跟我学算法-tensorflow 实现卷积神经网络附带保存和读取

时间:2024-06-02 17:06:02

这里的话就不多说明了,因为上上一个博客已经说明了

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('data/', one_hot=True) # 构造初始化参数, 方差为0.1
n_input = 784
n_output = 10
weights = {
'wc1' : tf.Variable(tf.truncated_normal([3, 3, 1, 64], stddev=0.1)),
'wc2' : tf.Variable(tf.truncated_normal([3, 3, 64, 128], stddev=0.1)),
'wd1' : tf.Variable(tf.truncated_normal([7*7*128, 1024], stddev=0.1)),
'wd2' : tf.Variable(tf.truncated_normal([1024, n_output], stddev=0.1)) } biases = {
'b1' : tf.Variable(tf.truncated_normal([64], stddev=0.1)),
'b2' : tf.Variable(tf.truncated_normal([128], stddev=0.1)),
'bd1' : tf.Variable(tf.truncated_normal([1024], stddev=0.1)),
'bd2' : tf.Variable(tf.truncated_normal([n_output], stddev=0.1)) } def conv_basic(_input, _w, _b, _keepratio): _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
#进行卷积操作
_conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')
# 使用激活函数
_conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))
# 进行池化操作, padding='SAME', 表示维度不足就补齐
_pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], stride=[1, 2, 2, 1], padding='SAME')
#去除一部分数据
_pool1_dr1 = tf.nn.dropout(_pool1, _keepratio)
#第二次卷积操作
_conv2 = tf.nn.conv2d(_pool1_dr1, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')
# 使用激活函数
_conv2 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))
# 进行池化操作
_pool2 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], stride=[1, 2, 2, 1], padding='SAME')
_pool_dr2 = tf.nn.dropout(_pool1, _keepratio) # 第一次全连接操作
# 对_pool_dr2 根据wd1重新构造函数
_densel = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
_fcl = tf.nn.relu(tf.add(tf.matmul(_densel, _w['wd1'], _b['bd1'])))
_fc_dr1 = tf.nn.dropout(_fcl, _keepratio)
# 第二次全连接
_out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])
out = {'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool1_dr1': _pool_dr1,
'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'dense1': _dense1,
'fcl': _fcl, 'fc_dr1': _fc_dr1, 'out': _out
}
return out x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32) # FUNCTIONS # 构造cost函数
#获得预测结果
_pred =conv_basic(x, weights, biases, keepratio)['out']
# 输入预测结果与真实值构造cost 函数
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(_pred, y))
# 优化函数使得cost最小
optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
# 计算准确率
_corr = tf.equal(tf.argmax(_pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))
init = tf.global_variables_initializer() # 进行训练
sess = tf.Session()
sess.run(init)
save_step = 1
# 每次只保存3个值
saver = tf.train.Saver(max_to_keep=3)
#迭代次数
training_epochs = 15
# 每次训练的样本数
batch_size = 16
#循环打印的次数
display_step = 1
do_train = 1
if do_train == 1:
for epoch in range(training_epochs):
avg_cost = 0.
#total_batch = int(mnist.train.num_examples/batch_size)
total_batch = 10
# Loop over all batches
for i in range(total_batch):
# 提取训练数据和标签
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
#训练模型优化参数
sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio:0.7})
# 加和损失值
avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})/total_batch # Display logs per epoch step
if epoch % display_step == 0:
print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})
print (" Training accuracy: %.3f" % (train_acc))
#test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.})
#print (" Test accuracy: %.3f" % (test_acc))
if epoch % save_step == 0:
saver.save(sess, "save/nets/cnn_mnist_basic.ckpt-" + str(epoch))
print ("OPTIMIZATION FINISHED") if do_train == 0:
epoch = training_epochs - 1
saver.restore(sess, "save/nets/cnn_mnist_basic.ckpt-" + str(epoch))
# 对测试集进行测试
feed_test = {x: mnist.test.images, y: mnist.test.labels, keepratio:1.}
test_acc = sess.run(accr, feed_dict=feed_test)
print(test_acc)