Python mnist.loss方法代码示例

# 需要导入模块: from tensorflow.examples.tutorials.mnist import mnist [as 别名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import loss [as 别名]
def main(unused_argv):
  if FLAGS.log_dir is None or FLAGS.log_dir == "":
    raise ValueError("Must specify an explicit `log_dir`")
  if FLAGS.data_dir is None or FLAGS.data_dir == "":
    raise ValueError("Must specify an explicit `data_dir`")

  device, target = device_and_target()
  with tf.device(device):
    images = tf.placeholder(tf.float32, [None, 784], name='image_input')
    labels = tf.placeholder(tf.float32, [None], name='label_input')
    data = read_data_sets(FLAGS.data_dir,
            one_hot=False,
            fake_data=False)
    logits = mnist.inference(images, FLAGS.hidden1, FLAGS.hidden2)
    loss = mnist.loss(logits, labels)
    loss = tf.Print(loss, [loss], message="Loss = ")
    train_op = mnist.training(loss, FLAGS.learning_rate)

  with tf.train.MonitoredTrainingSession(
      master=target,
      is_chief=(FLAGS.task_index == 0),
      checkpoint_dir=FLAGS.log_dir) as sess:
    while not sess.should_stop():
      xs, ys = data.train.next_batch(FLAGS.batch_size, fake_data=False)
      sess.run(train_op, feed_dict={images:xs, labels:ys}) 

# 需要导入模块: from tensorflow.examples.tutorials.mnist import mnist [as 别名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import loss [as 别名]
def inference(inp, num_clusters, hidden1_units, hidden2_units):
  """Build the MNIST model up to where it may be used for inference.

  Args:
    inp: input data
    num_clusters: number of clusters of input features to train.
    hidden1_units: Size of the first hidden layer.
    hidden2_units: Size of the second hidden layer.

  Returns:
    logits: Output tensor with the computed logits.
    clustering_loss: Clustering loss.
    kmeans_training_op: An op to train the clustering.
  """
  # Clustering
  kmeans = tf.contrib.factorization.KMeans(
      inp,
      num_clusters,
      distance_metric=tf.contrib.factorization.COSINE_DISTANCE,
      # TODO(agarwal): kmeans++ is currently causing crash in dbg mode.
      # Enable this after fixing.
      # initial_clusters=tf.contrib.factorization.KMEANS_PLUS_PLUS_INIT,
      use_mini_batch=True)

  all_scores, _, clustering_scores, kmeans_training_op = kmeans.training_graph()
  # Some heuristics to approximately whiten this output.
  all_scores = (all_scores[0] - 0.5) * 5
  # Here we avoid passing the gradients from the supervised objective back to
  # the clusters by creating a stop_gradient node.
  all_scores = tf.stop_gradient(all_scores)
  clustering_loss = tf.reduce_sum(clustering_scores[0])
  # Hidden 1
  with tf.name_scope('hidden1'):
    weights = tf.Variable(
        tf.truncated_normal([num_clusters, hidden1_units],
                            stddev=1.0 / math.sqrt(float(IMAGE_PIXELS))),
        name='weights')
    biases = tf.Variable(tf.zeros([hidden1_units]),
                         name='biases')
    hidden1 = tf.nn.relu(tf.matmul(all_scores, weights) + biases)
  # Hidden 2
  with tf.name_scope('hidden2'):
    weights = tf.Variable(
        tf.truncated_normal([hidden1_units, hidden2_units],
                            stddev=1.0 / math.sqrt(float(hidden1_units))),
        name='weights')
    biases = tf.Variable(tf.zeros([hidden2_units]),
                         name='biases')
    hidden2 = tf.nn.relu(tf.matmul(hidden1, weights) + biases)
  # Linear
  with tf.name_scope('softmax_linear'):
    weights = tf.Variable(
        tf.truncated_normal([hidden2_units, NUM_CLASSES],
                            stddev=1.0 / math.sqrt(float(hidden2_units))),
        name='weights')
    biases = tf.Variable(tf.zeros([NUM_CLASSES]),
                         name='biases')
    logits = tf.matmul(hidden2, weights) + biases
  return logits, clustering_loss, kmeans_training_op