Python eval_pb2.EvalConfig方法代码示例

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def get_configs_from_pipeline_file():
  """Reads evaluation configuration from a pipeline_pb2.TrainEvalPipelineConfig.

  Reads evaluation config from file specified by pipeline_config_path flag.

  Returns:
    model_config: a model_pb2.DetectionModel
    eval_config: a eval_pb2.EvalConfig
    input_config: a input_reader_pb2.InputReader
  """
  pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
  with tf.gfile.GFile(FLAGS.pipeline_config_path, 'r') as f:
    text_format.Merge(f.read(), pipeline_config)

  model_config = pipeline_config.model
  if FLAGS.eval_training_data:
    eval_config = pipeline_config.train_config
  else:
    eval_config = pipeline_config.eval_config
  input_config = pipeline_config.eval_input_reader

  return model_config, eval_config, input_config 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_for_coco_detections(self, batch_size=1,
                                                   max_gt_boxes=None,
                                                   scale_to_absolute=False):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(['coco_detection_metrics'])
    categories = self._get_categories_list()
    eval_dict = self._make_evaluation_dict(batch_size=batch_size,
                                           max_gt_boxes=max_gt_boxes,
                                           scale_to_absolute=scale_to_absolute)
    metric_ops = eval_util.get_eval_metric_ops_for_evaluators(
        eval_config, categories, eval_dict)
    _, update_op = metric_ops['DetectionBoxes_Precision/mAP']

    with self.test_session() as sess:
      metrics = {}
      for key, (value_op, _) in metric_ops.iteritems():
        metrics[key] = value_op
      sess.run(update_op)
      metrics = sess.run(metrics)
      self.assertAlmostEqual(1.0, metrics['DetectionBoxes_Precision/mAP'])
      self.assertNotIn('DetectionMasks_Precision/mAP', metrics) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_for_coco_detections_and_masks(
      self, batch_size=1, max_gt_boxes=None, scale_to_absolute=False):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(
        ['coco_detection_metrics', 'coco_mask_metrics'])
    categories = self._get_categories_list()
    eval_dict = self._make_evaluation_dict(batch_size=batch_size,
                                           max_gt_boxes=max_gt_boxes,
                                           scale_to_absolute=scale_to_absolute)
    metric_ops = eval_util.get_eval_metric_ops_for_evaluators(
        eval_config, categories, eval_dict)
    _, update_op_boxes = metric_ops['DetectionBoxes_Precision/mAP']
    _, update_op_masks = metric_ops['DetectionMasks_Precision/mAP']

    with self.test_session() as sess:
      metrics = {}
      for key, (value_op, _) in metric_ops.iteritems():
        metrics[key] = value_op
      sess.run(update_op_boxes)
      sess.run(update_op_masks)
      metrics = sess.run(metrics)
      self.assertAlmostEqual(1.0, metrics['DetectionBoxes_Precision/mAP'])
      self.assertAlmostEqual(1.0, metrics['DetectionMasks_Precision/mAP']) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_for_coco_detections_and_resized_masks(
      self, batch_size=1, max_gt_boxes=None, scale_to_absolute=False):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(
        ['coco_detection_metrics', 'coco_mask_metrics'])
    categories = self._get_categories_list()
    eval_dict = self._make_evaluation_dict(batch_size=batch_size,
                                           max_gt_boxes=max_gt_boxes,
                                           scale_to_absolute=scale_to_absolute,
                                           resized_groundtruth_masks=True)
    metric_ops = eval_util.get_eval_metric_ops_for_evaluators(
        eval_config, categories, eval_dict)
    _, update_op_boxes = metric_ops['DetectionBoxes_Precision/mAP']
    _, update_op_masks = metric_ops['DetectionMasks_Precision/mAP']

    with self.test_session() as sess:
      metrics = {}
      for key, (value_op, _) in metric_ops.iteritems():
        metrics[key] = value_op
      sess.run(update_op_boxes)
      sess.run(update_op_masks)
      metrics = sess.run(metrics)
      self.assertAlmostEqual(1.0, metrics['DetectionBoxes_Precision/mAP'])
      self.assertAlmostEqual(1.0, metrics['DetectionMasks_Precision/mAP']) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_for_coco_detections(self):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(['coco_detection_metrics'])
    categories = self._get_categories_list()
    eval_dict = self._make_evaluation_dict()
    metric_ops = eval_util.get_eval_metric_ops_for_evaluators(
        eval_config, categories, eval_dict)
    _, update_op = metric_ops['DetectionBoxes_Precision/mAP']

