Danbury AI
IS Sponsored By:
Machine Learning With TensorFlow
TensorFlow™ is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well.
Presented By: Andrew & Mike
Overview
Deep Learning Framework Space
(+) Great Model Zoo
(+) Good deployment infrastructure.
(+) Support for heterogeneous distributed systems
(+) Mobile Friendly
(+) Python and C++ Interfaces
(+) Deep learning frameworks built on top ( Keras, Lasagne and Blocks )
(+) Long academic history
(+) Python + Numpy
(+) Abundance of pretrained models
(+/-) Lua
(+) Used by Facebook and Twitter
What is TensorFlow?
TensorFlow Features
interface to build and execute your computational graphs. SWIG extensions.
The Data Flow Graph
Data Flow Graph Efficiency
dictate which parts of the computation graph should be run.
Graph Example
Installing TensorFlow ( Python 2 )
# Ubuntu/Linux 64-bit�$ sudo apt-get install python-pip python-dev python-virtualenv��# Mac OS X�$ sudo easy_install pip�$ sudo pip install --upgrade virtualenv
$ virtualenv --system-site-packages ~/tensorflow
Installing TensorFlow ( Python 2 )
$ source ~/tensorflow/bin/activate # If using bash�$ source ~/tensorflow/bin/activate.csh # If using csh�(tensorflow)$ # Your prompt should change��# Ubuntu/Linux 64-bit, CPU only:�(tensorflow)$ pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.8.0-cp27-none-linux_x86_64.whl��# Ubuntu/Linux 64-bit, GPU enabled. Requires CUDA toolkit 7.5 and CuDNN v4. For�# other versions, see "Install from sources" below.�(tensorflow)$ pip install --upgrade https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.8.0-cp27-none-linux_x86_64.whl��# Mac OS X, CPU only:�(tensorflow)$ pip install --upgrade
https://storage.googleapis.com/tensorflow/mac/tensorflow-0.8.0-py2-none-any.whl�
Installing TensorFlow ( Python 2 )
$ source ~/tensorflow/bin/activate # If using bash.�$ source ~/tensorflow/bin/activate.csh # If using csh.�(tensorflow)$ # Your prompt should change.�# Run Python programs that use TensorFlow.�...�# When you are done using TensorFlow, deactivate the environment.�(tensorflow)$ deactivate
TensorBoard
A Single Neuron
DEMO
See “Beginner MINST.ipynb” on repo
MNIST Walkthrough
DEMO
See “Beginner MINST.ipynb” on repo
TF Learn
TensorFlow GPU Processing
GPU > CPU
GPU = CPU
GPU < CPU
Sliding Window MNIST
DEMO
Resources and Sources
Resources & Sources
Resources & Sources
QUESTIONS& COMMMENTS
Presented By: Andrew Ribeiro
And Michael Rogowski
UNUSED SLIDES
TensorBoard: class tf.train.SummaryWriter
Softmax Regression Model