Welcome to TensorFlow!

CS 20: TensorFlow for Deep Learning Research

Lecture 1
1/12/2018

1
Thanks Danijar Hafner for the logo!
2
 Agenda
Welcome

Overview of TensorFlow

Graphs and Sessions

3
 What’s TensorFlow™?

“Open source software library for

numerical computation using data flow graphs”

4
Launched Nov 2015

5
 Why TensorFlow?
● Many machine learning libraries

6
 Why TensorFlow?
● Flexibility + Scalability
Originally developed by Google as a single infrastructure for machine learning
in both production and research

7
 Why TensorFlow?
● Flexibility + Scalability
● Popularity

8
Companies using TensorFlow

9
Demand for tutorials on TensorFlow

10
Some cool projects using
TensorFlow

11
 Classify skin cancer

Dermatologist-level classification of skin cancer with deep neural networks (Esteva et al., Nature 2017) 12
 WaveNet: Text to Speech
It takes several hours to synthesize 1 second!

Wavenet: A generative model for raw audio (Oord et al., 2016) 13

 Drawing

Draw Together with a Neural Network (Ha et al., 2017) 14

 Neural Style Translation

Image Style Transfer Using Convolutional Neural Networks (Gatys et al., 2016)
15
Tensorflow adaptation by Cameroon Smith (cysmith@github)
I hope that this class will give you
the tool to build cool projects like
those!
16
 Goals
● Understand TF’s computation graph approach
● Explore TF’s built-in functions and classes
● Learn how to build and structure models best suited for a deep learning
project

17
CS20

18
 Staff

Chip Huyen Michael Straka Pedro Garzon

[email protected] [email protected] [email protected]

19
 Logistics
● Piazza: piazza.com/stanford/winter2018/cs20
● Staff email: [email protected]
● Students mailing list: cs20-win1718-students
● Guests mailing list: cs20-win1718-guests

20
 Grading
● Assignments (3)
● Participation
● Check in

21
 Resources
● The official documentations
● TensorFlow’s official sample models
● StackOverflow should be your first port of call in case of bug
● Books
○ Aurélien Géron’s Hands-On Machine Learning with Scikit-Learn and TensorFlow (O’Reilly,
March 2017)
○ François Chollet’s Deep Learning with Python (Manning Publications, November 2017)
○ Nishant Shukla’s Machine Learning with TensorFlow (Manning Publications, January 2018)
○ Lieder et al.’s Learning TensorFlow A Guide to Building Deep Learning Systems (O’Reilly,
August 2017)

22
 Permission Number
Link

23
 Many of you are ahead of me in
academia so I probably need more
of your help than you do mine
24
Getting Started

25
import tensorflow as tf

26
Graphs and Sessions

27
 Data Flow Graphs

TensorFlow separates definition of computations from their execution

Graph from TensorFlow for Machine Intelligence 28

 Data Flow Graphs

Phase 1: assemble a graph

Phase 2: use a session to execute operations in the graph.

Graph from TensorFlow for Machine Intelligence 29

 Data Flow Graphs
This might change in the
Phase 1: assemble a graph future with eager mode!!

Phase 2: use a session to execute operations in the graph.

Graph from TensorFlow for Machine Intelligence 30

What’s a tensor?

31
 What’s a tensor?

An n-dimensional array

0-d tensor: scalar (number)

1-d tensor: vector

2-d tensor: matrix

and so on

32
 Data Flow Graphs

import tensorflow as tf Visualized by TensorBoard

a = tf.add(3, 5)

33
 Data Flow Graphs

import tensorflow as tf Visualized by TensorBoard

a = tf.add(3, 5)

Why x, y?

TF automatically names the nodes when you don’t

explicitly name them.
x=3
y=5

34
 Data Flow Graphs

import tensorflow as tf Interpreted?

a = tf.add(3, 5)

3
Nodes: operators, variables, and constants
Edges: tensors 5 a

35
 Data Flow Graphs

import tensorflow as tf Interpreted?

a = tf.add(3, 5)

3
Nodes: operators, variables, and constants
Edges: tensors 5 a

Tensors are data.

TensorFlow = tensor + flow = data + flow
(I know, mind=blown)

36
 Data Flow Graphs

import tensorflow as tf
a = tf.add(3, 5)
print(a)
3

5 a

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

(Not 8)

37
 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

38
 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

import tensorflow as tf
a = tf.add(3, 5)
sess = tf.Session()
print(sess.run(a))
sess.close()

The session will look at the graph, trying to think: hmm, how can I get the value of a,
then it computes all the nodes that leads to a. 39
 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

import tensorflow as tf
a = tf.add(3, 5)
sess = tf.Session()
print(sess.run(a)) >> 8
sess.close() 8

The session will look at the graph, trying to think: hmm, how can I get the value of a,
then it computes all the nodes that leads to a. 40
 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

import tensorflow as tf
a = tf.add(3, 5)
sess = tf.Session()
with tf.Session() as sess:
print(sess.run(a)) 8
sess.close()

41
 tf.Session()

A Session object encapsulates the environment in which Operation objects are

executed, and Tensor objects are evaluated.

