Lab学习笔记02：Tensorflow下载与安装及第一个训练神经网络模型

步骤过程参照：http://wiki.jikexueyuan.com/project/tensorflow-zh/get_started/os_setup.html#install_cuda

 

一、安装过程

我选择了文档更推荐的基于VirtualEnv 的安装方法。

我是macOS系统，这里列举的是mac的安装方法。

1. 安装必备工具

$ sudo easy_install pip  # 如果还没有安装 pip
$ sudo pip install --upgrade virtualenv

由于我在之前的课程中，安装过pip和virtualenv，所以该步骤跳过。

2. 建立全新的virtualenv 环境. 为了将环境建在 ~/tensorflow 目录下, 执行:

$ virtualenv --system-site-packages ~/tensorflow
$ cd ~/tensorflow

3. 激活 virtualenv:

$ source bin/activate  # 我使用的是bash
(tensorflow)$  # 终端提示符应该发生变化

4. 在 virtualenv 内, 安装 TensorFlow:

(tensorflow)$ pip install --upgrade <$url_to_binary.whl>

注意：在这里我遇到了问题，在Stack Overflow上找到解决方案，将<$url_to_binary.whl>改为如下方式成功：

(tensorflow)$ pip install --upgrade https://storage.googleapis.com/tensorflow/mac/tensorflow-0.8.0-py2-none-any.whl

5. 运行TensorFlow程序

6. 当时使用完TensorFlow：

(tensorflow)$ deactivate  # 停用 virtualenv

 

二、训练第一个 TensorFlow 神经网络模型

我利用 tensorflow/lib/python2.7/site-packages/tensorflow/models/image/mnist文件夹中的convolutional.py文件，训练模型得到如下结果：

/Users/yang/tensorflow/bin/python2.7 /Users/yang/tensorflow/lib/python2.7/site-packages/tensorflow/models/image/mnist/convolutional.py
Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting data/train-images-idx3-ubyte.gz
Extracting data/train-labels-idx1-ubyte.gz
Extracting data/t10k-images-idx3-ubyte.gz
Extracting data/t10k-labels-idx1-ubyte.gz
Initialized!
Step 0 (epoch 0.00), 5.3 ms
Minibatch loss: 12.054, learning rate: 0.010000
Minibatch error: 90.6%
Validation error: 84.6%
Step 100 (epoch 0.12), 456.5 ms
Minibatch loss: 3.269, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 6.9%
Step 200 (epoch 0.23), 403.6 ms
Minibatch loss: 3.474, learning rate: 0.010000
Minibatch error: 12.5%
Validation error: 3.6%
Step 300 (epoch 0.35), 440.9 ms
Minibatch loss: 3.215, learning rate: 0.010000
Minibatch error: 7.8%
Validation error: 3.4%
Step 400 (epoch 0.47), 428.5 ms
Minibatch loss: 3.224, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 2.8%
Step 500 (epoch 0.58), 419.7 ms
Minibatch loss: 3.303, learning rate: 0.010000
Minibatch error: 7.8%
Validation error: 2.6%
Step 600 (epoch 0.70), 352.2 ms
Minibatch loss: 3.212, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 2.7%
Step 700 (epoch 0.81), 398.7 ms
Minibatch loss: 3.008, learning rate: 0.010000
Minibatch error: 3.1%
Validation error: 2.4%
Step 800 (epoch 0.93), 365.9 ms
Minibatch loss: 3.082, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 2.1%
Step 900 (epoch 1.05), 382.6 ms
Minibatch loss: 2.941, learning rate: 0.009500
Minibatch error: 3.1%
Validation error: 1.5%
Step 1000 (epoch 1.16), 400.3 ms
Minibatch loss: 2.858, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.8%
......