import tensorflow as tf
INPUT_NODE = 784 #28*28
OUTPUT_NODE = 10 #输出0~9
LAYER1_NODE = 500 #隐藏层节点个数
#权值函数
def get_weight(shape,regularizer):
w = tf.Variable(tf.truncated_normal(shape,stddev=0.1))
#正则化权重,采用l2方法
if regularizer!=None:
tf.add_to_collection('losses',tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
#偏执值
def get_bias(shape):
b = tf.Variable(tf.zeros(shape))
return b
#前向传播网络,输入x 和正则参数
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
X 为 N行784列
import tensorflow as tf
import mnist_forward
import os
from tensorflow.examples.tutorials.mnist import input_data
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.arg_max(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)
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:
sess.run(tf.global_variables_initializer())
# ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
# if ckpt and ckpt.model_checkpoint_path:
# saver.restore(sess,ckpt.model_checkpoint_path)
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 steps,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('./datas/MNIST_data',one_hot=True)
print('a')
backward(mnist)
if __name__ =='__main__':
main()
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import mnist_backward
TEST_INTERVAL_SECS =5
def test(mnist):
with tf.Graph().as_default() as g:
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,None)
ema = tf.train.ExponentialMovingAverage(mnist_backward.MOVING_AVERAGE_DECAY)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore)
correct_prediction = tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess,ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
accuracy_score = sess.run(accuracy,feed_dict={x:mnist.test.images,y_:mnist.test.labels})
print('After %s training step,test accuracy = %g'%(global_step,accuracy_score))
else:
print('No checkpoint file found')
return
time.sleep(TEST_INTERVAL_SECS)
def main():
mnist = input_data.read_data_sets('./datas/MNIST_data',one_hot=True)
test(mnist)
if __name__ =='__main__':
main()
import tensorflow as tf
from PIL import Image
import numpy as np
import mnist_backward
import mnist_forward
def restore_model(testPictArr):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE])
y = mnist_forward.forward(x,None)
preValue = tf.argmax(y,1)
variable_averages = tf.train.ExponentialMovingAverage(mnist_backward.MOVING_AVERAGE_DECAY)
varibale_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(varibale_to_restore)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess,ckpt.model_checkpoint_path)
preValue = sess.run(preValue,feed_dict={x:testPictArr})
return preValue
else:
print('No checkpoint file found')
return -1
def pre_pic(picName):
img = Image.open(picName)
reIm = img.resize((28,28),Image.ANTIALIAS)#消除锯齿的方法
im_arr = np.array(reIm.convert('L'))#变成灰度图
threshold = 50
for i in range(28):
for j in range(28):
im_arr[i][j] = 288-im_arr[i][j]
if(im_arr[i][j]
5000轮,准率0.972