TensorFlow 使用

「爱情、让人受尽委屈。」 2024-04-20 09:14 74阅读 0赞

## • 搭建你的TensorFlow开发环境 ##

**tensorflow：**

tensorflow 一Current release for CPU-only (recommendedfor beginners) 
    tensorflow-gpu 一Current release with GPU support (Ubuntu and Windows) 
    tf-nightly —Nightly build for CPU-only (unstable) 
    tf-nightly-gpu —Nightly build with GPU support (unstable, Ubuntu and Windows)

**创建Python虚拟环境**

C:\Users\67001>pip install virtualenv

# 创建一个名字为envname的虚拟环境
    D:\Program Files\Anaconda3\virtual_Env>virtualenv TestEnv
    Using base prefix 'd:\\program files\\anaconda3'
      No LICENSE.txt / LICENSE found in source
    New python executable in D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts\python.exe
    Installing setuptools, pip, wheel...
    done.
    
    virtualenv -p python2 envname # 如果安装了多个python版本，如py2和py3，需要指定使用哪个创建虚拟环境
    
    # 进入虚拟环境文件
    D:\Program Files\Anaconda3\virtual_Env>cd TestEnv
    # 进入相关的启动文件夹
    D:\Program Files\Anaconda3\virtual_Env\TestEnv>cd Scripts
    # 启动虚拟环境
    D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>activate
    
    (TestEnv) D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>

deactivate # 退出虚拟环境

**在虚拟环境下安装tensorflow：**

(TestEnv) D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>pip install tensorflow

**或者：****国内安装比较快**

(TestEnv) D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>pip install -i https://pypi.tuna.tsinghua.edu.cn/simple/ --upgrade tensorflow

## • “Hello TensorFlow” ##

>>> import tensorflow as tf
    # 定义常量操作 hello
    >>> hello = tf.constant("Hello TensorFlow")
    # 创建一个会话
    >>> sess = tf.Session()
    2019-07-24 15:31:55.832973: I tensorflow/core/platform/cpu_feature_guard.cc:142] 
    Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
    #执行常量操作hello并打印到标准输出
    >>> print(sess.run(hello))
    b'Hello TensorFlow'

**支持AVX2指令集的CPUs**

• Intel
    • Haswell processor, Q2 2013
    • Haswell E processor, Q3 2014
    • Broadwell processor, Q4 2014
    • Broadwell E processor, Q3 2016
    • Skylake processor, Q3 2015
    • Kaby Lake processor, Q3 2016(ULV mobile)/Q1 2017(desktop/mobile)
    • Skylake-X processor, Q2 2017
    • Coffee Lake processor, Q4 2017
    • Cannon Lake processor, expected in 2018
    • Cascade Lake processor, expected in 2018
    • Ice Lake processor, expected in 2018
    
    
    • AMD
    • Excavator processor and newer, Q2 2015
    • Zen processor, Q1 2017
    • Zen+ processor, Q2 2018

## • 在交互式环境中使用 TensorFlow ##

pip install jupyter
    
    (TestEnv) D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>pip install ipykernel
    
    (TestEnv) D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>python -m ipykernel install --user --name=TestEnv
    Installed kernelspec TestEnv in C:\Users\67001\AppData\Roaming\jupyter\kernels\testenv
    
    (TestEnv) D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>jupyter kernelspec list
    Available kernels:
      testenv    C:\Users\67001\AppData\Roaming\jupyter\kernels\testenv
      python3    d:\program files\anaconda3\virtual_env\testenv\share\jupyter\kernels\python3

(TestEnv) D:\Program Files\Anaconda3\virtual_Env\TestEnv\Scripts>jupyter notebook

### **多层感知机模型示例** ###

**Neural Network Overview**[  
][Link 1]

**![nn][]**

**MNIST Dataset Overview**[  
][Link 2]

MNIST图像数据集使用形如［28，28］的二阶数组来表示每张图像，数组中的每个元素对应一个像素点。

该数据集中的图像都是256阶灰度图，像素值0表示白色（背景），255表示黑色（前景）。

由于每张图像的尺寸都是28x28像素，为了方便连续存储，我们可以将形如［28，28］

的二阶数组“摊平”成形如［784］的一阶数组。数组中的784个元素共同组成了一个784维的向量。

![1604514-20190724164318734-213800048.png][]