42
 tf.Session()

A Session object encapsulates the environment in which Operation objects are

executed, and Tensor objects are evaluated.

Session will also allocate memory to store the current values of variables.

43
 More graph
Visualized by TensorBoard
x = 2
y = 3
op1 = tf.add(x, y)
op2 = tf.multiply(x, y)
op3 = tf.pow(op2, op1)
with tf.Session() as sess:
op3 = sess.run(op3)

44
 Subgraphs
x = 2
y = 3 useless pow_op
add_op = tf.add(x, y)
mul_op = tf.multiply(x, y)
useless = tf.multiply(x, add_op)
pow_op = tf.pow(add_op, mul_op)
with tf.Session() as sess:
z = sess.run(pow_op)
add_op mul_op

Because we only want the value of pow_op and pow_op doesn’t

depend on useless, session won’t compute value of useless
→ save computation

45
 Subgraphs
x = 2
y = 3 useless pow_op
add_op = tf.add(x, y)
mul_op = tf.multiply(x, y)
useless = tf.multiply(x, add_op)
pow_op = tf.pow(add_op, mul_op)
with tf.Session() as sess:
z, not_useless = sess.run([pow_op,
useless]) add_op mul_op

tf.Session.run(fetches,
feed_dict=None,
options=None,
run_metadata=None)
46
fetches is a list of tensors whose values you want
 Subgraphs
Possible to break graphs into
several chunks and run them
parallelly across multiple CPUs,
GPUs, TPUs, or other devices

Example: AlexNet

Graph from Hands-On Machine Learning with Scikit-Learn and TensorFlow 47

 Distributed Computation
To put part of a graph on a specific CPU or GPU:

# Creates a graph.
with tf.device('/gpu:2'):
a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], name='a')
b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], name='b')
c = tf.multiply(a, b)

# Creates a session with log_device_placement set to True.

sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))

# Runs the op.

print(sess.run(c))

48
What if I want to build more
than one graph?

49
 You can
but you don’t need more than one graph
The session runs the default graph

50
But what if I really want to?

51
URGH, NO

52
 BUG ALERT!

● Multiple graphs require multiple sessions, each will try to use all
available resources by default
● Can't pass data between them without passing them through
python/numpy, which doesn't work in distributed
● It’s better to have disconnected subgraphs within one graph

53
I insist ...

54
 tf.Graph()
create a graph:

g = tf.Graph()

55
 tf.Graph()
to add operators to a graph, set it as default:

g = tf.Graph()
with g.as_default():
x = tf.add(3, 5)
sess = tf.Session(graph=g)
with tf.Session() as sess:
sess.run(x)

56
 tf.Graph()
To handle the default graph:

g = tf.get_default_graph()

57
 tf.Graph()
Do not mix default graph and user created graphs

g = tf.Graph()

# add ops to the default graph

a = tf.constant(3)

# add ops to the user created graph Prone to errors

with g.as_default():
b = tf.constant(5)

58
 tf.Graph()
Do not mix default graph and user created graphs

g1 = tf.get_default_graph()
g2 = tf.Graph()

# add ops to the default graph

with g1.as_default():
a = tf.Constant(3) Better
But still not good enough because no more than
# add ops to the user created graph one graph!
with g2.as_default():
b = tf.Constant(5)

59
60
 Why graphs

1. Save computation. Only run subgraphs that lead

to the values you want to fetch.

61
 Why graphs

1. Save computation. Only run subgraphs that lead

to the values you want to fetch.
2. Break computation into small, differential pieces
to facilitate auto-differentiation

62
 Why graphs

1. Save computation. Only run subgraphs that lead

to the values you want to fetch.
2. Break computation into small, differential pieces
to facilitate auto-differentiation
3. Facilitate distributed computation, spread the
work across multiple CPUs, GPUs, TPUs, or other
devices

63
 Why graphs

1. Save computation. Only run subgraphs that lead

to the values you want to fetch.
2. Break computation into small, differential pieces
to facilitate auto-differentiation
3. Facilitate distributed computation, spread the
work across multiple CPUs, GPUs, TPUs, or other
devices
4. Many common machine learning models are
taught and visualized as directed graphs
A neural net graph from Stanford’s
CS224N course
64
 Next class
Basic operations

Constants and variables

Data pipeline

Fun with TensorBoard

Feedback: [email protected]

Thanks!

65