tensor2tensor/models/research/vqa_self_attention.py [145:170]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  def body(self, features):
    hp = self.hparams
    # pylint: disable=eval-used
    if hp.image_input_type == "image":
      image_feat = vqa_layers.image_embedding(
          features["inputs"],
          model_fn=eval(hp.image_model_fn),
          trainable=hp.train_resnet,
          is_training=hp.mode == tf.estimator.ModeKeys.TRAIN)
    else:
      image_feat = features["inputs"]

    image_feat = common_layers.flatten4d3d(image_feat)
    image_hidden_size = hp.hidden_size
    image_feat = common_layers.dense(image_feat, image_hidden_size)
    utils.collect_named_outputs("norms", "image_feat_after_proj",
                                tf.norm(image_feat, axis=-1))

    question = common_layers.flatten4d3d(features["question"])
    utils.collect_named_outputs("norms", "question_embedding",
                                tf.norm(question, axis=-1))
    (encoder_input, encoder_self_attention_bias,
     encoder_decoder_attention_bias) = prepare_image_question_encoder(
         image_feat, question, hp)
    encoder_input = tf.nn.dropout(
        encoder_input, keep_prob=1.-hp.layer_prepostprocess_dropout)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensor2tensor/models/research/vqa_self_attention.py [210:235]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  def body(self, features):
    hp = self.hparams
    # pylint: disable=eval-used
    if hp.image_input_type == "image":
      image_feat = vqa_layers.image_embedding(
          features["inputs"],
          model_fn=eval(hp.image_model_fn),
          trainable=hp.train_resnet,
          is_training=hp.mode == tf.estimator.ModeKeys.TRAIN)
    else:
      image_feat = features["inputs"]

    image_feat = common_layers.flatten4d3d(image_feat)
    image_hidden_size = hp.hidden_size
    image_feat = common_layers.dense(image_feat, image_hidden_size)
    utils.collect_named_outputs("norms", "image_feat_after_proj",
                                tf.norm(image_feat, axis=-1))

    question = common_layers.flatten4d3d(features["question"])
    utils.collect_named_outputs("norms", "question_embedding",
                                tf.norm(question, axis=-1))
    (encoder_input, encoder_self_attention_bias,
     encoder_decoder_attention_bias) = prepare_image_question_encoder(
         image_feat, question, hp)
    encoder_input = tf.nn.dropout(
        encoder_input, keep_prob=1.-hp.layer_prepostprocess_dropout)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -