def testRaiseValueErrorWithInvalidDepthMultiplier(self):
    batch_size = 5
    height, width = 224, 224
    num_classes = 1000

    inputs = tf.random_uniform((batch_size, height, width, 3))
    with self.assertRaises(ValueError):
      _ = mobilenet_v1.mobilenet_v1(
          inputs, num_classes, depth_multiplier=-0.1)
    with self.assertRaises(ValueError):
      _ = mobilenet_v1.mobilenet_v1(
          inputs, num_classes, depth_multiplier=0.0)

def build_model():
  """Build the mobilenet_v1 model for evaluation.

  Returns:
    g: graph with rewrites after insertion of quantization ops and batch norm
    folding.
    eval_ops: eval ops for inference.
    variables_to_restore: List of variables to restore from checkpoint.
  """
  g = tf.Graph()
  with g.as_default():
    inputs, labels = imagenet_input(is_training=False)

    scope = mobilenet_v1.mobilenet_v1_arg_scope(
        is_training=False, weight_decay=0.0)
    with slim.arg_scope(scope):
      logits, _ = mobilenet_v1.mobilenet_v1(
          inputs,
          is_training=False,
          depth_multiplier=FLAGS.depth_multiplier,
          num_classes=FLAGS.num_classes)

    if FLAGS.quantize:
      tf.contrib.quantize.create_eval_graph()

    eval_ops = metrics(logits, labels)

  return g, eval_ops

  def testTrainEvalWithReuse(self):
    train_batch_size = 5
    eval_batch_size = 2
    height, width = 150, 150
    num_classes = 1000

    train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
    mobilenet_v1.mobilenet_v1(train_inputs, num_classes)
    eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
    logits, _ = mobilenet_v1.mobilenet_v1(eval_inputs, num_classes,
                                          reuse=True)
    predictions = tf.argmax(logits, 1)

    with self.test_session() as sess:
      sess.run(tf.global_variables_initializer())
      output = sess.run(predictions)
      self.assertEquals(output.shape, (eval_batch_size,))

  def testBuildEndPointsWithDepthMultiplierLessThanOne(self):
    batch_size = 5
    height, width = 224, 224
    num_classes = 1000

    inputs = tf.random_uniform((batch_size, height, width, 3))
    _, end_points = mobilenet_v1.mobilenet_v1(inputs, num_classes)

    endpoint_keys = [key for key in end_points.keys() if key.startswith('Conv')]

    _, end_points_with_multiplier = mobilenet_v1.mobilenet_v1(
        inputs, num_classes, scope='depth_multiplied_net',
        depth_multiplier=0.5)

    for key in endpoint_keys:
      original_depth = end_points[key].get_shape().as_list()[3]
      new_depth = end_points_with_multiplier[key].get_shape().as_list()[3]
      self.assertEqual(0.5 * original_depth, new_depth)

  def testLogitsNotSqueezed(self):
    num_classes = 25
    images = tf.random_uniform([1, 224, 224, 3])
    logits, _ = mobilenet_v1.mobilenet_v1(images,
                                          num_classes=num_classes,
                                          spatial_squeeze=False)

    with self.test_session() as sess:
      tf.global_variables_initializer().run()
      logits_out = sess.run(logits)
      self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])

  def testBuildPreLogitsNetwork(self):
    batch_size = 5
    height, width = 224, 224
    num_classes = None

    inputs = tf.random_uniform((batch_size, height, width, 3))
    net, end_points = mobilenet_v1.mobilenet_v1(inputs, num_classes)
    self.assertTrue(net.op.name.startswith('MobilenetV1/Logits/AvgPool'))
    self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 1024])
    self.assertFalse('Logits' in end_points)
    self.assertFalse('Predictions' in end_points)

  def testHalfSizeImages(self):
    batch_size = 5
    height, width = 112, 112
    num_classes = 1000

    inputs = tf.random_uniform((batch_size, height, width, 3))
    logits, end_points = mobilenet_v1.mobilenet_v1(inputs, num_classes)
    self.assertTrue(logits.op.name.startswith('MobilenetV1/Logits'))
    self.assertListEqual(logits.get_shape().as_list(),
                         [batch_size, num_classes])
    pre_pool = end_points['Conv2d_13_pointwise']
    self.assertListEqual(pre_pool.get_shape().as_list(),
                         [batch_size, 4, 4, 1024])

  def testBuildClassificationNetwork(self):
    batch_size = 5
    height, width = 224, 224
    num_classes = 1000

    inputs = tf.random_uniform((batch_size, height, width, 3))
    logits, end_points = mobilenet_v1.mobilenet_v1(inputs, num_classes)
    self.assertTrue(logits.op.name.startswith('MobilenetV1/Logits'))
    self.assertListEqual(logits.get_shape().as_list(),
                         [batch_size, num_classes])
    self.assertTrue('Predictions' in end_points)
    self.assertListEqual(end_points['Predictions'].get_shape().as_list(),
                         [batch_size, num_classes])

  def testEvaluation(self):
    batch_size = 2
    height, width = 224, 224
    num_classes = 1000

    eval_inputs = tf.random_uniform((batch_size, height, width, 3))
    logits, _ = mobilenet_v1.mobilenet_v1(eval_inputs, num_classes,
                                          is_training=False)
    predictions = tf.argmax(logits, 1)

    with self.test_session() as sess:
      sess.run(tf.global_variables_initializer())
      output = sess.run(predictions)
      self.assertEquals(output.shape, (batch_size,))

def build_model():
  """Builds graph for model to train with rewrites for quantization.

