Python object_detection.protos.hyperparams_pb2.Hyperparams() Examples

def test_variance_in_range_with_variance_scaling_initializer_uniform(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        variance_scaling_initializer {
          factor: 2.0
          mode: FAN_IN
          uniform: true
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    initializer = conv_scope_arguments['weights_initializer']
    self._assert_variance_in_range(initializer, shape=[100, 40],
                                   variance=2. / 100.) 

def test_build_default_mask_rcnn_box_predictor(self):
    box_predictor_proto = box_predictor_pb2.BoxPredictor()
    box_predictor_proto.mask_rcnn_box_predictor.fc_hyperparams.op = (
        hyperparams_pb2.Hyperparams.FC)
    box_predictor = box_predictor_builder.build(
        argscope_fn=mock.Mock(return_value='arg_scope'),
        box_predictor_config=box_predictor_proto,
        is_training=True,
        num_classes=90)
    self.assertFalse(box_predictor._use_dropout)
    self.assertAlmostEqual(box_predictor._dropout_keep_prob, 0.5)
    self.assertEqual(box_predictor.num_classes, 90)
    self.assertTrue(box_predictor._is_training)
    self.assertEqual(box_predictor._box_code_size, 4)
    self.assertFalse(box_predictor._predict_instance_masks)
    self.assertFalse(box_predictor._predict_keypoints) 

def _build_activation_fn(activation_fn):
  """Builds a callable activation from config.

  Args:
    activation_fn: hyperparams_pb2.Hyperparams.activation

  Returns:
    Callable activation function.

  Raises:
    ValueError: On unknown activation function.
  """
  if activation_fn == hyperparams_pb2.Hyperparams.NONE:
    return None
  if activation_fn == hyperparams_pb2.Hyperparams.RELU:
    return tf.nn.relu
  if activation_fn == hyperparams_pb2.Hyperparams.RELU_6:
    return tf.nn.relu6
  raise ValueError('Unknown activation function: {}'.format(activation_fn)) 

def _build_arg_scope_with_hyperparams(self,
                                        op_type=hyperparams_pb2.Hyperparams.FC):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def test_get_instance_masks(self):
    image_features = tf.random_uniform([2, 7, 7, 3], dtype=tf.float32)
    mask_box_predictor = box_predictor.MaskRCNNBoxPredictor(
        is_training=False,
        num_classes=5,
        fc_hyperparams=self._build_arg_scope_with_hyperparams(),
        use_dropout=False,
        dropout_keep_prob=0.5,
        box_code_size=4,
        conv_hyperparams=self._build_arg_scope_with_hyperparams(
            op_type=hyperparams_pb2.Hyperparams.CONV),
        predict_instance_masks=True)
    box_predictions = mask_box_predictor.predict(
        image_features, num_predictions_per_location=1, scope='BoxPredictor')
    mask_predictions = box_predictions[box_predictor.MASK_PREDICTIONS]
    self.assertListEqual([2, 1, 5, 14, 14],
                         mask_predictions.get_shape().as_list()) 

def test_build_default_mask_rcnn_box_predictor(self):
    box_predictor_proto = box_predictor_pb2.BoxPredictor()
    box_predictor_proto.mask_rcnn_box_predictor.fc_hyperparams.op = (
        hyperparams_pb2.Hyperparams.FC)
    box_predictor = box_predictor_builder.build(
        argscope_fn=mock.Mock(return_value='arg_scope'),
        box_predictor_config=box_predictor_proto,
        is_training=True,
        num_classes=90)
    self.assertFalse(box_predictor._use_dropout)
    self.assertAlmostEqual(box_predictor._dropout_keep_prob, 0.5)
    self.assertEqual(box_predictor.num_classes, 90)
    self.assertTrue(box_predictor._is_training)
    self.assertEqual(box_predictor._box_code_size, 4)
    self.assertFalse(box_predictor._predict_instance_masks)
    self.assertFalse(box_predictor._predict_keypoints) 

def test_separable_conv2d_and_conv2d_and_transpose_have_same_parameters(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l1_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    kwargs_1, kwargs_2, kwargs_3 = scope.values()
    self.assertDictEqual(kwargs_1, kwargs_2)
    self.assertDictEqual(kwargs_1, kwargs_3) 

def test_return_l1_regularized_weights(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l1_regularizer {
          weight: 0.5
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    regularizer = conv_scope_arguments['weights_regularizer']
    weights = np.array([1., -1, 4., 2.])
    with self.test_session() as sess:
      result = sess.run(regularizer(tf.constant(weights)))
    self.assertAllClose(np.abs(weights).sum() * 0.5, result) 

def test_return_l2_regularizer_weights(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
          weight: 0.42
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]

    regularizer = conv_scope_arguments['weights_regularizer']
    weights = np.array([1., -1, 4., 2.])
    with self.test_session() as sess:
      result = sess.run(regularizer(tf.constant(weights)))
    self.assertAllClose(np.power(weights, 2).sum() / 2.0 * 0.42, result) 

