《TensorFlow实例》

Posted 2020-12-27 welcome-xwell

Ubuntu python3 TensorFlow实例：使用RNN算法实现对MINST-data数字集识别，最终识别准确率达96.875%

PS：小白一个，初级阶段，从调试到实现，step by step.

由于没能及时保留原著作者文章来源，对此深表歉意！！！

 

附录作者GitHub链接，以示尊重。

aymericdamien/TensorFlow-Examples: TensorFlow Tutorial and Examples for Beginners with Latest APIs  https://github.com/aymericdamien/TensorFlow-Examples

 

python文件列表：

2:RNN.py

3:tensorboard.py

数据集：MNIST_data

实现过程：

RNN.py

"""
This code is a modified version of the code from this link:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
His code is a very good one for RNN beginners. Feel free to check it out.
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# set random seed for comparing the two result calculations
tf.set_random_seed(1)

# this is data
mnist = input_data.read_data_sets(‘MNIST_data‘, one_hot=True)

# hyperparameters
lr = 0.001      #learning rate
training_iters = 100000
batch_size = 128

n_inputs = 28   # MNIST data input (img shape: 28*28)
n_steps = 28    # time steps
n_hidden_units = 128   # neurons in hidden layer
n_classes = 10      # MNIST classes (0-9 digits)

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])

# Define weights
weights = {
    # (28, 128)
    ‘in‘: tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
    # (128, 10)
    ‘out‘: tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}
biases = {
    # (128, )
    ‘in‘: tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),
    # (10, )
    ‘out‘: tf.Variable(tf.constant(0.1, shape=[n_classes, ]))
}


def RNN(X, weights, biases):
    # hidden layer for input to cell
    ########################################

    # transpose the inputs shape from
    # X ==> (128 batch * 28 steps, 28 inputs)
    X = tf.reshape(X, [-1, n_inputs])

    # into hidden
    # X_in = (128 batch * 28 steps, 128 hidden)
    X_in = tf.matmul(X, weights[‘in‘]) + biases[‘in‘]
    # X_in ==> (128 batch, 28 steps, 128 hidden)
    X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])

    # cell
    ##########################################

    # basic LSTM Cell.
    if int((tf.__version__).split(‘.‘)[1]) < 12 and int((tf.__version__).split(‘.‘)[0]) < 1:
        cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
    else:
        cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units)
    # lstm cell is divided into two parts (c_state, h_state)
    init_state = cell.zero_state(batch_size, dtype=tf.float32)

    # You have 2 options for following step.
    # 1: tf.nn.rnn(cell, inputs);
    # 2: tf.nn.dynamic_rnn(cell, inputs).
    # If use option 1, you have to modified the shape of X_in, go and check out this:
    # https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
    # In here, we go for option 2.
    # dynamic_rnn receive Tensor (batch, steps, inputs) or (steps, batch, inputs) as X_in.
    # Make sure the time_major is changed accordingly.
    outputs, final_state = tf.nn.dynamic_rnn(cell, X_in, initial_state=init_state, time_major=False)

    # hidden layer for output as the final results
    #############################################
    # results = tf.matmul(final_state[1], weights[‘out‘]) + biases[‘out‘]

    # # or
    # unpack to list [(batch, outputs)..] * steps
    if int((tf.__version__).split(‘.‘)[1]) < 12 and int((tf.__version__).split(‘.‘)[0]) < 1:
        outputs = tf.unpack(tf.transpose(outputs, [1, 0, 2]))    # states is the last outputs
    else:
        outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))
    results = tf.matmul(outputs[-1], weights[‘out‘]) + biases[‘out‘]    # shape = (128, 10)

    return results


pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)

correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

with tf.Session() as sess:
    # tf.initialize_all_variables() no long valid from
    # 2017-03-02 if using tensorflow >= 0.12
    if int((tf.__version__).split(‘.‘)[1]) < 12 and int((tf.__version__).split(‘.‘)[0]) < 1:
        init = tf.initialize_all_variables()
    else:
        init = tf.global_variables_initializer()
    sess.run(init)
    step = 0
    while step * batch_size < training_iters:
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        batch_xs = batch_xs.reshape([batch_size, n_steps, n_inputs])
        sess.run([train_op], feed_dict={
            x: batch_xs,
            y: batch_ys,
        })
        if step % 20 == 0:
            print(sess.run(accuracy, feed_dict={
            x: batch_xs,
            y: batch_ys,
            }))
        step += 1

 

tensorboard.py

# View more python learning tutorial on my Youtube and Youku channel!!!

"""
Please note, this code is only for python 3+. If you are using python 2+, please modify the code accordingly.
"""
from __future__ import print_function
import tensorflow as tf
import numpy as np


def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
    # add one more layer and return the output of this layer
    layer_name = ‘layer%s‘ % n_layer
    with tf.name_scope(layer_name):
        with tf.name_scope(‘weights‘):
            Weights = tf.Variable(tf.random_normal([in_size, out_size]), name=‘W‘)
            tf.summary.histogram(layer_name + ‘/weights‘, Weights)
        with tf.name_scope(‘biases‘):
            biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name=‘b‘)
            tf.summary.histogram(layer_name + ‘/biases‘, biases)
        with tf.name_scope(‘Wx_plus_b‘):
            Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b, )
        tf.summary.histogram(layer_name + ‘/outputs‘, outputs)
    return outputs


# Make up some real data
x_data = np.linspace(-1, 1, 300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network
with tf.name_scope(‘inputs‘):
    xs = tf.placeholder(tf.float32, [None, 1], name=‘x_input‘)
    ys = tf.placeholder(tf.float32, [None, 1], name=‘y_input‘)

# add hidden layer
l1 = add_layer(xs, 1, 10, n_layer=1, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, n_layer=2, activation_function=None)

# the error between prediciton and real data
with tf.name_scope(‘loss‘):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                                        reduction_indices=[1]))
    tf.summary.scalar(‘loss‘, loss)

with tf.name_scope(‘train‘):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

sess = tf.Session()
merged = tf.summary.merge_all()

writer = tf.summary.FileWriter("logs/", sess.graph)

init = tf.global_variables_initializer()
sess.run(init)

for i in range(1000):
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        result = sess.run(merged,
                          feed_dict={xs: x_data, ys: y_data})
        writer.add_summary(result, i)

# direct to the local dir and run this in terminal:
# $ tensorboard --logdir logs

相关介绍分析见文章来源：

tensorflow 学习笔记12 循环神经网络RNN LSTM结构实现MNIST手写识别 - CSDN博客  https://blog.csdn.net/Revendell/article/details/77451561

最终效果：

$ tensorboard --logdir logs

在tensorboard上查看RNN卷积递归过程