Python object_detection.utils.config_util.get_configs_from_pipeline_file() Examples

The following are 30 code examples of object_detection.utils.config_util.get_configs_from_pipeline_file(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module object_detection.utils.config_util , or try the search function .
Example #1
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testNewTrainInputPathList(self):
    """Tests that train input path can be overwritten with multiple files."""
    original_train_path = ["path/to/data"]
    new_train_path = ["another/path/to/data", "yet/another/path/to/data"]
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    reader_config = pipeline_config.train_input_reader.tf_record_input_reader
    reader_config.input_path.extend(original_train_path)
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, train_input_path=new_train_path)
    reader_config = configs["train_input_config"].tf_record_input_reader
    final_path = reader_config.input_path
    self.assertEqual(new_train_path, final_path)
Example #2
Source File: config_util_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def test_create_pipeline_proto_from_configs(self):
    """Tests that proto can be reconstructed from configs dictionary."""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.faster_rcnn.num_classes = 10
    pipeline_config.train_config.batch_size = 32
    pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
    pipeline_config.eval_config.num_examples = 20
    pipeline_config.eval_input_reader.queue_capacity = 100
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    pipeline_config_reconstructed = (
        config_util.create_pipeline_proto_from_configs(configs))
    self.assertEqual(pipeline_config, pipeline_config_reconstructed)
Example #3
Source File: inputs_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def _get_configs_for_model(model_name):
  """Returns configurations for model."""
  fname = os.path.join(
      FLAGS.test_srcdir,
      ('google3/third_party/tensorflow_models/'
       'object_detection/samples/configs/' + model_name + '.config'))
  label_map_path = os.path.join(FLAGS.test_srcdir,
                                ('google3/third_party/tensorflow_models/'
                                 'object_detection/data/pet_label_map.pbtxt'))
  data_path = os.path.join(FLAGS.test_srcdir,
                           ('google3/third_party/tensorflow_models/'
                            'object_detection/test_data/pets_examples.record'))
  configs = config_util.get_configs_from_pipeline_file(fname)
  return config_util.merge_external_params_with_configs(
      configs,
      train_input_path=data_path,
      eval_input_path=data_path,
      label_map_path=label_map_path)
Example #4
Source File: model_lib_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def test_create_estimator_with_default_train_eval_steps(self):
    """Tests that number of train/eval defaults to config values."""
    run_config = tf.estimator.RunConfig()
    hparams = model_hparams.create_hparams(
        hparams_overrides='load_pretrained=false')
    pipeline_config_path = get_pipeline_config_path(MODEL_NAME_FOR_TEST)
    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    config_train_steps = configs['train_config'].num_steps
    config_eval_steps = configs['eval_config'].num_examples
    train_and_eval_dict = model_lib.create_estimator_and_inputs(
        run_config, hparams, pipeline_config_path)
    estimator = train_and_eval_dict['estimator']
    train_steps = train_and_eval_dict['train_steps']
    eval_steps = train_and_eval_dict['eval_steps']

    self.assertIsInstance(estimator, tf.estimator.Estimator)
    self.assertEqual(config_train_steps, train_steps)
    self.assertEqual(config_eval_steps, eval_steps)
Example #5
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testNewMaskType(self):
    """Tests that mask type can be overwritten in input readers."""
    original_mask_type = input_reader_pb2.NUMERICAL_MASKS
    new_mask_type = input_reader_pb2.PNG_MASKS
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    train_input_reader = pipeline_config.train_input_reader
    train_input_reader.mask_type = original_mask_type
    eval_input_reader = pipeline_config.eval_input_reader
    eval_input_reader.mask_type = original_mask_type
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, mask_type=new_mask_type)
    self.assertEqual(new_mask_type, configs["train_input_config"].mask_type)
    self.assertEqual(new_mask_type, configs["eval_input_config"].mask_type)
Example #6
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testDontOverwriteEmptyLabelMapPath(self):
    """Tests that label map path will not by overwritten with empty string."""
    original_label_map_path = "path/to/original/label_map"
    new_label_map_path = ""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    train_input_reader = pipeline_config.train_input_reader
    train_input_reader.label_map_path = original_label_map_path
    eval_input_reader = pipeline_config.eval_input_reader
    eval_input_reader.label_map_path = original_label_map_path
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, label_map_path=new_label_map_path)
    self.assertEqual(original_label_map_path,
                     configs["train_input_config"].label_map_path)
    self.assertEqual(original_label_map_path,
                     configs["eval_input_config"].label_map_path)
Example #7
Source File: config_util_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def test_get_configs_from_pipeline_file(self):
    """Test that proto configs can be read from pipeline config file."""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.faster_rcnn.num_classes = 10
    pipeline_config.train_config.batch_size = 32
    pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
    pipeline_config.eval_config.num_examples = 20
    pipeline_config.eval_input_reader.queue_capacity = 100

