Tensorflow Intro
1. Tensorflow core concept
Tensorflow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications. A computing system based on graph.
Two steps using Tensorflow:
(1) Graph Built (operation + tensor)
Graph consisted of operations; Each operations of a graph connected together with Tensor, therefore the computing process in Tensorflow is a flow of Tensor.
(2) Graph implementation
Graph must be calulated adn implemented using Session(), session offers the env for operation implementation and tensor calucation.
code example:
import tensorflow as tf
# Build a graph.
a = tf.constant([1.0, 2.0])
b = tf.constant([3.0, 4.0])
c = a * b
# Launch the graph in a session.
sess = tf.Session()
# Evaluate the tensor 'c'.
print sess.run(c)
sess.close()
# result: [3., 8.]
2. Tensorflow詳解
2.1 Tensorflow structure：
(1) Tensor
(2) Variable
(3) op
