Ubuntu16.04安裝TensorFlow及Mnist訓練

版權聲明：本文爲博主原創文章，歡迎轉載，並請註明出處。聯繫方式：460356155@qq.com

TensorFlow是Google開發的開源的深度學習框架，也是當前使用最普遍的深度學習框架。

1、安裝

ubuntu16.04安裝TensorFlow很簡單：

pip install tensorflow==1.1.0 --user

安裝是否成功驗證：

>>> import tensorflow as tf
>>> tf.__version__
'1.1.0'
>>> session = tf.Session()
>>> a = tf.constant(100)
>>> b = tf.constant(200)
>>> print(session.run(a+b))
300

 

2、Mnist訓練

定義三層全鏈接的網絡結構：768 × 300 × 10，完整代碼以下：

# -*- coding:utf-8 -*-

u"""TensorFlow訓練Mnist"""

__author__ = 'zhengbiqing 460356155@qq.com'


import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data


# 超參數定義
learning_rate = 0.5
epochs = 5000
batch_size = 128


def main():
    # 模型定義
    # 輸入圖片爲28 x 28 = 784 像素
    x = tf.placeholder(tf.float32, [None, 784])

    # 輸入層---->隱藏層權重及bias初始化
    W1 = tf.Variable(tf.random_normal([784, 300], stddev=0.03), name='W1')
    b1 = tf.Variable(tf.random_normal([300]), name='b1')

    # 隱藏層---->輸出層權重及bias初始化
    W2 = tf.Variable(tf.random_normal([300, 10], stddev=0.03), name='W2')
    b2 = tf.Variable(tf.random_normal([10]), name='b2')


    # 隱藏層輸出計算
    hidden_out = tf.add(tf.matmul(x, W1), b1)
    hidden_out = tf.nn.relu(hidden_out)


    # 模型輸出
    model_out = tf.nn.softmax(tf.add(tf.matmul(hidden_out, W2), b2))
    # model_out = tf.nn.softmax(model_out)

    
    # 交叉熵定義
    y = tf.placeholder(tf.int64, [None])
    cross_entropy = tf.losses.sparse_softmax_cross_entropy(labels=y, logits=model_out)


    # 優化器，肯定優化目標
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cross_entropy)


    # mnist 數據集
    mnist = input_data.read_data_sets("MNIST_data/")


    # 建立session
    with tf.Session() as sess:
        # session初始化
        tf.global_variables_initializer().run(session=sess)

        # 模型訓練
        for epoch in range(epochs):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys})

            # 測試準確率
            if epoch % 50 == 0:
                correct = tf.equal(tf.argmax(model_out, 1), y)
                accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
                acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
                print('Epoch:%d, Acc:%f' % (epoch, acc))


if __name__ == '__main__':
    main()

運行結果：

zbq@zbq:~/tf$ python tf-minist.py
Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
Epoch:0, Acc:0.097400
Epoch:50, Acc:0.606300
Epoch:100, Acc:0.726400
Epoch:150, Acc:0.745900
Epoch:200, Acc:0.751400
......

Epoch:4800, Acc:0.957200
Epoch:4850, Acc:0.957800
Epoch:4900, Acc:0.958000
Epoch:4950, Acc:0.958700

 運行5000個迭代，準確率達到了95%左右，對一個簡單的三層全鏈接網絡，該準確率仍是不錯的。