def test_do_not_use_batch_norm_if_default(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    self.assertEqual(conv_scope_arguments['normalizer_fn'], None)
    self.assertEqual(conv_scope_arguments['normalizer_params'], None) 

def test_use_none_activation(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
      activation: NONE
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    self.assertEqual(conv_scope_arguments['activation_fn'], None) 

def test_use_relu_activation(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
      activation: RELU
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    self.assertEqual(conv_scope_arguments['activation_fn'], tf.nn.relu) 

def test_use_relu_6_activation(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
      activation: RELU_6
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    self.assertEqual(conv_scope_arguments['activation_fn'], tf.nn.relu6) 

def test_variance_in_range_with_variance_scaling_initializer_fan_in(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        variance_scaling_initializer {
          factor: 2.0
          mode: FAN_IN
          uniform: false
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    initializer = conv_scope_arguments['weights_initializer']
    self._assert_variance_in_range(initializer, shape=[100, 40],
                                   variance=2. / 100.) 

def test_variance_in_range_with_variance_scaling_initializer_fan_avg(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        variance_scaling_initializer {
          factor: 2.0
          mode: FAN_AVG
          uniform: false
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    initializer = conv_scope_arguments['weights_initializer']
    self._assert_variance_in_range(initializer, shape=[100, 40],
                                   variance=4. / (100. + 40.)) 

def _build_arg_scope_with_hyperparams(self,
                                        op_type=hyperparams_pb2.Hyperparams.FC):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def test_variance_in_range_with_truncated_normal_initializer(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
          mean: 0.0
          stddev: 0.8
        }
      }
    """
    conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
    scope = hyperparams_builder.build(conv_hyperparams_proto, is_training=True)
    conv_scope_arguments = scope.values()[0]
    initializer = conv_scope_arguments['weights_initializer']
    self._assert_variance_in_range(initializer, shape=[100, 40],
                                   variance=0.49, tol=1e-1) 

def _build_activation_fn(activation_fn):
  """Builds a callable activation from config.

  Args:
    activation_fn: hyperparams_pb2.Hyperparams.activation

  Returns:
    Callable activation function.

  Raises:
    ValueError: On unknown activation function.
  """
  if activation_fn == hyperparams_pb2.Hyperparams.NONE:
    return None
  if activation_fn == hyperparams_pb2.Hyperparams.RELU:
    return tf.nn.relu
  if activation_fn == hyperparams_pb2.Hyperparams.RELU_6:
    return tf.nn.relu6
  raise ValueError('Unknown activation function: {}'.format(activation_fn)) 

def _build_conv_hyperparams(self):
    conv_hyperparams = hyperparams_pb2.Hyperparams()
    conv_hyperparams_text_proto = """
      activation: RELU_6
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
      batch_norm {
        scale: false
      }
    """
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
    return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams) 

def _build_conv_hyperparams(self):
    conv_hyperparams = hyperparams_pb2.Hyperparams()
    conv_hyperparams_text_proto = """
      activation: RELU_6
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
      batch_norm {
        train: true,
        scale: false,
        center: true,
        decay: 0.2,
        epsilon: 0.1,
      }
    """
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
    return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams) 

def _build_arg_scope_with_conv_hyperparams(self):
    conv_hyperparams = hyperparams_pb2.Hyperparams()
    conv_hyperparams_text_proto = """
      activation: RELU_6
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        random_normal_initializer {
          stddev: 0.01
          mean: 0.0
        }
      }
      batch_norm {
        train: true,
      }
    """
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
    return hyperparams_builder.build(conv_hyperparams, is_training=True) 

def _build_conv_arg_scope_no_batch_norm(self):
    conv_hyperparams = hyperparams_pb2.Hyperparams()
    conv_hyperparams_text_proto = """
      activation: RELU_6
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        random_normal_initializer {
          stddev: 0.01
          mean: 0.0
        }
      }
    """
    text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
    return hyperparams_builder.build(conv_hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(self,
                                        op_type=hyperparams_pb2.Hyperparams.FC):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(
      self, op_type=hyperparams_pb2.Hyperparams.CONV):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(self,
                                        op_type=hyperparams_pb2.Hyperparams.FC):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(self,
                                        op_type=hyperparams_pb2.Hyperparams.FC):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(
      self, op_type=hyperparams_pb2.Hyperparams.CONV):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(self,
                                        op_type=hyperparams_pb2.Hyperparams.FC):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(
      self, op_type=hyperparams_pb2.Hyperparams.CONV):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True) 

def _build_arg_scope_with_hyperparams(
      self, op_type=hyperparams_pb2.Hyperparams.CONV):
    hyperparams = hyperparams_pb2.Hyperparams()
    hyperparams_text_proto = """
      activation: NONE
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        truncated_normal_initializer {
        }
      }
    """
    text_format.Merge(hyperparams_text_proto, hyperparams)
    hyperparams.op = op_type
    return hyperparams_builder.build(hyperparams, is_training=True)