Python inception_v3.inception_v3_arg_scope方法代码示例

# 需要导入模块: from tensorflow.contrib.slim.python.slim.nets import inception_v3 [as 别名]
# 或者: from tensorflow.contrib.slim.python.slim.nets.inception_v3 import inception_v3_arg_scope [as 别名]
def build_graph(self):
    """Forms the core by building a wrapper around the inception graph.

      Here we add the necessary input & output tensors, to decode jpegs,
      serialize embeddings, restore from checkpoint etc.

      To use other Inception models modify this file. Note that to use other
      models beside Inception, you should make sure input_shape matches
      their input. Resizing or other modifications may be necessary as well.
      See tensorflow/contrib/slim/python/slim/nets/inception_v3.py for
      details about InceptionV3.

    Returns:
      input_jpeg: A tensor containing raw image bytes as the input layer.
      embedding: The embeddings tensor, that will be materialized later.
    """

    input_jpeg = tf.placeholder(tf.string, shape=None)
    image = tf.image.decode_jpeg(input_jpeg, channels=self.CHANNELS)

    # Note resize expects a batch_size, but we are feeding a single image.
    # So we have to expand then squeeze.  Resize returns float32 in the
    # range [0, uint8_max]
    image = tf.expand_dims(image, 0)

    # convert_image_dtype also scales [0, uint8_max] -> [0 ,1).
    image = tf.image.convert_image_dtype(image, dtype=tf.float32)
    image = tf.image.resize_bilinear(
        image, [self.HEIGHT, self.WIDTH], align_corners=False)

    # Then rescale range to [-1, 1) for Inception.
    image = tf.subtract(image, 0.5)
    inception_input = tf.multiply(image, 2.0)

    # Build Inception layers, which expect a tensor of type float from [-1, 1)
    # and shape [batch_size, height, width, channels].
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      _, end_points = inception.inception_v3(inception_input, is_training=False)

    embedding = end_points['PreLogits']
    return input_jpeg, embedding 

# 需要导入模块: from tensorflow.contrib.slim.python.slim.nets import inception_v3 [as 别名]
# 或者: from tensorflow.contrib.slim.python.slim.nets.inception_v3 import inception_v3_arg_scope [as 别名]
def testModelHasExpectedNumberOfParameters(self):
    batch_size = 5
    height, width = 299, 299
    inputs = random_ops.random_uniform((batch_size, height, width, 3))
    with arg_scope(inception_v3.inception_v3_arg_scope()):
      inception_v3.inception_v3_base(inputs)
    total_params, _ = model_analyzer.analyze_vars(
        variables_lib.get_model_variables())
    self.assertAlmostEqual(21802784, total_params) 

# 需要导入模块: from tensorflow.contrib.slim.python.slim.nets import inception_v3 [as 别名]
# 或者: from tensorflow.contrib.slim.python.slim.nets.inception_v3 import inception_v3_arg_scope [as 别名]
def build_inception_graph(self):
    """Builds an inception graph and add the necessary input & output tensors.

      To use other Inception models modify this file. Also preprocessing must be
      modified accordingly.

      See tensorflow/contrib/slim/python/slim/nets/inception_v3.py for
      details about InceptionV3.

    Returns:
      input_jpeg: A placeholder for jpeg string batch that allows feeding the
                  Inception layer with image bytes for prediction.
      inception_embeddings: The embeddings tensor.
    """

    # These constants are set by Inception v3's expectations.
    height = 299
    width = 299
    channels = 3

    image_str_tensor = tf.placeholder(tf.string, shape=[None])

    # The CloudML Prediction API always "feeds" the Tensorflow graph with
    # dynamic batch sizes e.g. (?,).  decode_jpeg only processes scalar
    # strings because it cannot guarantee a batch of images would have
    # the same output size.  We use tf.map_fn to give decode_jpeg a scalar
    # string from dynamic batches.
    def decode_and_resize(image_str_tensor):
      """Decodes jpeg string, resizes it and returns a uint8 tensor."""
      image = tf.image.decode_jpeg(image_str_tensor, channels=channels)
      # Note resize expects a batch_size, but tf_map supresses that index,
      # thus we have to expand then squeeze.  Resize returns float32 in the
      # range [0, uint8_max]
      image = tf.expand_dims(image, 0)
      image = tf.image.resize_bilinear(
          image, [height, width], align_corners=False)
      image = tf.squeeze(image, squeeze_dims=[0])
      image = tf.cast(image, dtype=tf.uint8)
      return image

    image = tf.map_fn(
        decode_and_resize, image_str_tensor, back_prop=False, dtype=tf.uint8)
    # convert_image_dtype, also scales [0, uint8_max] -> [0 ,1).
    image = tf.image.convert_image_dtype(image, dtype=tf.float32)

    # Then shift images to [-1, 1) for Inception.
    image = tf.subtract(image, 0.5)
    image = tf.multiply(image, 2.0)

    # Build Inception layers, which expect A tensor of type float from [-1, 1)
    # and shape [batch_size, height, width, channels].
    with slim.arg_scope(inception.inception_v3_arg_scope()):
      _, end_points = inception.inception_v3(image, is_training=False)

    inception_embeddings = end_points['PreLogits']
    inception_embeddings = tf.squeeze(
        inception_embeddings, [1, 2], name='SpatialSqueeze')
    return image_str_tensor, inception_embeddings