    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    self.assertProtoEquals(pipeline_config.model, configs["model"])
    self.assertProtoEquals(pipeline_config.train_config,
                           configs["train_config"])
    self.assertProtoEquals(pipeline_config.train_input_reader,
                           configs["train_input_config"])
    self.assertProtoEquals(pipeline_config.eval_config,
                           configs["eval_config"])
    self.assertProtoEquals(pipeline_config.eval_input_reader,
                           configs["eval_input_config"])
Example #8
Source File: config_util_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def testMergingKeywordArguments(self):
    """Tests that keyword arguments get merged as do hyperparameters."""
    original_num_train_steps = 100
    original_num_eval_steps = 5
    desired_num_train_steps = 10
    desired_num_eval_steps = 1
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.train_config.num_steps = original_num_train_steps
    pipeline_config.eval_config.num_examples = original_num_eval_steps
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs,
        train_steps=desired_num_train_steps,
        eval_steps=desired_num_eval_steps)
    train_steps = configs["train_config"].num_steps
    eval_steps = configs["eval_config"].num_examples
    self.assertEqual(desired_num_train_steps, train_steps)
    self.assertEqual(desired_num_eval_steps, eval_steps)
Example #9
Source File: config_util_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def testNewTrainInputPath(self):
    """Tests that train input path can be overwritten with single file."""
    original_train_path = ["path/to/data"]
    new_train_path = "another/path/to/data"
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    reader_config = pipeline_config.train_input_reader.tf_record_input_reader
    reader_config.input_path.extend(original_train_path)
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, train_input_path=new_train_path)
    reader_config = configs["train_input_config"].tf_record_input_reader
    final_path = reader_config.input_path
    self.assertEqual([new_train_path], final_path)
Example #10
Source File: config_util_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def testNewLabelMapPath(self):
    """Tests that label map path can be overwritten in input readers."""
    original_label_map_path = "path/to/original/label_map"
    new_label_map_path = "path//to/new/label_map"
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    train_input_reader = pipeline_config.train_input_reader
    train_input_reader.label_map_path = original_label_map_path
    eval_input_reader = pipeline_config.eval_input_reader
    eval_input_reader.label_map_path = original_label_map_path
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, label_map_path=new_label_map_path)
    self.assertEqual(new_label_map_path,
                     configs["train_input_config"].label_map_path)
    self.assertEqual(new_label_map_path,
                     configs["eval_input_config"].label_map_path)
Example #11
Source File: config_util_test.py    From Traffic-Rule-Violation-Detection-System with MIT License 6 votes vote down vote up 
def test_get_configs_from_pipeline_file(self):
    """Test that proto configs can be read from pipeline config file."""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.faster_rcnn.num_classes = 10
    pipeline_config.train_config.batch_size = 32
    pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
    pipeline_config.eval_config.num_examples = 20
    pipeline_config.eval_input_reader.queue_capacity = 100

