Function train_fn

code/logistic_cg.py:240–244

(theta_value)

    # creates a function that computes the average cost on the training set
    def train_fn(theta_value):
        classifier.theta.set_value(theta_value, borrow=True)
        train_losses = [batch_cost(i * batch_size)
                        for i in range(n_train_batches)]
        return numpy.mean(train_losses)

    # creates a function that computes the average gradient of cost with
    # respect to theta