e74a5d43d931a182023566f1640bb8ec09a655c2,deepchem/models/tensorflow_models/__init__.py,TensorflowGraph,add_training_cost,#TensorflowGraph#,162

Before Change

        with self._shared_name_scope("aggregated"):
          with tf.name_scope("gradient"):
            loss = tf.add_n(gradient_costs)
          with tf.name_scope("old_cost"):
            old_loss = tf.add_n(old_costs)

          // weight decay
          if model_params["penalty"] != 0.0:
            penalty = model_ops.WeightDecay(model_params)
            loss += penalty
            old_loss += penalty

After Change

              // calculate with div/sum so it stays on the GPU.
              print("model_params["batch_size"]")
              print(model_params["batch_size"])
              print("weighted_cost")
              print(weighted_cost)
              gradient_cost = tf.div(tf.reduce_sum(weighted_cost),
                                     model_params["batch_size"])
              gradient_costs.append(gradient_cost)

Instances