    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    self.assertProtoEquals(pipeline_config.model, configs["model"])
    self.assertProtoEquals(pipeline_config.train_config,
                           configs["train_config"])
    self.assertProtoEquals(pipeline_config.train_input_reader,
                           configs["train_input_config"])
    self.assertProtoEquals(pipeline_config.eval_config,
                           configs["eval_config"])
    self.assertProtoEquals(pipeline_config.eval_input_reader,
                           configs["eval_input_config"])
Example #12
Source File: config_util_test.py    From Traffic-Rule-Violation-Detection-System with MIT License 6 votes vote down vote up 
def test_create_pipeline_proto_from_configs(self):
    """Tests that proto can be reconstructed from configs dictionary."""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.faster_rcnn.num_classes = 10
    pipeline_config.train_config.batch_size = 32
    pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
    pipeline_config.eval_config.num_examples = 20
    pipeline_config.eval_input_reader.queue_capacity = 100
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    pipeline_config_reconstructed = (
        config_util.create_pipeline_proto_from_configs(configs))
    self.assertEqual(pipeline_config, pipeline_config_reconstructed)
Example #13
Source File: config_util_test.py    From Traffic-Rule-Violation-Detection-System with MIT License 6 votes vote down vote up 
def testNewMomentumOptimizerValue(self):
    """Tests that new momentum value is updated appropriately."""
    original_momentum_value = 0.4
    hparams = tf.contrib.training.HParams(momentum_optimizer_value=1.1)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    optimizer_config = pipeline_config.train_config.optimizer.rms_prop_optimizer
    optimizer_config.momentum_optimizer_value = original_momentum_value
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    optimizer_config = configs["train_config"].optimizer.rms_prop_optimizer
    new_momentum_value = optimizer_config.momentum_optimizer_value
    self.assertAlmostEqual(1.0, new_momentum_value)  # Clipped to 1.0.
Example #14
Source File: config_util_test.py    From Traffic-Rule-Violation-Detection-System with MIT License 6 votes vote down vote up 
def testNewClassificationLocalizationWeightRatio(self):
    """Tests that the loss weight ratio is updated appropriately."""
    original_localization_weight = 0.1
    original_classification_weight = 0.2
    new_weight_ratio = 5.0
    hparams = tf.contrib.training.HParams(
        classification_localization_weight_ratio=new_weight_ratio)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.ssd.loss.localization_weight = (
        original_localization_weight)
    pipeline_config.model.ssd.loss.classification_weight = (
        original_classification_weight)
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    loss = configs["model"].ssd.loss
    self.assertAlmostEqual(1.0, loss.localization_weight)
    self.assertAlmostEqual(new_weight_ratio, loss.classification_weight)
Example #15
Source File: config_util_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def testNewFocalLossParameters(self):
    """Tests that the loss weight ratio is updated appropriately."""
    original_alpha = 1.0
    original_gamma = 1.0
    new_alpha = 0.3
    new_gamma = 2.0
    hparams = tf.HParams(focal_loss_alpha=new_alpha, focal_loss_gamma=new_gamma)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    classification_loss = pipeline_config.model.ssd.loss.classification_loss
    classification_loss.weighted_sigmoid_focal.alpha = original_alpha
    classification_loss.weighted_sigmoid_focal.gamma = original_gamma
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    classification_loss = configs["model"].ssd.loss.classification_loss
    self.assertAlmostEqual(new_alpha,
                           classification_loss.weighted_sigmoid_focal.alpha)
    self.assertAlmostEqual(new_gamma,
                           classification_loss.weighted_sigmoid_focal.gamma)
Example #16
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testNewLabelMapPath(self):
    """Tests that label map path can be overwritten in input readers."""
    original_label_map_path = "path/to/original/label_map"
    new_label_map_path = "path//to/new/label_map"
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    train_input_reader = pipeline_config.train_input_reader
