Python utils.get_models() Examples

def get_args():
    parser = ArgumentParser(formatter_class=ArgumentDefaultsHelpFormatter)
    parser.add_argument('--dexp', help='root experiment folder', default='exp')
    parser.add_argument('--model', help='which model to use', default='glad', choices=get_models())
    parser.add_argument('--epoch', help='max epoch to run for', default=50, type=int)
    parser.add_argument('--demb', help='word embedding size', default=400, type=int)
    parser.add_argument('--dhid', help='hidden state size', default=200, type=int)
    parser.add_argument('--batch_size', help='batch size', default=50, type=int)
    parser.add_argument('--lr', help='learning rate', default=1e-3, type=float)
    parser.add_argument('--stop', help='slot to early stop on', default='joint_goal')
    parser.add_argument('--resume', help='save directory to resume from')
    parser.add_argument('-n', '--nick', help='nickname for model', default='default')
    parser.add_argument('--seed', default=42, help='random seed', type=int)
    parser.add_argument('--test', action='store_true', help='run in evaluation only mode')
    parser.add_argument('--gpu', type=int, help='which GPU to use')
    parser.add_argument('--dropout', nargs='*', help='dropout rates', default=['emb=0.2', 'local=0.2', 'global=0.2'])
    args = parser.parse_args()
    args.dout = os.path.join(args.dexp, args.model, args.nick)
    args.dropout = {d.split('=')[0]: float(d.split('=')[1]) for d in args.dropout}
    if not os.path.isdir(args.dout):
        os.makedirs(args.dout)
    return args 

def test_get_models(self):
    with tempfile.TemporaryDirectory() as models_dir:
      model1 = '000013-model.meta'
      model2 = '000017-model.meta'
      f1 = open(os.path.join(models_dir, model1), 'w')
      f1.close()
      f2 = open(os.path.join(models_dir, model2), 'w')
      f2.close()
      model_nums_names = utils.get_models(models_dir)
      self.assertEqual(len(model_nums_names), 2)
      self.assertEqual(model_nums_names[0], (13, '000013-model'))
      self.assertEqual(model_nums_names[1], (17, '000017-model')) 

def validate(trained_models_dir, holdout_dir, estimator_model_dir, params):
  """Validate the latest model on the holdout dataset.

  Args:
    trained_models_dir: Directories where the completed generations/models are.
    holdout_dir: Directories where holdout data are.
    estimator_model_dir: tf.estimator model directory.
    params: An object of hyperparameters for the model.
  """
  model_num, _ = utils.get_latest_model(trained_models_dir)

  # Get the holdout game data
  nums_names = utils.get_models(trained_models_dir)

  # Model N was trained on games up through model N-1, so the validation set
  # should only be for models through N-1 as well, thus the (model_num) term.
  models = [num_name for num_name in nums_names if num_name[0] < model_num]

  # pair is a tuple of (model_num, model_name), like (13, 000013-modelname)
  holdout_dirs = [os.path.join(holdout_dir, pair[1])
                  for pair in models[-params.holdout_generation:]]
  tf_records = []
  with utils.logged_timer('Building lists of holdout files'):
    for record_dir in holdout_dirs:
      if os.path.exists(record_dir):  # make sure holdout dir exists
        tf_records.extend(
            tf.gfile.Glob(os.path.join(record_dir, '*'+_TF_RECORD_SUFFIX)))

  print('The length of tf_records is {}.'.format(len(tf_records)))
  first_tf_record = os.path.basename(tf_records[0])
  last_tf_record = os.path.basename(tf_records[-1])
  with utils.logged_timer('Validating from {} to {}'.format(
      first_tf_record, last_tf_record)):
    dualnet.validate(estimator_model_dir, tf_records, params) 

def test_get_models(self):
    with tempfile.TemporaryDirectory() as models_dir:
      model1 = '000013-model.meta'
      model2 = '000017-model.meta'
      f1 = open(os.path.join(models_dir, model1), 'w')
      f1.close()
      f2 = open(os.path.join(models_dir, model2), 'w')
      f2.close()
      model_nums_names = utils.get_models(models_dir)
      self.assertEqual(len(model_nums_names), 2)
      self.assertEqual(model_nums_names[0], (13, '000013-model'))
      self.assertEqual(model_nums_names[1], (17, '000017-model')) 

def validate(trained_models_dir, holdout_dir, estimator_model_dir, params):
  """Validate the latest model on the holdout dataset.

