def train():
with tf.Graph().as_default():
global_step = tf.Variable(initial_value=0, trainable=False)
img_batch, label_batch = input_dateset.preprocess_input_data()
logits = forward_prop.network(img_batch)
total_loss = forward_prop.loss(logits, label_batch)
one_step_gradient_update = forward_prop.one_step_train(
total_loss, globle_step)
saver = tf.train.Saver(var_list=tf.all_varibale())
all_summary_obj = tf.merge_all_summaries()
initiate_variables = tf.initialize_all_variables()
with tf.Session(config=tf.ConfigProto(
log_device_placement=False)) as sess:
sess.run(initialize_variables)
tf.train.start_queue_runners(sess=sess)
Event_writer = tf.train.summaryWriter(logdir=event_log_path,
graph=sess.graph)
for step in range(max_iter_num):
_, loss_value = sess.run(
fetches=[one_step_gradient_update, total_loss])
assert not np.isnan(loss_value)
if step % 10 == 0:
print('step %d, the loss_vlaue is %.2f' %
(step, loss_value))
if step % 100 == 0:
all_summaries = sess.run(all_summary_obj)
Event_writer.add_summary(summary=all_summaries,
global_step=step)
if step % 1000 == 0 or (step + 1) == max_iter_num:
variable_save_path = os.path.join(checkpoint_path,
'model-parameter.bin')
saver.save(sess, variables_save_path, global_step=step)
def evaluate(): with tf.Graph().as_default() as g: img_batch, labels = input_dataset.input_data(eval_flag=True) logits = forward_prop.network(img_batch) predict_true_or_false = tf.nn.in_top_k(predictions=logits, targets=labels, k=1) moving_average_op = tf.trian.ExponentialMovingAverage(decay=forward_prop, moving_average_decay) variables_to_restore = moving_average_op.variables_to_restore() saver = tf.train.Saver(var_list=variables_to_restore) summary_op = tf.merge_all_summaries() summary_writer = tf.train.SummaryWriter(logdir='./event-log-test', graph=g) eval_once(summary_op, summary_writer, saver, predict_true_or_false)
def evaluate():
with tf.Graph().as_default() as g:
img_batch, labels = input_dataset.input_data(eval_flag=True)#读入测试数据集
logits = forward_prop.network(img_batch)#使用moving average操作前的模型参数，计算模型输出值
#判断targets是否在前k个predictions里面，当k=1时等价于常规的计算正确率的方法，sess.run(predict_true_or_false)会执行符号计算
predict_true_or_false = tf.nn.in_top_k(predictions=logits, targets=labels, k=1)
#恢复moving average操作后的模型参数
moving_average_op = tf.train.ExponentialMovingAverage(decay=forward_prop.moving_average_decay)
#返回要恢复的names到Variables的映射，也即一个map映射。如果一个变量有moving average,就使用moving average变量名作为the restore
# name, 否则就使用变量名
variables_to_restore = moving_average_op.variables_to_restore()
saver = tf.train.Saver(var_list=variables_to_restore)
summary_op = tf.merge_all_summaries() #创建序列化后的summary对象
#创建一个event file,用于之后写summary对象到logdir目录下的文件中
summary_writer = tf.train.SummaryWriter(logdir='./event-log-test', graph=g)
eval_once(summary_op, summary_writer, saver, predict_true_or_false)
def train():
with tf.Graph().as_default(): #指定当前图为默认graph
global_step = tf.Variable(
initial_value=0, trainable=False
) #设置trainable=False,是因为防止训练过程中对global_step变量也进行滑动更新操作
img_batch, label_batch = input_dataset.preprocess_input_data(
) #输入图像的预处理，包括亮度、对比度、图像翻转等操作
# img_batch, label_batch = input_dataset.input_data(eval_flag=False)
logits = forward_prop.network(img_batch) #图像信号的前向传播过程
total_loss = forward_prop.loss(logits, label_batch) #计算损失
one_step_gradient_update = forward_prop.one_step_train(
total_loss, global_step) #返回一步梯度更新操作
#创建一个saver对象，用于保存参数到文件中
saver = tf.train.Saver(var_list=tf.all_variables(
)) #tf.all_variables return a list of `Variable` objects
all_summary_obj = tf.merge_all_summaries(
) #返回所有summary对象先merge再serialize后的的字符串类型tensor
initiate_variables = tf.initialize_all_variables()
#log_device_placement参数可以记录每一个操作使用的设备，这里的操作比较多，就不需要记录了，故设置为False
with tf.Session(config=tf.ConfigProto(
log_device_placement=False)) as sess:
sess.run(initiate_variables) #变量初始化
tf.train.start_queue_runners(sess=sess) #启动所有的queuerunners
Event_writer = tf.train.SummaryWriter(logdir=event_log_path,
graph=sess.graph)
for step in range(max_iter_num):
_, loss_value = sess.run(
fetches=[one_step_gradient_update, total_loss])
assert not np.isnan(loss_value) #用于验证当前迭代计算出的loss_value是否合理
if step % 10 == 0:
print('step %d, the loss_value is %.2f' %
(step, loss_value))
if step % 100 == 0:
# 添加`Summary`协议缓存到事件文件中，故不能写total_loss变量到事件文件中，因为这里的total_loss为普通的tensor类型
all_summaries = sess.run(all_summary_obj)
Event_writer.add_summary(summary=all_summaries,
global_step=step)
if step % 1000 == 0 or (step + 1) == max_iter_num:
variables_save_path = os.path.join(
checkpoint_path,
'model-parameters.bin') #路径合并，返回合并后的字符串
saver.save(
sess, variables_save_path, global_step=step
) #把所有变量（包括moving average前后的模型参数）保存在variables_save_path路径下