def train(mnist):
# 将处理输入数据的计算都放在名字为“input”的命名空间下。
with tf.name_scope('input'):
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)
# 将处理滑动平均相关的计算都放在名为moving_average的命名空间下。
with tf.name_scope("moving_average"):
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variable_averages_op = variable_averages.apply(tf.trainable_variables())
# 将计算损失函数相关的计算都放在名为loss_function的命名空间下。
with tf.name_scope("loss_function"):
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'))
# 将定义学习率、优化方法以及每一轮训练需要训练的操作都放在名字为“train_step”的命名空间下。
with tf.name_scope("train_step"):
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)
with tf.control_dependencies([train_step, variable_averages_op]):
train_op = tf.no_op(name='train')
# 初始化Tensorflow持久化类。
saver = tf.train.Saver()
with tf.Session() as sess:
tf.global_variables_initializer().run()
# 在训练过程中不再测试模型在验证数据上的表现，验证和测试的过程将会有一个独立的程序来完成。
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})
# 每1000轮保存一次模型。
if i % 1000 == 0:
# 输出当前的训练情况。这里只输出了模型在当前训练batch上的损失函数大小。通过损失函数的大小可以大概了解到
# 训练的情况。在验证数据集上的正确率信息会有一个独立的程序来生成。
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
# 保存当前的模型。注意这里给出了global_step参数，这样可以让每个被保存的模型的文件名末尾加上训练的轮数，
# 比如“model.ckpt-1000” 表示训练1000轮之后得到的模型。
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
# 将当前的计算图输出到TensorBoard日志文件。
writer = tf.summary.FileWriter("./log", tf.get_default_graph())
writer.close()
def get_loss(x, y_, regularizer, scope, reuse_variables=None):
# 沿用前面定义的函数来计算神经网络的前向传播结果。
with tf.variable_scope(tf.get_variable_scope(), reuse=reuse_variables):
y = mnist_inference.inference(x, regularizer)
# 计算交叉熵损失。
cross_entropy = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=y_))
# 计算当前GPU上计算得到的正则化损失。
regularization_loss = tf.add_n(tf.get_collection('losses', scope))
# 计算最终的总损失。
loss = cross_entropy + regularization_loss
return loss
def train(mnist):
# 输入数据的命名空间。
with tf.name_scope('input'):
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)
# 处理滑动平均的命名空间。
with tf.name_scope("moving_average"):
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY, global_step)
variable_averages_op = variable_averages.apply(
tf.trainable_variables())
# 计算损失函数的命名空间。
with tf.name_scope("loss_function"):
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'))
# 定义学习率、优化方法及每一轮执行训练操作的命名空间。
with tf.name_scope("train_step"):
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)
with tf.control_dependencies([train_step, variable_averages_op]):
train_op = tf.no_op(name='train')
# 训练模型
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 % 1000 == 0:
print(
"After %d training step(s), loss on training batch is %g."
% (i, loss_value))
# 计算MNIST测试数据对应的输出层矩阵。
final_result = sess.run(y, feed_dict={x: mnist.test.images})
# 返回输出层矩阵的值。
return final_result