tensorflow图像分类实战解析（下）

  global_step = tf.Variable(0, name='global_step', trainable=False)
  train_op = optimizer.minimize(loss, global_step=global_step)
  return train_op

设定最小化目标以及最大步长

def evaluation(logits, labels):
  correct = tf.nn.in_top_k(logits, labels, 1)
  return tf.reduce_sum(tf.cast(correct, tf.int32))

衡量标签得到的数值和ground-truth之间的关系

def placeholder_inputs(batch_size):
  images_placeholder = tf.placeholder(tf.float32, shape=(batch_size,IMAGE_PIXELS))

这里的batchsize定义了placeholder一次性读入图片的数目，所以理论上应该是有能力不需要将所有图片全部读入内存中再进行处理的。这个我还得继续研究

  labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size))
  return images_placeholder, labels_placeholder



def fill_feed_dict(images_feed,labels_feed, images_pl, labels_pl):
  feed_dict = {
      images_pl: images_feed,
      labels_pl: labels_feed,
  }
  return feed_dict

很重要的feed-dict 用来灌数据，其实就是在建立一个字典

def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):
  # And run one epoch of eval.

评价现在参数训练效果的函数

  true_count = 0  # Counts the number of correct predictions.
  steps_per_epoch = 4 // FLAGS.batch_size
  num_examples &#