fe9ebeefe7593432d1df9cb2c8b7ffdc8ec1a38b,tensorlayer/cost.py,,cross_entropy,#Any#Any#,12

Before Change

    The code is borrowed from: `here <https://en.wikipedia.org/wiki/Cross_entropy>`_.
    
    with tf.name_scope("cross_entropy_loss"):
        net_output_tf = output
        target_tf = target
        cross_entropy = tf.add(tf.mul(tf.log(net_output_tf, name=None),target_tf),
                             tf.mul(tf.log(1 - net_output_tf), (1 - target_tf)))
        return -1 * tf.reduce_mean(tf.reduce_sum(cross_entropy, 1), name="cross_entropy_mean")

def mean_squared_error(output, target):
    Return the cost function of Mean-squre-error of two distributions.

After Change

        // cross_entropy = tf.add(tf.mul(tf.log(net_output_tf, name=None),target_tf),
        //                      tf.mul(tf.log(1 - net_output_tf), (1 - target_tf)))
        // return -1 * tf.reduce_mean(tf.reduce_sum(cross_entropy, 1), name="cross_entropy_mean")
        return tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(output, target))

def mean_squared_error(output, target):
    Return the cost function of Mean-squre-error of two distributions.

Instances