    train_input_reader.label_map_path = original_label_map_path
    eval_input_reader = pipeline_config.eval_input_reader
    eval_input_reader.label_map_path = original_label_map_path
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, label_map_path=new_label_map_path)
    self.assertEqual(new_label_map_path,
                     configs["train_input_config"].label_map_path)
    self.assertEqual(new_label_map_path,
                     configs["eval_input_config"].label_map_path)
Example #17
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testMergingKeywordArguments(self):
    """Tests that keyword arguments get merged as do hyperparameters."""
    original_num_train_steps = 100
    original_num_eval_steps = 5
    desired_num_train_steps = 10
    desired_num_eval_steps = 1
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.train_config.num_steps = original_num_train_steps
    pipeline_config.eval_config.num_examples = original_num_eval_steps
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs,
        train_steps=desired_num_train_steps,
        eval_steps=desired_num_eval_steps)
    train_steps = configs["train_config"].num_steps
    eval_steps = configs["eval_config"].num_examples
    self.assertEqual(desired_num_train_steps, train_steps)
    self.assertEqual(desired_num_eval_steps, eval_steps)
Example #18
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testNewFocalLossParameters(self):
    """Tests that the loss weight ratio is updated appropriately."""
    original_alpha = 1.0
    original_gamma = 1.0
    new_alpha = 0.3
    new_gamma = 2.0
    hparams = tf.contrib.training.HParams(
        focal_loss_alpha=new_alpha, focal_loss_gamma=new_gamma)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    classification_loss = pipeline_config.model.ssd.loss.classification_loss
    classification_loss.weighted_sigmoid_focal.alpha = original_alpha
    classification_loss.weighted_sigmoid_focal.gamma = original_gamma
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    classification_loss = configs["model"].ssd.loss.classification_loss
    self.assertAlmostEqual(new_alpha,
                           classification_loss.weighted_sigmoid_focal.alpha)
    self.assertAlmostEqual(new_gamma,
                           classification_loss.weighted_sigmoid_focal.gamma)
Example #19
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testNewClassificationLocalizationWeightRatio(self):
    """Tests that the loss weight ratio is updated appropriately."""
    original_localization_weight = 0.1
    original_classification_weight = 0.2
    new_weight_ratio = 5.0
    hparams = tf.contrib.training.HParams(
        classification_localization_weight_ratio=new_weight_ratio)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.ssd.loss.localization_weight = (
        original_localization_weight)
    pipeline_config.model.ssd.loss.classification_weight = (
        original_classification_weight)
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    loss = configs["model"].ssd.loss
    self.assertAlmostEqual(1.0, loss.localization_weight)
    self.assertAlmostEqual(new_weight_ratio, loss.classification_weight)
Example #20
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def testNewMomentumOptimizerValue(self):
    """Tests that new momentum value is updated appropriately."""
    original_momentum_value = 0.4
    hparams = tf.contrib.training.HParams(momentum_optimizer_value=1.1)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    optimizer_config = pipeline_config.train_config.optimizer.rms_prop_optimizer
    optimizer_config.momentum_optimizer_value = original_momentum_value
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    optimizer_config = configs["train_config"].optimizer.rms_prop_optimizer
    new_momentum_value = optimizer_config.momentum_optimizer_value
    self.assertAlmostEqual(1.0, new_momentum_value)  # Clipped to 1.0.
Example #21
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def test_save_pipeline_config(self):
    """Tests that the pipeline config is properly saved to disk."""
    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.faster_rcnn.num_classes = 10
    pipeline_config.train_config.batch_size = 32
    pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
    pipeline_config.eval_config.num_examples = 20
    pipeline_config.eval_input_reader.queue_capacity = 100

