Comparison Between Deep Learning Packages

Slides:



Advertisements
Similar presentations
Theano Md. Iftekhar Tanveer Rafayet Ali Md. Iftekhar Tanveer Rafayet Ali.
Advertisements

HPCC Mid-Morning Break High Performance Computing on a GPU cluster Dirk Colbry, Ph.D. Research Specialist Institute for Cyber Enabled Discovery.
Ch 1. Introduction Dr. Bernard Chen Ph.D. University of Central Arkansas Spring 2012.
A General Distributed Deep Learning Platform
Deep Learning for Julia Chiyuan Zhang CSAIL, MIT
Students: Meera & Si Mentor: Afshin Dehghan WEEK 4: DEEP TRACKING.
Facial Detection via Convolutional Neural Network Nathan Schneider.
Fill-in-The-Blank Using Sum Product Network
Comparing TensorFlow Deep Learning Performance Using CPUs, GPUs, Local PCs and Cloud Pace University, Research Day, May 5, 2017 John Lawrence, Jonas Malmsten,
TensorFlow The Deep Learning Library You Should Be Using.
TENSORFLOW Team 2: Andrey, Daniel, John, Jonas, Ken
TensorFlow CS 5665 F16 practicum Karun Joseph, A Reference:
Deep Learning Software: TensorFlow
Analysis of Sparse Convolutional Neural Networks
CS 6501: 3D Reconstruction and Understanding Convolutional Neural Networks Connelly Barnes.
BigDL Deep Learning Library on HDInsight
Big Data A Quick Review on Analytical Tools
CS 6825: Deep Learning and CNN
Why it is Called Tensor Flow Parallelism in ANNs Project Ideas and Discussion Glenn Fung Presents Batch Renormalizating Paper.
Deep Learning Insights and Open-ended Questions
Deep Learning in HEP Large number of applications:
Computing Gradient Hung-yi Lee 李宏毅
Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay.
Matt Gormley Lecture 16 October 24, 2016
Deep Learning Platform as a Service
Low-Cost High-Performance Computing Via Consumer GPUs
Deep Learning Libraries
Overview of TensorFlow
A VERY Brief Introduction to Convolutional Neural Network using TensorFlow 李 弘
First Steps With Deep Learning Course.
Deep Learning Workshop
TensorFlow and Clipper (Lecture 24, cs262a)
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Project Implementation for ITCS4122
Torch 02/27/2018 Hyeri Kim Good afternoon, everyone. I’m Hyeri. Today, I’m gonna talk about Torch.
Introduction to Deep Learning for neuronal data analyses
Tensorflow in Deep Learning
Handwritten Digits Recognition
INF 5860 Machine learning for image classification
Brewing Deep Networks With Caffe
Neural network systems
Deep Learning Packages
Introduction to Tensorflow
Deep Learning Tutorial
Counting in Dense Crowds using Deep Learning
MXNet Internals Cyrus M. Vahid, Principal Solutions Architect,
ECE 599/692 – Deep Learning Lecture 1 - Introduction
Introduction to Deep Learning with Keras
SAS Deep Learning: From Toolkit to Fast Model Prototyping
Overview of big data tools
Automated Video Cutting:
CSC 578 Neural Networks and Deep Learning
Declarative Transfer Learning from Deep CNNs at Scale
Vinit Shah, Joseph Picone and Iyad Obeid
Object Tracking: Comparison of
Debugging Dataflow Graphs using TensorFlow Debugger.
Martin Schrimpf & Jon Gauthier MIT BCS Peer Lectures
TensorFlow: A System for Large-Scale Machine Learning
Deep Learning Authors: Yann LeCun, Yoshua Bengio, Geoffrey Hinton
Sketch Object Prediction
H2O is used by more than 14,000 companies
Deep Learning Libraries
Action Recognition.
CSC 578 Neural Networks and Deep Learning
Real-time Object Recognition using deep learning-Raspberry Pi
YOLO-based Object Detection on ARM Mali GPU
Igor Stančin, Alan Jović to: {igor.stancin,
Parallel Systems to Compute
Andrew Karl, Ph.D. James Wisnowski, Ph.D. Lambros Petropoulos
Machine Learning for Cyber
Presentation transcript:

Comparison Between Deep Learning Packages Yi Wu 9/22/2018

Outlines Background Caffe Theano TensorFlow Work Preliminary Results 9/22/2018

Background 9/22/2018

Background 9/22/2018

Background 9/22/2018

Caffe From UC Berkeley Written in C++ Python bindings 9/22/2018

Caffe Network structures are stored in .proto files 9/22/2018 http://caffe.berkeleyvision.org/tutorial/net_layer_blob.html

Caffe Model Zoo https://github.com/BVLC/caffe/wiki/Model-Zoo 9/22/2018

Caffe (+) Train models without writing any code (+) Lots of pre-trained models, good for testing and fine-tuning (+) Python interface (-) Cumbersome for big networks (-) No good for recurrent networks 9/22/2018

Theano From Yoshua Bengio’s group at University of Montreal symbolic computation compatible with Python 9/22/2018

Theano gradient on anything http://www.marekrei.com/blog/theano-tutorial/ 9/22/2018

Theano black box magic http://www.marekrei.com/blog/theano-tutorial/ 9/22/2018

Theano (+) Python + numpy (+) computation graph (+) RNN fits nicely in computation graph (-) Hard to manually optimize 9/22/2018

TensorFlow From Google Computation graphs Scalable 9/22/2018

TensorFlow X h h2 y w_h2 w_h w_0 https://github.com/nlintz/TensorFlow-Tutorials/blob/master/04_modern_net.py 9/22/2018

TensorFlow X h h2 y w_h2 w_h w_0 define graph nodes https://github.com/nlintz/TensorFlow-Tutorials/blob/master/04_modern_net.py 9/22/2018

TensorFlow X h h2 y w_h2 w_h w_0 define graph edges https://github.com/nlintz/TensorFlow-Tutorials/blob/master/04_modern_net.py 9/22/2018

TensorFlow Tensorboard http://thenewstack.io/look-inside-tensorflow-googles-open-source-deep-learning-framework/ 9/22/2018

Work Image classification (CNN) data: PASCAL 2012 model: VGG16 21 classes 11540 images (random 1000) model: VGG16 9/22/2018

Work Hardware data: 1000 images test for speed CPU: I7 4GHz GPU: GTX 1080 RAM: 32G data: 1000 images test for speed CPU: Caffe vs Theano vs TensorFlow GPU: Theano vs TensorFlow test for easiness to use installation code test & debug visualization 9/22/2018

Preliminary Result 9/22/2018

Preliminary Result training with GPU predicted class takes 2 sec 9/22/2018