More info: [http://yann.lecun.com/exdb/mnist/][http_yann.lecun.com_exdb_mnist]

from __future__ import print_function
    
    # 导入 MNIST 数据集
    from tensorflow.examples.tutorials.mnist import input_data
    mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
    
    import tensorflow as tf

# 超参数
    learning_rate = 0.1
    num_steps = 500
    batch_size = 128
    display_step = 100
    
    # 神经网络参数
    n_hidden_1 = 256 # 第一层神经元个数
    n_hidden_2 = 256 # 第二层神经元个数
    num_input = 784 # MNIST 输入数据(图像大小: 28*28)
    num_classes = 10 # MNIST 手写体数字类别 (0-9)
    
    # 输入到数据流图中的训练数据
    X = tf.placeholder("float", [None, num_input])
    Y = tf.placeholder("float", [None, num_classes])
    
    
    # 权重和偏置
    weights = {
        'h1': tf.Variable(tf.random_normal([num_input, n_hidden_1])),
        'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
        'out': tf.Variable(tf.random_normal([n_hidden_2, num_classes]))
    }
    biases = {
        'b1': tf.Variable(tf.random_normal([n_hidden_1])),
        'b2': tf.Variable(tf.random_normal([n_hidden_2])),
        'out': tf.Variable(tf.random_normal([num_classes]))
    }
    
    
    
    # 权重和偏置
    weights = {
        'h1': tf.Variable(tf.random_normal([num_input, n_hidden_1])),
        'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
        'out': tf.Variable(tf.random_normal([n_hidden_2, num_classes]))
    }
    biases = {
        'b1': tf.Variable(tf.random_normal([n_hidden_1])),
        'b2': tf.Variable(tf.random_normal([n_hidden_2])),
        'out': tf.Variable(tf.random_normal([num_classes]))
    }
    
    
    
    # 定义神经网络
    def neural_net(x):
        # 第一层隐藏层（256个神经元）
        layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
        # 第二层隐藏层（256个神经元）
        layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
        # 输出层
        out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
        return out_layer
    
    
    
    # 构建模型
    logits = neural_net(X)
    
    # 定义损失函数和优化器
    loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
        logits=logits, labels=Y))
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
    train_op = optimizer.minimize(loss_op)
    
    # 定义预测准确率
    correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
    
    # 初始化所有变量（赋默认值）
    init = tf.global_variables_initializer()
    
    
    
    # 开始训练
    with tf.Session() as sess:
    
        # 执行初始化操作
        sess.run(init)
    
        for step in range(1, num_steps+1):
            batch_x, batch_y = mnist.train.next_batch(batch_size)
            # 执行训练操作，包括前向和后向传播
            sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})
            if step % display_step == 0 or step == 1:
                # 计算损失值和准确率
                loss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x,
                                                                     Y: batch_y})
                print("Step " + str(step) + ", Minibatch Loss= " + \
                      "{:.4f}".format(loss) + ", Training Accuracy= " + \
                      "{:.3f}".format(acc))
    
        print("Optimization Finished!")
    
        # 计算测试数据的准确率
        print("Testing Accuracy:", \
            sess.run(accuracy, feed_dict={X: mnist.test.images,
                                          Y: mnist.test.labels}))

## • 在容器中使用 TensorFlow ##

**VM vs Docker Container**

![1604514-20190724164608379-572643289.png][]

转载于:https://www.cnblogs.com/LXL616/p/11238262.html

[Link 1]: http://localhost:8888/notebooks/TensorFlow/TensorFlowTest/basic-models.ipynb#Neural-Network-Overview
[nn]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/18/f47e2f15705c44a4a861af9626fbeadf.jpeg
[Link 2]: http://localhost:8888/notebooks/TensorFlow/TensorFlowTest/basic-models.ipynb#MNIST-Dataset-Overview
[1604514-20190724164318734-213800048.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/18/bd350e53118846ceb41c2a5361c4cb00.png
[http_yann.lecun.com_exdb_mnist]: http://yann.lecun.com/exdb/mnist/
[1604514-20190724164608379-572643289.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/18/17833fcec57c4334bb290a9a947a897e.png