CIFAR10 程式碼分析詳解——cifar10_train.py
阿新 • • 發佈:2019-01-02
先在這裡種個草,開篇後慢慢補完
引入各種庫,並定義引數
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import time
import tensorflow as tf
import cifar10
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('train_dir', '/tmp/cifar10_train',
"""Directory where to write event logs """
"""and checkpoint.""")
tf.app.flags.DEFINE_integer('max_steps', 1000000,
"""Number of batches to run.""")
tf.app.flags.DEFINE_boolean('log_device_placement', False,
"""Whether to log device placement.""")
tf.app.flags.DEFINE_integer('log_frequency', 10,
"""How often to log results to the console.""")
下面是訓練函式主體
def train():
"""Train CIFAR-10 for a number of steps."""
#定義一個圖,關於Graph的用法查連結
with tf.Graph().as_default():
#獲取global_step,至於為什麼這麼用有待考證。
tf.contrib.framework.get_or_create_global_step(Graph)
#若無輸入圖,則為預設圖
global_step = tf.contrib.framework.get_or_create_global_step()
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images)
# Calculate loss.
loss = cifar10.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = cifar10.train(loss, global_step)
#log部分以後再補充????
class _LoggerHook(tf.train.SessionRunHook):
"""Logs loss and runtime."""
def begin(self):
self._step = -1
self._start_time = time.time()
def before_run(self, run_context):
self._step += 1
return tf.train.SessionRunArgs(loss) # Asks for loss value.
def after_run(self, run_context, run_values):
if self._step % FLAGS.log_frequency == 0:
current_time = time.time()
duration = current_time - self._start_time
self._start_time = current_time
loss_value = run_values.results
examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
sec_per_batch = float(duration / FLAGS.log_frequency)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print (format_str % (datetime.now(), self._step, loss_value,
examples_per_sec, sec_per_batch))
#這裡要找到stop criterion????
with tf.train.MonitoredTrainingSession(
checkpoint_dir=FLAGS.train_dir,
hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
tf.train.NanTensorHook(loss),
_LoggerHook()],
config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement)) as mon_sess:
while not mon_sess.should_stop():
mon_sess.run(train_op)
def main(argv=None): # pylint: disable=unused-argument
cifar10.maybe_download_and_extract()
if tf.gfile.Exists(FLAGS.train_dir):
tf.gfile.DeleteRecursively(FLAGS.train_dir)
tf.gfile.MakeDirs(FLAGS.train_dir)
train()
if __name__ == '__main__':
tf.app.run()
該部分程式碼比較簡單,在主體函式 train() 中先通過 cifar10.distorted_input() 讀取影象和標籤,然後通過cifar10.inference() 進行 logits 的估計,通過cifar10.loss() 來計算損失,再建立一個 train_op=cifar10.train() 來進行模型訓練引數更新,直到滿足 stop criterion。呼叫的函式參見相應的文章。