  Returns:
    g: Graph with fake quantization ops and batch norm folding suitable for
    training quantized weights.
    train_tensor: Train op for execution during training.
  """
  g = tf.Graph()
  with g.as_default(), tf.device(
      tf.train.replica_device_setter(FLAGS.ps_tasks)):
    inputs, labels = imagenet_input(is_training=True)
    with slim.arg_scope(mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)):
      logits, _ = mobilenet_v1.mobilenet_v1(
          inputs,
          is_training=True,
          depth_multiplier=FLAGS.depth_multiplier,
          num_classes=FLAGS.num_classes)

    tf.losses.softmax_cross_entropy(labels, logits)

    # Call rewriter to produce graph with fake quant ops and folded batch norms
    # quant_delay delays start of quantization till quant_delay steps, allowing
    # for better model accuracy.
    if FLAGS.quantize:
      tf.contrib.quantize.create_training_graph(quant_delay=get_quant_delay())

    total_loss = tf.losses.get_total_loss(name='total_loss')
    # Configure the learning rate using an exponential decay.
    num_epochs_per_decay = 2.5
    imagenet_size = 1271167
    decay_steps = int(imagenet_size / FLAGS.batch_size * num_epochs_per_decay)

    learning_rate = tf.train.exponential_decay(
        get_learning_rate(),
        tf.train.get_or_create_global_step(),
        decay_steps,
        _LEARNING_RATE_DECAY_FACTOR,
        staircase=True)
    opt = tf.train.GradientDescentOptimizer(learning_rate)

    train_tensor = slim.learning.create_train_op(
        total_loss,
        optimizer=opt)

  slim.summaries.add_scalar_summary(total_loss, 'total_loss', 'losses')
  slim.summaries.add_scalar_summary(learning_rate, 'learning_rate', 'training')
  return g, train_tensor

  def testUnknowBatchSize(self):
    batch_size = 1
    height, width = 224, 224
    num_classes = 1000

    inputs = tf.placeholder(tf.float32, (None, height, width, 3))
    logits, _ = mobilenet_v1.mobilenet_v1(inputs, num_classes)
    self.assertTrue(logits.op.name.startswith('MobilenetV1/Logits'))
    self.assertListEqual(logits.get_shape().as_list(),
                         [None, num_classes])
    images = tf.random_uniform((batch_size, height, width, 3))

    with self.test_session() as sess:
      sess.run(tf.global_variables_initializer())
      output = sess.run(logits, {inputs: images.eval()})
      self.assertEquals(output.shape, (batch_size, num_classes))

 def testUnknownImageShape(self):
   tf.reset_default_graph()
   batch_size = 2
   height, width = 224, 224
   num_classes = 1000
   input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
   with self.test_session() as sess:
     inputs = tf.placeholder(tf.float32, shape=(batch_size, None, None, 3))
     logits, end_points = mobilenet_v1.mobilenet_v1(inputs, num_classes)
     self.assertTrue(logits.op.name.startswith('MobilenetV1/Logits'))
     self.assertListEqual(logits.get_shape().as_list(),
                          [batch_size, num_classes])
     pre_pool = end_points['Conv2d_13_pointwise']
     feed_dict = {inputs: input_np}
     tf.global_variables_initializer().run()
     pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
     self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])

def freeze_mobilenet(meta_file, img_size=224, factor=1.0, num_classes=1001):

  tf.reset_default_graph()

  inp = tf.placeholder(tf.float32,
                      shape=(None, img_size, img_size, 3),
                      name="input")

  is_training=False
  weight_decay = 0.0
  arg_scope = mobilenet_v1.mobilenet_v1_arg_scope(weight_decay=weight_decay)
  with slim.arg_scope(arg_scope):
    logits, _ = mobilenet_v1.mobilenet_v1(inp,
                                          num_classes=num_classes,
                                          is_training=is_training,
                                          depth_multiplier=factor)

  predictions = tf.contrib.layers.softmax(logits)
  output = tf.identity(predictions, name='output')

  ckpt_file = meta_file.replace('.meta', '')
  output_graph_fn = ckpt_file.replace('.ckpt', '.pb')
  output_node_names = "output"

  rest_var = slim.get_variables_to_restore()

  with tf.Session() as sess:
    graph = tf.get_default_graph()
    input_graph_def = graph.as_graph_def()

    saver = tf.train.Saver(rest_var)
    saver.restore(sess, ckpt_file)

    # We use a built-in TF helper to export variables to constant
    output_graph_def = graph_util.convert_variables_to_constants(
        sess, # The session is used to retrieve the weights
        input_graph_def, # The graph_def is used to retrieve the nodes
        # The output node names are used to select the useful nodes
        output_node_names.split(",")
    )

    # Finally we serialize and dump the output graph to the filesystem
    with tf.gfile.GFile(output_graph_fn, "wb") as f:
        f.write(output_graph_def.SerializeToString())
    print("{} ops in the final graph.".format(len(output_graph_def.node)))

 def create(self, images, num_classes, is_training):
   """See baseclass."""
   with slim.arg_scope(mobilenet_v1.mobilenet_v1_arg_scope()):
     _, endpoints = mobilenet_v1.mobilenet_v1(
         inputs=images, num_classes=num_classes, is_training=is_training)
     return endpoints