    with self.test_session() as sess:
      metrics = {}
      for key, (value_op, _) in metric_ops.iteritems():
        metrics[key] = value_op
      sess.run(update_op)
      metrics = sess.run(metrics)
      print(metrics)
      self.assertAlmostEqual(1.0, metrics['DetectionBoxes_Precision/mAP'])
      self.assertNotIn('DetectionMasks_Precision/mAP', metrics) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_for_coco_detections_and_masks(self):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(
        ['coco_detection_metrics', 'coco_mask_metrics'])
    categories = self._get_categories_list()
    eval_dict = self._make_evaluation_dict()
    metric_ops = eval_util.get_eval_metric_ops_for_evaluators(
        eval_config, categories, eval_dict)
    _, update_op_boxes = metric_ops['DetectionBoxes_Precision/mAP']
    _, update_op_masks = metric_ops['DetectionMasks_Precision/mAP']

    with self.test_session() as sess:
      metrics = {}
      for key, (value_op, _) in metric_ops.iteritems():
        metrics[key] = value_op
      sess.run(update_op_boxes)
      sess.run(update_op_masks)
      metrics = sess.run(metrics)
      self.assertAlmostEqual(1.0, metrics['DetectionBoxes_Precision/mAP'])
      self.assertAlmostEqual(1.0, metrics['DetectionMasks_Precision/mAP']) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_for_coco_detections_and_resized_masks(self):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(
        ['coco_detection_metrics', 'coco_mask_metrics'])
    categories = self._get_categories_list()
    eval_dict = self._make_evaluation_dict(resized_groundtruth_masks=True)
    metric_ops = eval_util.get_eval_metric_ops_for_evaluators(
        eval_config, categories, eval_dict)
    _, update_op_boxes = metric_ops['DetectionBoxes_Precision/mAP']
    _, update_op_masks = metric_ops['DetectionMasks_Precision/mAP']

    with self.test_session() as sess:
      metrics = {}
      for key, (value_op, _) in metric_ops.iteritems():
        metrics[key] = value_op
      sess.run(update_op_boxes)
      sess.run(update_op_masks)
      metrics = sess.run(metrics)
      self.assertAlmostEqual(1.0, metrics['DetectionBoxes_Precision/mAP'])
      self.assertAlmostEqual(1.0, metrics['DetectionMasks_Precision/mAP']) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def get_configs_from_multiple_files():
  """Reads evaluation configuration from multiple config files.

  Reads the evaluation config from the following files:
    model_config: Read from --model_config_path
    eval_config: Read from --eval_config_path
    input_config: Read from --input_config_path

  Returns:
    model_config: a model_pb2.DetectionModel
    eval_config: a eval_pb2.EvalConfig
    input_config: a input_reader_pb2.InputReader
  """
  eval_config = eval_pb2.EvalConfig()
  with tf.gfile.GFile(FLAGS.eval_config_path, 'r') as f:
    text_format.Merge(f.read(), eval_config)

  model_config = model_pb2.DetectionModel()
  with tf.gfile.GFile(FLAGS.model_config_path, 'r') as f:
    text_format.Merge(f.read(), model_config)

  input_config = input_reader_pb2.InputReader()
  with tf.gfile.GFile(FLAGS.input_config_path, 'r') as f:
    text_format.Merge(f.read(), input_config)

  return model_config, eval_config, input_config 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_raises_error_with_unsupported_metric(self):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(['unsupported_metric'])
    categories = self._get_categories_list()
    eval_dict = self._make_evaluation_dict()
    with self.assertRaises(ValueError):
      eval_util.get_eval_metric_ops_for_evaluators(
          eval_config, categories, eval_dict) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_eval_metric_ops_for_evaluators(self):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(
        ['coco_detection_metrics', 'coco_mask_metrics'])
    eval_config.include_metrics_per_category = True

    evaluator_options = eval_util.evaluator_options_from_eval_config(
        eval_config)
    self.assertTrue(evaluator_options['coco_detection_metrics'][
        'include_metrics_per_category'])
    self.assertTrue(evaluator_options['coco_mask_metrics'][
        'include_metrics_per_category']) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def test_get_evaluator_with_no_evaluator_options(self):
    eval_config = eval_pb2.EvalConfig()
    eval_config.metrics_set.extend(['coco_detection_metrics'])
    eval_config.include_metrics_per_category = True
    categories = self._get_categories_list()

    evaluator = eval_util.get_evaluators(
        eval_config, categories, evaluator_options=None)

    # Even though we are setting eval_config.include_metrics_per_category = True
    # this option is never passed into the DetectionEvaluator constructor (via
    # `evaluator_options`).
    self.assertFalse(evaluator[0]._include_metrics_per_category) 

# 需要导入模块: from object_detection.protos import eval_pb2 [as 别名]
# 或者: from object_detection.protos.eval_pb2 import EvalConfig [as 别名]
def _update_retain_original_images(eval_config, retain_original_images):
  """Updates eval config with option to retain original images.

  The eval_config object is updated in place, and hence not returned.

  Args:
    eval_config: A eval_pb2.EvalConfig.
    retain_original_images: Boolean indicating whether to retain original images
      in eval mode.
  """
  eval_config.retain_original_images = retain_original_images