Deep Learning By Example

Operations

Operations are nodes that represent mathematical operations over the tensors on a graph. These operations can be any kind of functions, like add and subtract tensors, or maybe an activation function.

tf.matmul, tf.add, and tf.nn.sigmoid are some of the operations in TensorFlow. These are like functions in Python, but operate directly over tensors and each one does a specific thing.

Other operations can be easily found at: https://www.tensorflow.org/api_guides/python/math_ops.

Let's play around with some of these operations:

a = tf.constant([5])b = tf.constant([2])c = tf.add(a,b)d = tf.subtract(a,b)with tf.Session() as session:    result = session.run(c)    print 'c =: %s' % result    result = session.run(d)    print 'd =: %s' % result

Output: ...