Python model_lib.create_estimator_and_inputs方法代码示例

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def test_create_estimator_and_inputs(self):
    """Tests that Estimator and input function are constructed correctly."""
    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)
    train_steps = 20
    train_and_eval_dict = model_lib.create_estimator_and_inputs(
        run_config,
        hparams,
        pipeline_config_path,
        train_steps=train_steps)
    estimator = train_and_eval_dict['estimator']
    train_steps = train_and_eval_dict['train_steps']
    self.assertIsInstance(estimator, tf.estimator.Estimator)
    self.assertEqual(20, train_steps)
    self.assertIn('train_input_fn', train_and_eval_dict)
    self.assertIn('eval_input_fns', train_and_eval_dict)
    self.assertIn('eval_on_train_input_fn', train_and_eval_dict) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def test_create_tpu_estimator_and_inputs(self):
    """Tests that number of train/eval defaults to config values."""

    run_config = tpu_config.RunConfig()
    hparams = model_hparams.create_hparams(
        hparams_overrides='load_pretrained=false')
    pipeline_config_path = get_pipeline_config_path(MODEL_NAME_FOR_TEST)
    train_steps = 20
    train_and_eval_dict = model_lib.create_estimator_and_inputs(
        run_config,
        hparams,
        pipeline_config_path,
        train_steps=train_steps,
        use_tpu_estimator=True)
    estimator = train_and_eval_dict['estimator']
    train_steps = train_and_eval_dict['train_steps']

    self.assertIsInstance(estimator, tpu_estimator.TPUEstimator)
    self.assertEqual(20, train_steps) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def test_create_estimator_and_inputs(self):
    """Tests that Estimator and input function are constructed correctly."""
    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)
    train_steps = 20
    eval_steps = 10
    train_and_eval_dict = model_lib.create_estimator_and_inputs(
        run_config,
        hparams,
        pipeline_config_path,
        train_steps=train_steps,
        eval_steps=eval_steps)
    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(20, train_steps)
    self.assertEqual(10, eval_steps)
    self.assertIn('train_input_fn', train_and_eval_dict)
    self.assertIn('eval_input_fn', train_and_eval_dict)
    self.assertIn('eval_on_train_input_fn', train_and_eval_dict) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
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) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def test_create_tpu_estimator_and_inputs(self):
    """Tests that number of train/eval defaults to config values."""

    run_config = tpu_config.RunConfig()
    hparams = model_hparams.create_hparams(
        hparams_overrides='load_pretrained=false')
    pipeline_config_path = get_pipeline_config_path(MODEL_NAME_FOR_TEST)
    train_steps = 20
    eval_steps = 10
    train_and_eval_dict = model_lib.create_estimator_and_inputs(
        run_config,
        hparams,
        pipeline_config_path,
        train_steps=train_steps,
        eval_steps=eval_steps,
        use_tpu_estimator=True)
    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, tpu_estimator.TPUEstimator)
    self.assertEqual(20, train_steps)
    self.assertEqual(10, eval_steps) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def test_create_estimator_and_inputs_sequence_example(self):
    """Tests that Estimator and input function are constructed correctly."""
    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_SEQUENCE_EXAMPLE_TEST)
    train_steps = 20
    train_and_eval_dict = model_lib.create_estimator_and_inputs(
        run_config,
        hparams,
        pipeline_config_path,
        train_steps=train_steps)
    estimator = train_and_eval_dict['estimator']
    train_steps = train_and_eval_dict['train_steps']
    self.assertIsInstance(estimator, tf.estimator.Estimator)
    self.assertEqual(20, train_steps)
    self.assertIn('train_input_fn', train_and_eval_dict)
    self.assertIn('eval_input_fns', train_and_eval_dict)
    self.assertIn('eval_on_train_input_fn', train_and_eval_dict) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def test_create_tpu_estimator_and_inputs(self):
    """Tests that number of train/eval defaults to config values."""
    run_config = tf.estimator.tpu.RunConfig()
    hparams = model_hparams.create_hparams(
        hparams_overrides='load_pretrained=false')
    pipeline_config_path = get_pipeline_config_path(MODEL_NAME_FOR_TEST)
    train_steps = 20
    train_and_eval_dict = model_lib.create_estimator_and_inputs(
        run_config,
        hparams,
        pipeline_config_path,
        train_steps=train_steps,
        use_tpu_estimator=True)
    estimator = train_and_eval_dict['estimator']
    train_steps = train_and_eval_dict['train_steps']

    self.assertIsInstance(estimator, tf.estimator.tpu.TPUEstimator)
    self.assertEqual(20, train_steps) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
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
    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']

    self.assertIsInstance(estimator, tf.estimator.Estimator)
    self.assertEqual(config_train_steps, train_steps) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def main(unused_argv):
  flags.mark_flag_as_required('model_dir')
  flags.mark_flag_as_required('pipeline_config_path')
  config = tf.estimator.RunConfig(model_dir=FLAGS.model_dir)

  train_and_eval_dict = model_lib.create_estimator_and_inputs(
      run_config=config,
      hparams=model_hparams.create_hparams(FLAGS.hparams_overrides),
      pipeline_config_path=FLAGS.pipeline_config_path,
      train_steps=FLAGS.num_train_steps,
      eval_steps=FLAGS.num_eval_steps)
  estimator = train_and_eval_dict['estimator']
  train_input_fn = train_and_eval_dict['train_input_fn']
  eval_input_fn = train_and_eval_dict['eval_input_fn']
  eval_on_train_input_fn = train_and_eval_dict['eval_on_train_input_fn']
  predict_input_fn = train_and_eval_dict['predict_input_fn']
  train_steps = train_and_eval_dict['train_steps']
  eval_steps = train_and_eval_dict['eval_steps']

  if FLAGS.checkpoint_dir:
    estimator.evaluate(eval_input_fn,
                       eval_steps,
                       checkpoint_path=tf.train.latest_checkpoint(
                           FLAGS.checkpoint_dir))
  else:
    train_spec, eval_specs = model_lib.create_train_and_eval_specs(
        train_input_fn,
        eval_input_fn,
        eval_on_train_input_fn,
        predict_input_fn,
        train_steps,
        eval_steps,
        eval_on_train_data=False)

    # Currently only a single Eval Spec is allowed.
    tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0]) 

# 需要导入模块: from object_detection import model_lib [as 别名]
# 或者: from object_detection.model_lib import create_estimator_and_inputs [as 别名]
def train(unused_argv, model_dir, pipeline_config_path, num_train_steps, num_eval_steps, network_arch):


  config = tf.estimator.RunConfig(model_dir=model_dir)

  train_and_eval_dict = model_lib.create_estimator_and_inputs(
      run_config=config,
      hparams=model_hparams.create_hparams(None),
      pipeline_config_path=pipeline_config_path,
      train_steps=num_train_steps,
      eval_steps=num_eval_steps)
  estimator = train_and_eval_dict['estimator']
  train_input_fn = train_and_eval_dict['train_input_fn']
  eval_input_fn = train_and_eval_dict['eval_input_fn']
  eval_on_train_input_fn = train_and_eval_dict['eval_on_train_input_fn']
  predict_input_fn = train_and_eval_dict['predict_input_fn']
  train_steps = train_and_eval_dict['train_steps']
  eval_steps = train_and_eval_dict['eval_steps']



  train_spec, eval_specs = model_lib.create_train_and_eval_specs(
      train_input_fn,
      eval_input_fn,
      eval_on_train_input_fn,
      predict_input_fn,
      train_steps,
      eval_steps,
      eval_on_train_data=False)
  # Currently only a single Eval Spec is allowed.
  tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])