Notice code in file: https://github.com/GoogleCloudPlatform/tensorflow-without-a-phd/blob/master/tensorflow-mnist-tutorial/mnist_1.0_softmax.py

# cross-entropy
# log takes the log of each element, * multiplies the tensors element by element
# reduce_mean will add all the components in the tensor
# so here we end up with the total cross-entropy for all images in the batch
cross_entropy = -tf.reduce_mean(Y_ * tf.log(Y)) * 1000.0  # normalized for batches of 100 images,
# *10 because  "mean" included an unwa ... ...