def model_fn()

in example_zoo/tensorflow/models/mnist/official/mnist/mnist.py [0:0]

• 42 lines of code
• 5 McCabe index (conditional complexity)

def model_fn(features, labels, mode, params):
  """The model_fn argument for creating an Estimator."""
  model = create_model(params['data_format'])
  image = features
  if isinstance(image, dict):
    image = features['image']

  if mode == tf.estimator.ModeKeys.PREDICT:
    logits = model(image, training=False)
    predictions = {
        'classes': tf.argmax(logits, axis=1),
        'probabilities': tf.nn.softmax(logits),
    }
    return tf.estimator.EstimatorSpec(
        mode=tf.estimator.ModeKeys.PREDICT,
        predictions=predictions,
        export_outputs={
            'classify': tf.estimator.export.PredictOutput(predictions)
        })
  if mode == tf.estimator.ModeKeys.TRAIN:
    optimizer = tf.train.AdamOptimizer(learning_rate=LEARNING_RATE)

    logits = model(image, training=True)
    loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
    accuracy = tf.metrics.accuracy(
        labels=labels, predictions=tf.argmax(logits, axis=1))

    # Name tensors to be logged with LoggingTensorHook.
    tf.identity(LEARNING_RATE, 'learning_rate')
    tf.identity(loss, 'cross_entropy')
    tf.identity(accuracy[1], name='train_accuracy')

    # Save accuracy scalar to Tensorboard output.
    tf.summary.scalar('train_accuracy', accuracy[1])

    return tf.estimator.EstimatorSpec(
        mode=tf.estimator.ModeKeys.TRAIN,
        loss=loss,
        train_op=optimizer.minimize(loss, tf.train.get_or_create_global_step()))
  if mode == tf.estimator.ModeKeys.EVAL:
    logits = model(image, training=False)
    loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
    return tf.estimator.EstimatorSpec(
        mode=tf.estimator.ModeKeys.EVAL,
        loss=loss,
        eval_metric_ops={
            'accuracy':
                tf.metrics.accuracy(
                    labels=labels, predictions=tf.argmax(logits, axis=1)),
        })