frame_level_models.py 文件源码

def create_model(self, model_input, vocab_size, num_frames, **unused_params):
    """Creates a model which uses a logistic classifier over the average of the
    frame-level features.

    This class is intended to be an example for implementors of frame level
    models. If you want to train a model over averaged features it is more
    efficient to average them beforehand rather than on the fly.

    Args:
      model_input: A 'batch_size' x 'max_frames' x 'num_features' matrix of
                   input features.
      vocab_size: The number of classes in the dataset.
      num_frames: A vector of length 'batch' which indicates the number of
           frames for each video (before padding).

    Returns:
      A dictionary with a tensor containing the probability predictions of the
      model in the 'predictions' key. The dimensions of the tensor are
      'batch_size' x 'num_classes'.
    """
    num_frames = tf.cast(tf.expand_dims(num_frames, 1), tf.float32)
    feature_size = model_input.get_shape().as_list()[2]
    max_frames = model_input.get_shape().as_list()[1]


    denominators = tf.reshape(
        tf.tile(num_frames, [1, feature_size]), [-1, feature_size])
    avg_pooled = tf.reduce_sum(model_input,
                               axis=[1]) / denominators
    output = slim.fully_connected(
        avg_pooled, vocab_size, activation_fn=tf.nn.sigmoid,
        weights_regularizer=slim.l2_regularizer(1e-8))
    return {"predictions": output}