Tensorflow--MNIST简单全连接层分类

Posted 2021-03-17 x1aolata

# @time    : 2020/1/5 22:39
# @author  : x1aolata
# @file    : mnist_train.py
# @script  : 训练简单手写数字识别模型-直接全连接-用于测试模型保存与转化


from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.framework import graph_util

# number 1 to 10 data 加载数据集
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)


def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
    correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
    return result


def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)


def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)


xs = tf.placeholder(tf.float32, [None, 784], name='x_input') / 255.  # 28x28
ys = tf.placeholder(tf.float32, [None, 10], name='y-input')

keep_prob = tf.constant(0.5)

x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape)  # [n_samples, 28,28,1]

## fc1 layer ##
W_fc1 = weight_variable([28 * 28, 1024])
b_fc1 = bias_variable([1024])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]

h_fc1 = tf.nn.relu(tf.matmul(xs, W_fc1) + b_fc1)
# h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

## fc2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)
# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))  # loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

sess = tf.Session()

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

for i in range(1000):
    pre_num = tf.argmax(prediction, 1, output_type='int32', name="output")
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys})
    if i % 50 == 0:
        print(compute_accuracy(
            mnist.test.images, mnist.test.labels))

# 保存训练好的模型
# 形参output_node_names用于指定输出的节点名称,output_node_names=['output']对应pre_num=tf.argmax(y,1,name="output"),
output_graph_def = graph_util.convert_variables_to_constants(sess, sess.graph_def, output_node_names=['output'])
with tf.gfile.FastGFile('model/mnist_01.pb', mode='wb') as f:  # ’wb’中w代表写文件，b代表将数据以二进制方式写入文件。
    f.write(output_graph_def.SerializeToString())