43f66c69baa7https://github.com/pytorch/pytorch#installationhttps://github.com/pytorch/pytorch#installation