INNER CODE UNIT · Python

gradient_cost

deepchem/deepchem · contrib/tensorflow_models/__init__.py:283

              gradient_cost = tf.math.divide(
                  tf.reduce_sum(weighted_cost), self.batch_size)
              gradient_costs.append(gradient_cost)

        # aggregated costs
        with TensorflowGraph.shared_name_scope('aggregated', graph,
                                               name_scopes):
          with tf.name_scope('gradient'):
            loss = tf.add_n(gradient_costs)

          # weight decay
          if self.penalty != 0.0:
            penalty = model_ops.weight_decay(self.penalty_type, self.penalty)
            loss += penalty

      return loss

  def fit(self,

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…