1.mnist_inference
import tensorflow as tf
input_node = 784
output_node = 10
layer1_node = 500
def get_weight_variable(shape, regularizer) :
weights = tf.get_variable("weights", shape,
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None :
tf.add_to_collection('losses', regularizer(weights))
return weights
def inference(input_tensor, regularizer) :
with tf.variable_scope('layer1', reuse=tf.AUTO_REUSE) :
weights = get_weight_variable([input_node, layer1_node], regularizer)
biases = tf.get_variable("biases", [layer1_node],
initializer=tf.constant_initializer(0.0))
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)
with tf.variable_scope('layer2', reuse=tf.AUTO_REUSE) :
weights = get_weight_variable([layer1_node, output_node], regularizer)
biases = tf.get_variable("biases", [output_node],
initializer=tf.constant_initializer(0.0))
layer2 = tf.matmul(layer1, weights) + biases
return layer2
2.mnist_train
import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
batch_size = 100
learning_rate_base = 0.8
learning_rate_decay = 0.99
regularaztion_rate = 0.0001
training_steps = 30000
moving_average_decay = 0.99
model_save_path = "/path/to/model/"
model_name = "model.ckpt"
def train(mnist) :
x = tf.placeholder(tf.float32, [None, mnist_inference.input_node], name='x-input')
y_= tf.placeholder(tf.float32, [None, mnist_inference.output_node], name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(regularaztion_rate)
y = mnist_inference.inference(x, regularizer)
global_step = tf.Variable(0, trainable=False)
variable_averages = tf.train.ExponentialMovingAverage(
moving_average_decay, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
variable_names = [v.name for v in tf.trainable_variables()]
print(variable_names)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=y, labels=tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean + 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)
train_step = tf.train.GradientDescentOptimizer(learning_rate)\
.minimize(loss, global_step=global_step)
# 如果global_step非None，该操作还会为global_step做自增操作
with tf.control_dependencies([train_step, variables_averages_op]) :
train_op = tf.no_op(name='train')
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)
_, loss_value, step = sess.run([train_op, loss, global_step],
feed_dict={x:xs, y_:ys})
if i % 500 == 0 :
print("After %d training step(s), loss in training "
"batch is %f." % (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("/path/to/MNIST_data", one_hot=True)
train(mnist)
if __name__ == '__main__' :
tf.app.run()
3.mnist_eval
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train
# 10s加载一次新模型
interval = 10
def evaluate(mnist) :
with tf.Graph().as_default() as g :
x = tf.placeholder(tf.float32, [None, mnist_inference.input_node],
name='x-input')
y_ = tf.placeholder(tf.float32, [None, mnist_inference.output_node],
name='y-input')
validate_feed = {x : mnist.validation.images,
y_: mnist.validation.labels}
y = mnist_inference.inference(x, None)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
variable_averages = tf.train.ExponentialMovingAverage(
mnist_train.moving_average_decay)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
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), validation "
"accuracy = %g" % (global_step, accuracy_score))
else :
print('No checkpoint file found')
return
time.sleep(interval)
def main(argv=None) :
mnist = input_data.read_data_sets("/path/to/MNIST_data", one_hot=True)
evaluate(mnist)
if __name__ == '__main__' :
tf.app.run()
