Why does TensorFlow example fail when increasing batch size?

Question

I was looking at the Tensorflow MNIST example for beginners and found that in this part:

for i in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(1         


        

Answer 1

Nan occurs when 0*log(0) occurs:

replace:

cross_entropy = -tf.reduce_sum(y_*tf.log(y))

with:

cross_entropy = -tf.reduce_sum(y_*tf.log(y + 1e-10))