Python hyperparams_builder.build方法代码示例

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
def build(model_config, is_training):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
def test_explicit_fc_op_arg_scope_has_fully_connected_op(self):
    conv_hyperparams_text_proto = """
      op: FC
      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)
    self.assertTrue(self._get_scope_key(slim.fully_connected) in scope) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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.) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
def test_variance_in_range_with_variance_scaling_initializer_fan_out(self):
    conv_hyperparams_text_proto = """
      regularizer {
        l2_regularizer {
        }
      }
      initializer {
        variance_scaling_initializer {
          factor: 2.0
          mode: FAN_OUT
          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. / 40.) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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.)) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
def _get_second_stage_box_predictor(self, num_classes, is_training,
                                      predict_masks, masks_are_class_agnostic):
    box_predictor_proto = box_predictor_pb2.BoxPredictor()
    text_format.Merge(self._get_second_stage_box_predictor_text_proto(),
                      box_predictor_proto)
    if predict_masks:
      text_format.Merge(
          self._add_mask_to_second_stage_box_predictor_text_proto(
              masks_are_class_agnostic),
          box_predictor_proto)

    return box_predictor_builder.build(
        hyperparams_builder.build,
        box_predictor_proto,
        num_classes=num_classes,
        is_training=is_training) 

# 需要导入模块: from object_detection.builders import hyperparams_builder [as 别名]
# 或者: from object_detection.builders.hyperparams_builder import build [as 别名]
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)