    config_util.save_pipeline_config(pipeline_config, self.get_temp_dir())
    configs = config_util.get_configs_from_pipeline_file(
        os.path.join(self.get_temp_dir(), "pipeline.config"))
    pipeline_config_reconstructed = (
        config_util.create_pipeline_proto_from_configs(configs))

    self.assertEqual(pipeline_config, pipeline_config_reconstructed)
Example #22
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def test_create_pipeline_proto_from_configs(self):
    """Tests that proto can be reconstructed from configs dictionary."""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.faster_rcnn.num_classes = 10
    pipeline_config.train_config.batch_size = 32
    pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
    pipeline_config.eval_config.num_examples = 20
    pipeline_config.eval_input_reader.queue_capacity = 100
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    pipeline_config_reconstructed = (
        config_util.create_pipeline_proto_from_configs(configs))
    self.assertEqual(pipeline_config, pipeline_config_reconstructed)
Example #23
Source File: config_util_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def test_get_configs_from_pipeline_file(self):
    """Test that proto configs can be read from pipeline config file."""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.faster_rcnn.num_classes = 10
    pipeline_config.train_config.batch_size = 32
    pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
    pipeline_config.eval_config.num_examples = 20
    pipeline_config.eval_input_reader.queue_capacity = 100

    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    self.assertProtoEquals(pipeline_config.model, configs["model"])
    self.assertProtoEquals(pipeline_config.train_config,
                           configs["train_config"])
    self.assertProtoEquals(pipeline_config.train_input_reader,
                           configs["train_input_config"])
    self.assertProtoEquals(pipeline_config.eval_config,
                           configs["eval_config"])
    self.assertProtoEquals(pipeline_config.eval_input_reader,
                           configs["eval_input_config"])
Example #24
Source File: config_util_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def testNewMaskType(self):
    """Tests that mask type can be overwritten in input readers."""
    original_mask_type = input_reader_pb2.NUMERICAL_MASKS
    new_mask_type = input_reader_pb2.PNG_MASKS
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    train_input_reader = pipeline_config.train_input_reader
    train_input_reader.mask_type = original_mask_type
    eval_input_reader = pipeline_config.eval_input_reader
    eval_input_reader.mask_type = original_mask_type
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, mask_type=new_mask_type)
    self.assertEqual(new_mask_type, configs["train_input_config"].mask_type)
    self.assertEqual(new_mask_type, configs["eval_input_config"].mask_type)
Example #25
Source File: config_util_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def testDontOverwriteEmptyLabelMapPath(self):
    """Tests that label map path will not by overwritten with empty string."""
    original_label_map_path = "path/to/original/label_map"
    new_label_map_path = ""
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    train_input_reader = pipeline_config.train_input_reader
    train_input_reader.label_map_path = original_label_map_path
    eval_input_reader = pipeline_config.eval_input_reader
    eval_input_reader.label_map_path = original_label_map_path
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, label_map_path=new_label_map_path)
    self.assertEqual(original_label_map_path,
                     configs["train_input_config"].label_map_path)
    self.assertEqual(original_label_map_path,
                     configs["eval_input_config"].label_map_path)
Example #26
Source File: config_util_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def testNewLabelMapPath(self):
    """Tests that label map path can be overwritten in input readers."""
    original_label_map_path = "path/to/original/label_map"
    new_label_map_path = "path//to/new/label_map"
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    train_input_reader = pipeline_config.train_input_reader
    train_input_reader.label_map_path = original_label_map_path
    eval_input_reader = pipeline_config.eval_input_reader
    eval_input_reader.label_map_path = original_label_map_path
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, label_map_path=new_label_map_path)
    self.assertEqual(new_label_map_path,
                     configs["train_input_config"].label_map_path)
    self.assertEqual(new_label_map_path,
                     configs["eval_input_config"].label_map_path)
Example #27
Source File: config_util_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def testNewTrainInputPath(self):
    """Tests that train input path can be overwritten with single file."""
    original_train_path = ["path/to/data"]
    new_train_path = "another/path/to/data"
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    reader_config = pipeline_config.train_input_reader.tf_record_input_reader
    reader_config.input_path.extend(original_train_path)
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs, train_input_path=new_train_path)
    reader_config = configs["train_input_config"].tf_record_input_reader
    final_path = reader_config.input_path
    self.assertEqual([new_train_path], final_path)
Example #28
Source File: config_util_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def testMergingKeywordArguments(self):
    """Tests that keyword arguments get merged as do hyperparameters."""
    original_num_train_steps = 100
    original_num_eval_steps = 5
    desired_num_train_steps = 10
    desired_num_eval_steps = 1
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.train_config.num_steps = original_num_train_steps
    pipeline_config.eval_config.num_examples = original_num_eval_steps
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(
        configs,
        train_steps=desired_num_train_steps,
        eval_steps=desired_num_eval_steps)
    train_steps = configs["train_config"].num_steps
    eval_steps = configs["eval_config"].num_examples
    self.assertEqual(desired_num_train_steps, train_steps)
    self.assertEqual(desired_num_eval_steps, eval_steps)
Example #29
Source File: config_util_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def testNewFocalLossParameters(self):
    """Tests that the loss weight ratio is updated appropriately."""
    original_alpha = 1.0
    original_gamma = 1.0
    new_alpha = 0.3
    new_gamma = 2.0
    hparams = tf.contrib.training.HParams(
        focal_loss_alpha=new_alpha, focal_loss_gamma=new_gamma)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    classification_loss = pipeline_config.model.ssd.loss.classification_loss
    classification_loss.weighted_sigmoid_focal.alpha = original_alpha
    classification_loss.weighted_sigmoid_focal.gamma = original_gamma
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    classification_loss = configs["model"].ssd.loss.classification_loss
    self.assertAlmostEqual(new_alpha,
                           classification_loss.weighted_sigmoid_focal.alpha)
    self.assertAlmostEqual(new_gamma,
                           classification_loss.weighted_sigmoid_focal.gamma)
Example #30
Source File: config_util_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def testNewClassificationLocalizationWeightRatio(self):
    """Tests that the loss weight ratio is updated appropriately."""
    original_localization_weight = 0.1
    original_classification_weight = 0.2
    new_weight_ratio = 5.0
    hparams = tf.contrib.training.HParams(
        classification_localization_weight_ratio=new_weight_ratio)
    pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config")

    pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
    pipeline_config.model.ssd.loss.localization_weight = (
        original_localization_weight)
    pipeline_config.model.ssd.loss.classification_weight = (
        original_classification_weight)
    _write_config(pipeline_config, pipeline_config_path)

    configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
    configs = config_util.merge_external_params_with_configs(configs, hparams)
    loss = configs["model"].ssd.loss
    self.assertAlmostEqual(1.0, loss.localization_weight)
    self.assertAlmostEqual(new_weight_ratio, loss.classification_weight)