版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/Kexiii/article/details/78019925
基本架构
- mnist_inference.py
LeNet网络构建以及前向传播过程 - mnist_train.py
网络训练,并在每一定epoch后写checkpoint - mnist_eval.py
模型评价,定时读取checkpoint进行模型评价
在这里,mnist_train.py和mnist_eval.py可以分别同时运行,eval模块会定时读取由train模块运行过程中写的checkpoint从而实时对模型进行评估。最终的准确率应该在99.4%左右
代码
mnist_inference.py
import tensorflow as tf
#define basic parameters
INPUT_NODE = 28*28 # mnist 28*28 image
OUTPUT_NODE = 10 # 10 classes classification
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
#neural network's parameters
CONV1_DEPTH = 32
CONV1_SIZE = 5
CONV2_DEPTH = 64
CONV2_SIZE = 5
#512 nodes fully connected layer
FC_SIZE = 512
def inference(input_tensor,train,regularizer=None):
"""CNN forward pass
Args:
input_tensor:
input mnist image tensor with shape [None,28,28,1]
train:
indicate whether it's a training pass. If not,
dropout will not be applied
regularizer:
standard tensorflow weights regularizer
return:
output tensor with shape [NUM_LABELS]
"""
with tf.variable_scope('layer1-conv1'):
conv1_weights = tf.get_variable('weight',
[CONV1_SIZE,CONV1_SIZE,NUM_CHANNELS,CONV1_DEPTH],
initializer=tf.truncated_normal_initializer(stddev=0.1))
conv1_biases = tf.get_variable('bias',
[CONV1_DEPTH],initializer=tf.constant_initializer(0.0))
conv1 = tf.nn.conv2d(input_tensor,conv1_weights,
strides=[1,1,1,1],padding='SAME')
relu1 = tf.nn.relu(tf.nn.bias_add(conv1,conv1_biases))
with tf.name_scope('layer2-pool1'):
pool1 = tf.nn.max_pool(relu1,
ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
with tf.variable_scope('layer3-conv2'):
conv2_weights = tf.get_variable('weight',
[CONV2_SIZE,CONV2_SIZE,CONV1_DEPTH,CONV2_DEPTH],
initializer=tf.truncated_normal_initializer(stddev=0.1))
conv2_biases = tf.get_variable('bias',
[CONV2_DEPTH],initializer=tf.constant_initializer(0.0))
conv2 = tf.nn.conv2d(pool1,conv2_weights,
strides=[1,1,1,1],padding='SAME')
relu2 = tf.nn.relu(tf.nn.bias_add(conv2,conv2_biases))
with tf.name_scope('layer4-pool2'):
pool2 = tf.nn.max_pool(relu2,
ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
#flatten
pool_shape = pool2.get_shape().as_list()
nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]
fc_input = tf.reshape(pool2,[-1,nodes])
with tf.variable_scope('layer5-fc1'):
fc1_weights = tf.get_variable('weight',
[nodes,FC_SIZE],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses',regularizer(fc1_weights))
fc1_biases = tf.get_variable('bias',
[FC_SIZE],initializer=tf.constant_initializer(0.1))
fc1 = tf.nn.relu(tf.matmul(fc_input,fc1_weights)+fc1_biases)
if train:
fc1 = tf.nn.dropout(fc1,0.5)
with tf.variable_scope('layer6-fc2'):
fc2_weights = tf.get_variable('weight',
[FC_SIZE,NUM_LABELS],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses',regularizer(fc2_weights))
fc2_biases = tf.get_variable('bias',
[NUM_LABELS],initializer=tf.constant_initializer(0.1))
logit = tf.matmul(fc1,fc2_weights)+fc2_biases
return logit
mnist_train.py
import os
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
#define biasc parameters
BATCH_SIZE = 100
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
#PATH INFO
MODEL_SAVE_PATH='./'
MODEL_NAME = 'mnist_CNN_model.ckpt'
def train(mnist):
"""CNN training process
Args:
mnist:
mnist image generator
"""
x = tf.placeholder(tf.float32,
[BATCH_SIZE,mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS],
name='x-input')
y_ = tf.placeholder(tf.float32,
[BATCH_SIZE,mnist_inference.OUTPUT_NODE],
name='y-input')
#forward pass
y = mnist_inference.inference(x,train=True)
global_step = tf.Variable(0,trainable=False)
#compute loss
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
y,tf.argmax(y_,1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean
train_step = tf.train.AdamOptimizer().minimize(loss=loss,
global_step=global_step)
saver = tf.train.Saver()
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAINING_STEPS):
xs,ys = mnist.train.next_batch(BATCH_SIZE)
reshaped_xs = np.reshape(xs,
(BATCH_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS)
)
_,loss_value,step = sess.run(
[train_step,loss,global_step],
feed_dict={x:reshaped_xs,y_:ys}
)
if i% 100 == 0:
print('step(s) :%d'%(step))
if i % 1000 == 0:
print("After %d training step(s), loss:%g"%(step,loss_value))
saver.save(sess,os.path.join(MODEL_SAVE_PATH,MODEL_NAME),
global_step=global_step)
def main(argv=None):
mnist = input_data.read_data_sets('/tmp/data',one_hot=True)
train(mnist)
if __name__ == '__main__':
tf.app.run()
mnist_eval.py
import time
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train
#evalute the model 20 seonds per time
EVAL_INTERVAL_SECS = 20
def evaluate(mnist):
"""evaluate the model 20s per time
Args:
mnist:
mnist image generator
"""
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32,
[None,
mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS],
name='x-input')
y_ = tf.placeholder(tf.float32,
[None,
mnist_inference.OUTPUT_NODE],
name='y-input')
xv = mnist.validation.images
reshaped_xv = np.reshape(xv,
(5000,
mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS)
)
validate_feed={x:reshaped_xv,
y_:mnist.validation.labels}
y = mnist_inference.inference(x,train=False)
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
saver = tf.train.Saver()
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_train.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=validate_feed)
print("After %s training step(s), score:%g"%\
(global_step,accuracy_score))
else:
print("failed to open checkpoint file")
time.sleep(EVAL_INTERVAL_SECS)
def main(argv=None):
mnist = input_data.read_data_sets('/tmp/data',one_hot=True)
evaluate(mnist)
if __name__=='__main__':
tf.app.run()