CS20SI Tensorflow for Deeplearning课程笔记(一)

最新推荐文章于 2019-03-26 18:18:31 发布

原创最新推荐文章于 2019-03-26 18:18:31 发布 · 693 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#深度学习 #机器学习

Tensorflow 专栏收录该内容

4 篇文章

订阅专栏

本文介绍了TensorFlow的基础概念，包括张量、计算图等，并探讨了如何构建深度学习模型。同时推荐了一些学习资源，如《TensorFlow for Machine Intelligence》等书籍。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

一、课程目标

理解TF的计算图方法
探索TF的内置函数
学会怎么去构建和组织最好的模型去做深度学习项目

二、书籍

TensorFlow for Machine Intelligence (TFFMI)
Hands-On Machine Learning with Scikit-Learn and TensorFlow. Chapter 9
Up and running with TensorFlow
Fundamentals of Deep Learning. Chapter 3: Implementing Neural Networks in TensorFlow (FODL)
书籍容易过时，推荐tensorflow官网

三、简化版的Tensorflow

TF Learn (tf.contrib.learn)
TF Slim (tf.contrib.slim):
高级版 API: Keras, TFLearn, Pretty Tensor

四、Graphs and Sessions

1. tensor

一种n维的矩阵
0-d tensor: scalar (number)
1-d tensor: vector
2-d tensor: matrix
and so on

2. Data Flow Graphs

计算a的值的方式

import tensorflow as tf
a = tf.add(3, 5)
# with clause takes care
# of sess.close()
with tf.Session() as sess:
    print sess.run(a)

数据流图如下所示

这里写图片描述

3. tf.Session()

主要用于执行需要计算的tensor。

x = 2
y = 3
op1 = tf.add(x, y)
op2 = tf.mul(x, y)
op3 = tf.pow(op2, op1)
with tf.Session() as sess:
    op3 = sess.run(op3)

可以将图分成几部分，然后并行地计算在CPU,GPU上，如下图所示

这里写图片描述

4. tf.Graph()

添加一个运算给图，并将其设为默认图

g = tf.Graph()
with g.as_default():
    a = 3
    b = 5
    x = tf.add(a, b)
    sess = tf.Session(graph=g) # session is run on the graph g
# run session
    sess.close()

获取默认的图

g = tf.get_default_graph()

不要将默认的图和用户创建的图混合在一起，如下情况会报错

g = tf.Graph()
# add ops to the default graph
a = tf.constant(3)
# add ops to the user created graph
with g.as_default():
    b = tf.constant(5)
#Prone to errors

正确的使用方式

g1 = tf.get_default_graph()
g2 = tf.Graph()
# add ops to the default graph
with g1.as_default():
    a = tf.Constant(3)
# add ops to the user created graph
    with g2.as_default():
b = tf.Constant(5)

为什么使用Graph？
1. Save computation (only run subgraphs that lead to the values you want to fetch)
2. Break computation into small, differential pieces to facilitates auto-differentiation
3. Facilitate distributed computation, spread the work across multiple CPUs, GPUs, or devices
4. Many common machine learning models are commonly taught and visualized as directed graphs already