  Args:
    trained_models_dir: Directories where the completed generations/models are.
    holdout_dir: Directories where holdout data are.
    estimator_model_dir: tf.estimator model directory.
    params: A MiniGoParams instance of hyperparameters for the model.
  """
  model_num, _ = utils.get_latest_model(trained_models_dir)

  # Get the holdout game data
  nums_names = utils.get_models(trained_models_dir)

  # Model N was trained on games up through model N-1, so the validation set
  # should only be for models through N-1 as well, thus the (model_num) term.
  models = [num_name for num_name in nums_names if num_name[0] < model_num]

  # pair is a tuple of (model_num, model_name), like (13, 000013-modelname)
  holdout_dirs = [os.path.join(holdout_dir, pair[1])
                  for pair in models[-params.holdout_generation:]]
  tf_records = []
  with utils.logged_timer('Building lists of holdout files'):
    for record_dir in holdout_dirs:
      if os.path.exists(record_dir):  # make sure holdout dir exists
        tf_records.extend(
            tf.gfile.Glob(os.path.join(record_dir, '*'+_TF_RECORD_SUFFIX)))

  if not tf_records:
    print('No holdout dataset for validation! '
          'Please check your holdout directory: {}'.format(holdout_dir))
    return

  print('The length of tf_records is {}.'.format(len(tf_records)))
  first_tf_record = os.path.basename(tf_records[0])
  last_tf_record = os.path.basename(tf_records[-1])
  with utils.logged_timer('Validating from {} to {}'.format(
      first_tf_record, last_tf_record)):
    dualnet.validate(estimator_model_dir, tf_records, params) 

def test_get_models(self):
    with tempfile.TemporaryDirectory() as models_dir:
      model1 = '000013-model.meta'
      model2 = '000017-model.meta'
      f1 = open(os.path.join(models_dir, model1), 'w')
      f1.close()
      f2 = open(os.path.join(models_dir, model2), 'w')
      f2.close()
      model_nums_names = utils.get_models(models_dir)
      self.assertEqual(len(model_nums_names), 2)
      self.assertEqual(model_nums_names[0], (13, '000013-model'))
      self.assertEqual(model_nums_names[1], (17, '000017-model')) 

def validate(trained_models_dir, holdout_dir, estimator_model_dir, params):
  """Validate the latest model on the holdout dataset.

  Args:
    trained_models_dir: Directories where the completed generations/models are.
    holdout_dir: Directories where holdout data are.
    estimator_model_dir: tf.estimator model directory.
    params: A MiniGoParams instance of hyperparameters for the model.
  """
  model_num, _ = utils.get_latest_model(trained_models_dir)

  # Get the holdout game data
  nums_names = utils.get_models(trained_models_dir)

  # Model N was trained on games up through model N-1, so the validation set
  # should only be for models through N-1 as well, thus the (model_num) term.
  models = [num_name for num_name in nums_names if num_name[0] < model_num]

  # pair is a tuple of (model_num, model_name), like (13, 000013-modelname)
  holdout_dirs = [os.path.join(holdout_dir, pair[1])
                  for pair in models[-params.holdout_generation:]]
  tf_records = []
  with utils.logged_timer('Building lists of holdout files'):
    for record_dir in holdout_dirs:
      if os.path.exists(record_dir):  # make sure holdout dir exists
        tf_records.extend(
            tf.gfile.Glob(os.path.join(record_dir, '*'+_TF_RECORD_SUFFIX)))

  if not tf_records:
    print('No holdout dataset for validation! '
          'Please check your holdout directory: {}'.format(holdout_dir))
    return

  print('The length of tf_records is {}.'.format(len(tf_records)))
  first_tf_record = os.path.basename(tf_records[0])
  last_tf_record = os.path.basename(tf_records[-1])
  with utils.logged_timer('Validating from {} to {}'.format(
      first_tf_record, last_tf_record)):
    dualnet.validate(estimator_model_dir, tf_records, params)