tensorflow中使用mnist数据集训练全连接神经网络-学习笔记
tensorflow中使用mnist数据集训练全连接神经网络
——学习曹健老师“人工智能实践:tensorflow笔记”的学习笔记, 感谢曹老师
前期准备:mnist数据集下载,并存入data目录:
文件列表:四个文件,分别为训练和测试集数据
Four files are available on 官网 http://yann.lecun.com/exdb/mnist/ :
train-images-idx3-ubyte.gz: training set images (9912422 bytes)
train-labels-idx1-ubyte.gz:
training set labels (28881 bytes)
t10k-images-idx3-ubyte.gz:
test set images (1648877 bytes)
t10k-labels-idx1-ubyte.gz:
test set labels (4542 bytes)
一、主要思路:
1、训练集输入数据X为28×28图像,和 Y_ onehot label
2、构建一个三层NN,input layer,one hidden layer,outputlayer
3、使用指数衰减学习率,交叉熵loss,移动平均loss构建NN
二、主要代码:
forward构建:
//mnist_forward.py
import tensorflow as tf
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
def get_weight(shape, regularizer):
w = tf.Variable(tf.truncated_normal(shape, stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
def get_bias(shape):
b = tf.Variable(tf.zeros(shape))
return b
def forward(x,regularizer):
w1 = get_weight([INPUT_NODE, LAYER1_NODE], regularizer)
b1 = get_bias([LAYER1_NODE])
y1 = tf.nn.relu(tf.matmul(x, w1) + b1)
w2 = get_weight([LAYER1_NODE, OUTPUT_NODE], regularizer)
b2 = get_bias([OUTPUT_NODE])
y = tf.matmul(y1, w2) + b2
return y
backward构建:
//mnist_backward.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import os
BATCH_SIZE = 200
LEARNING_RATE_BASE = 0.1
LEARNING_RATE_DECAY = 0.99
REGULARIZER = 0.0001
STEPS = 50000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "./model/"
MODEL_NAME = "mnist_model"
def backward(mnist):
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE])
y_ = tf.placeholder(tf.float32, [None, mnist_forward.OUTPUT_NODE])
y = mnist_forward.forward(x, REGULARIZER)
global_step = tf.Variable(0, trainable=False)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_,1))
cem = tf.reduce_mean(ce)
loss = cem + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase = True
)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step = global_step)
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step, ema_op]):
train_op = tf.no_op(name='train')
saver = tf.train.Saver()
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
for i in range(STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
if i % 1000 ==0:
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step = global_step)
def main():
mnist = input_data.read_data_sets("./data/", one_hot = True)
backward(mnist)
if __name__ == '__main__':
main()