Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Getting Started with TensorFlow
Search
Rebecca Murphy
March 21, 2016
Programming
0
1.1k
Getting Started with TensorFlow
Rebecca Murphy
March 21, 2016
Tweet
Share
More Decks by Rebecca Murphy
See All by Rebecca Murphy
Refreerank
rebecca_roisin
0
110
pyFRET
rebecca_roisin
0
200
Other Decks in Programming
See All in Programming
1인 개발자로 행복하게 살기 - GDG 송도 헬로월드 2024
benjaminkim
1
5.6k
Rails と人魚の話/rails-and-mermaid
sanfrecce_osaka
0
100
Prepare for Jakarta EE 11 - Performance and Developer Productivity
ivargrimstad
0
470
VSCodeでのDatabricks開発もお勧めしたい/I would also recommend Databricks development with VSCode.
kazumain
0
240
データアナリストが行うDatabricksを活用したETLの自動化事例
shinoa
0
250
Rubyでたのしむクリエイティブコーディング/Enjoy Creative coding with Ruby
chobishiba
1
160
[技育CAMPアカデミア]アイディアを形に!【超入門】スマホアプリ開発〜リリースまでの流れをご紹介
teamlab
PRO
0
350
コーンフレークから始める モデリング会話入門
ogurotakayuki
0
280
エンターテイメント業界で利用されるAWS
demuyan
0
200
雑に思考を整理する技術と効能
konifar
55
26k
코틀린으로 멀티플랫폼 만들기
pangmoo
0
120
単体テストを書かない技術 #phpcon_odawara
o0h
PRO
26
7.9k
Featured
See All Featured
The Art of Programming - Codeland 2020
erikaheidi
41
12k
Optimizing for Happiness
mojombo
370
69k
Keith and Marios Guide to Fast Websites
keithpitt
408
22k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
34
8.9k
StorybookのUI Testing Handbookを読んだ
zakiyama
11
4.6k
Writing Fast Ruby
sferik
620
60k
Reflections from 52 weeks, 52 projects
jeffersonlam
344
19k
The Power of CSS Pseudo Elements
geoffreycrofte
59
5k
The Language of Interfaces
destraynor
151
23k
Designing Experiences People Love
moore
136
23k
Clear Off the Table
cherdarchuk
83
310k
Git: the NoSQL Database
bkeepers
PRO
422
63k
Transcript
TensorFlow Tutorial Rebecca Murphy
[email protected]
@rebecca_roisin TensorFlow Meetup Monday 21st
March 2016
Talk Overview • TensorFlow overview • Programming Model • Mechanics
of TensorFlow • Installation • Model Definition • Fitting • Checkpointing • TensorBoard visualisations • Why TensorFlow?
TensorFlow: Overview
What Is TensorFlow? • Google’s 2nd generation deep learning library
• Simple API (Python, C++) for: • Describing Machine Learning models • Implementing Machine Learning algorithms
What Can We Do With TensorFlow? • Regression models •
Neural networks • Deep learning: • Distributed representations • Convolutional Networks • Recurrent Neural Networks • LSTM Neural Networks
TensorFlow: Programming Model
TensorFlow: What Is a Tensor? • Tensor: n-dimensional array •
Scalar: 0D Tensor • Vector: 1D Tensor • Matrix: 2D Tensor • Typed: • Int, double, complex, string
Tensor Flows • Tensor Flow computations: stateful dataflow graphs •
Deep learning model = Directed graph • Node: (mathematical) operation • Edge: • Control dependencies • Data flow • Describe graph -> initialize -> execute (parts of ) graph
TensorFlow: Mechanics
Installing TensorFlow • Python API • Python 2.7 • Python
3.3+ • Setup instructions • pip install: • pip install --upgrade https://storage.googleapis. com/tensorflow/mac/tensorflow-0.7.1-cp27-none-any.whl • Docker: • docker run -it b.gcr.io/tensorflow/tensorflow
Mechanics of Learning • Define model • Load data •
Feed data • Make predictions • Evaluate • Visualise
Example Code • Try-tf github repositories • Associated blogpost •
Jason Baldridge @jasonbaldridge
Let’s get Started
Defining the Model
Model Definition: Key Features (1) • Tensor shapes are pre-defined:
• Tensors support mathematical manipulation • Operations are nodes in the model graph
Model Definition: Key Features (2) • Built-in functions for common
Deep Learning operations: • See Neural Network API for more • Gradient descent optimisation: • Variables store current state of model
Training the Model: Loading Data (1) • Load data into
variables • Need to write custom functions to parse data
Training the Model: Loading Data (2)
Training the Model: Sessions • Model graph describes computations •
Computations evaluated within a session: • Places graph onto CPU / GPU • Supplies methods to evaluate graph operations
The Feed Dict: Training the Model • Predefined placeholder tensors
• Feed-dict supplies batch of data
Training the Model: Evaluation • Pre-defined evaluation nodes compare predicted
and true labels: • Evaluate accuracy function within a session:
Checkpoints: Saving Models • Saver class allows model state to
be stored and reloaded • Use checkpoints to periodically save the state of the model
• Saver class allows model state to be stored and
reloaded • Restore a previously trained model Checkpoints: Loading Saved Models
Flags: Controlling Training • tf.app.flags: set command-line arguments • Wraps
python gflags • tf.app.run() parses flags before calling main()
TensorBoard: Visualising Learning
TensorBoard: Basics • TensorFlow visualisation tool • View • Graph
models • Training behaviour • Simple modifications to model code • Browser-based tool
TensorBoard: Annotations
TensorBoard: Scopes
TensorBoard: Saving Output • Set up summary and writer objects
• Periodically run evaluation and store output: • tensorboard --logdir=try_tf_logs/
TensorBoard: Model Visualisation (1)
TensorBoard: Model Visualisation (2)
TensorBoard: Training Visualisation (1)
TensorBoard: Training Visualisation (2)
TensorFlow: Where Next?
Why Use TensorFlow: Great Examples • TensorFlow Tutorials • Handwriting
generation from @hardmaru • Next letter prediction from @karpathy
Why Use TensorFlow: Active Community
TensorFlow: Future Developments • Improved memory usage in gradient calculations
• JIT Compilation • Improved node execution scheduling • Support for parallelisation across many machines • Support for more languages (Java, Lua, Go, R …) • Source: TensorFlow Whitepaper
Thank You!
Questions?