def build_stats()

in example_zoo/tensorflow/models/keras_imagenet_main/official/resnet/keras/keras_common.py [0:0]

• 22 lines of code
• 8 McCabe index (conditional complexity)

def build_stats(history, eval_output, time_callback):
  """Normalizes and returns dictionary of stats.

  Args:
    history: Results of the training step. Supports both categorical_accuracy
      and sparse_categorical_accuracy.
    eval_output: Output of the eval step. Assumes first value is eval_loss and
      second value is accuracy_top_1.
    time_callback: Time tracking callback likely used during keras.fit.

  Returns:
    Dictionary of normalized results.
  """
  stats = {}
  if eval_output:
    stats['accuracy_top_1'] = eval_output[1].item()
    stats['eval_loss'] = eval_output[0].item()

  if history and history.history:
    train_hist = history.history
    # Gets final loss from training.
    stats['loss'] = train_hist['loss'][-1].item()
    # Gets top_1 training accuracy.
    if 'categorical_accuracy' in train_hist:
      stats[TRAIN_TOP_1] = train_hist['categorical_accuracy'][-1].item()
    elif 'sparse_categorical_accuracy' in train_hist:
      stats[TRAIN_TOP_1] = train_hist['sparse_categorical_accuracy'][-1].item()

  if time_callback:
    timestamp_log = time_callback.timestamp_log
    stats['step_timestamp_log'] = timestamp_log
    stats['train_finish_time'] = time_callback.train_finish_time
    if len(timestamp_log) > 1:
      stats['avg_exp_per_second'] = (
          time_callback.batch_size * time_callback.log_steps *
          (len(time_callback.timestamp_log)-1) /
          (timestamp_log[-1].timestamp - timestamp_log[0].timestamp))

  return stats