TensorFlow Basic

1. Graph and Sessions

TensorFlow는 계산 정의를 실행과 분리합니다.

Phase 1: 그래프 조립

Phase 2: 그래프의 연산자를 실행하기 위해 세션을 사use a session to execute operations in the graph.

Tensor란?

An n-dimensional matrix

0-d tensor: scalar (number)

1-d tensor: vector

2-d tensor: matrix

and so on

Data Flow Graphs

import tensorflow as tf

a = tf.add(3, 5)

print a

>> Tensor("Add:0", shape=(), dtype=int32)

(Not 5)

Why x, y?

TF automatically names the nodes when you don’t explicitly name them. More about this next lecture! For now: x = 3 y = 5

Nodes: operators, variables, and constants

Edges: tensors

Tensors are data. Data Flow -> Tensor Flow (I know, mind=blown)

How to get the value of a?

Create a session, assign it to variable sess so we can call it later Within the session, evaluate the graph to fetch the value of a