神经网络学习入门干货(二) 识别mnist数据集
- 神经网络结构设计(输入层784点,隐藏层500点,输出层10点)
- 训练数据量Batch、轮数steps、学习率及衰减Learning—Rate、正则项系数lambda、滑动平均衰减率ema
- 辅助函数计算前向传播结果tf.nn.relu(tf.matmul())
- 网络权重和偏置变量取随机值tf.truncated_normal
- 交叉熵损失函数和正则化损失项tf.nn.sparse_softmax_cross_entropy_with_logits()
- 梯度下降优化算法(最小化损失函数)tf.train.GradientDescentOptimizer()
- 验证数据每1000轮准确率validate-acc、测试数据模型最终准确率
- 定义main主函数和app.run调用
代码
import tensorflow as tf
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
if avg_class == None:
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
return tf.matmul(layer1, weights2) + biases2
else:
layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1)) + avg_class.average(biases1))
return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2)
def train(mnist):
x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')
weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1))
biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))
weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))
y = inference(x, None, weights1, biases1, weights2, biases2)
global_step = tf.Variable(0, trainable=False)
variables_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(y, tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
regularization = regularizer(weights1) + regularizer(weights2)
loss = cross_entropy_mean + regularization
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE-DECY)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
train_op = tf.group(train_step, variables_averages_op)
correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
sess.run(init_op)
validate_feed = {x: mnist.validation.images, y_:mnist.validation.labels}
test_feed = {x: mnist.test.images, y_: mnist.test.labels}
for i in range(TRAINING_STEPS):
if i % 1000 == 0:
validate_acc = sess.run(accuracy, feed_dict=validate_feed)
xs, ys = mnist.train.next_batch(BATCH_SIZE)
sess.run(train_op, feed_dict={x: xs, y_: ys})
test_acc = sess.run(accuracy, feed_dict=test_feed)
def main(argv=None):
mnist = input_data.read_data_sets("/tmp/data", one-hot=True)
train(mnist)
if __name__ == '__main__':
tf.app.run()