SlideShare a Scribd company logo
TRANSFER LEARNING
Max Pagels, Data Science Specialist
@maxpagels, linkedin.com/in/maxpagels/
MACHINE LEARNING NEEDS DATA TO WORK
The more, the better. But what if you don’t have a lot of data to work with, and
no time to collect more? Is ML still an option?
IN SOME CASES, YES.
For general regression and classification problems such as face detection and
image recognition, there are lots (but still not enough) of freely available
datasets online that you can use to train your own models.
MNIST
70,000 28x28px labelled images of handwritten digits 0-9
FASHION MNIST
70,000 28x28px labelled images of clothing items (ten classes)
VGG FACE DATASET
Portrait images of 2,622 identities
CIFAR-10
60,000 32x32px colour images belonging to one of ten classes (airplane,
automobile, cat, deer etc.)
CIFAR-100
60,000 32x32px colour images belonging to one of a hundred different classes
GTD
Data from more than 170,000 terrorist attacks worldwide, 1970-2016
FOOD 101
101,000 images of 101 types of food items
YOUTUBE-8M
Over 7 million YouTube videos across 4716 classes
LOTS MORE ON KAGGLE
https://www.kaggle.com/datasets
INSTEAD OF TRAINING MODELS YOURSELF,
YOU CAN ALSO USE PRE-TRAINED ONES
If you use a well known dataset such as MNIST or CIFAR-10, chances are
someone’s already trained a neural network, random forest, or some other
learning algorithm on it with high accuracy.
BUT WHAT IF WE HAVE A SPECIFIC PROBLEM
FOR WHICH NO PRE-TRAINED MODEL EXISTS?
Can we somehow leverage the information learned by some pre-trained
model and adapt it to our specific use case?
EXAMPLE
Say we want to build a food classifier that reliably determine if an image
contains one of two Finnish dishes: fried baltic herring or fried perch?
A model pre-trained on Food 101 has learned a lot about what a fish looks like,
but the dataset doesn’t include images of fried baltic herring or fried perch.
Could we use the wisdom the model has learned about fish in order to make
building our custom model easier?
YES, AND IT’S CALLED TRANSFER LEARNING
The basic idea is to take a pre-trained model that has already learning useful
representations and tailor it to a custom use case.
TRANSFER LEARNING, IN A NUTSHELL
Say you have a pre-trained neural network that you would like to adapt to
your use case. To do transfer learning:
1. Chop off the neurons in the last layer of the model
2. Replace neurons with new ones, one neuron per class you want to predict
(or just one neuron in total if doing regression)
3. Finish training using a dataset of labelled images specific to your problem
Why would you want to do this?
ONE MAJOR REASON
You need less labelled data. A lot less. Usually, 50-100 labelled examples is
more than enough.
HOW DOES ONE IMPLEMENT TRANSFER
LEARNING?
You can do transfer learning quite easily in code using Keras, MXNet,
TensorFlow, CNTK etc: download pre-trained model, freeze weights, remove
last layer, add new layer.
There are, however, ready-made, zero-coding-required cloud services that
can do it for you.
CUSTOMVISION.AI DEMO
Transfer learning as a service
THANK YOU!
Special thanks to Ari Bornstein from Microsoft for the inspiration!
QUESTIONS?

More Related Content

Similar to Transfer learning with Custom Vision

B4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearningB4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearning
Hoa Le
 
[Revised] Intro to CNN
[Revised] Intro to CNN[Revised] Intro to CNN
[Revised] Intro to CNN
Vincent Tatan
 
How can we train with few data
How can we train with few dataHow can we train with few data
How can we train with few data
Dong Heon Cho
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
Kavika Roy
 
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDistributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Databricks
 
Fine-tuning Pre-Trained Models for Generative AI Applications
Fine-tuning Pre-Trained Models for Generative AI ApplicationsFine-tuning Pre-Trained Models for Generative AI Applications
Fine-tuning Pre-Trained Models for Generative AI Applications
Benjaminlapid1
 
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical ResearchII-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
Dr. Haxel Consult
 
Designing a neural network architecture for image recognition
Designing a neural network architecture for image recognitionDesigning a neural network architecture for image recognition
Designing a neural network architecture for image recognition
ShandukaniVhulondo
 
Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.
Fernando Constantino
 
Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learning
ShareDocView.com
 
Classification case study + intro to cnn
Classification case study + intro to cnnClassification case study + intro to cnn
Classification case study + intro to cnn
Vincent Tatan
 
Python Machine Learning January 2018 - Ho Chi Minh City
Python Machine Learning January 2018 - Ho Chi Minh CityPython Machine Learning January 2018 - Ho Chi Minh City
Python Machine Learning January 2018 - Ho Chi Minh City
Andrew Schwabe
 
GDSC Unsri - From Zero to Hero with TensorFlow.pptx
GDSC Unsri - From Zero to Hero with TensorFlow.pptxGDSC Unsri - From Zero to Hero with TensorFlow.pptx
GDSC Unsri - From Zero to Hero with TensorFlow.pptx
FellyciaHikmahwarani
 
Week3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptxWeek3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptx
fahmi324663
 
Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...
Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...
Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...
Michael Batavia
 
Machine learning with TensorFlow
Machine learning with TensorFlow  Machine learning with TensorFlow
Machine learning with TensorFlow
Eslam Saeed
 
Automation, intelligence and knowledge modelling
Automation, intelligence and knowledge modellingAutomation, intelligence and knowledge modelling
Automation, intelligence and knowledge modelling
Veselin Pizurica
 
Machine learning || Introduction || Main Components || Examples || Techniques
Machine learning || Introduction || Main Components || Examples || TechniquesMachine learning || Introduction || Main Components || Examples || Techniques
Machine learning || Introduction || Main Components || Examples || Techniques
Samra Shahzadi
 
100_Days_of_Data_Science
100_Days_of_Data_Science100_Days_of_Data_Science
100_Days_of_Data_Science
Sajzat hossain
 
Deep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and HypeDeep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and Hype
Siby Jose Plathottam
 

Similar to Transfer learning with Custom Vision (20)

B4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearningB4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearning
 
[Revised] Intro to CNN
[Revised] Intro to CNN[Revised] Intro to CNN
[Revised] Intro to CNN
 
How can we train with few data
How can we train with few dataHow can we train with few data
How can we train with few data
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
 
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDistributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
 
Fine-tuning Pre-Trained Models for Generative AI Applications
Fine-tuning Pre-Trained Models for Generative AI ApplicationsFine-tuning Pre-Trained Models for Generative AI Applications
Fine-tuning Pre-Trained Models for Generative AI Applications
 
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical ResearchII-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
 
Designing a neural network architecture for image recognition
Designing a neural network architecture for image recognitionDesigning a neural network architecture for image recognition
Designing a neural network architecture for image recognition
 
Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.
 
Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learning
 
Classification case study + intro to cnn
Classification case study + intro to cnnClassification case study + intro to cnn
Classification case study + intro to cnn
 
Python Machine Learning January 2018 - Ho Chi Minh City
Python Machine Learning January 2018 - Ho Chi Minh CityPython Machine Learning January 2018 - Ho Chi Minh City
Python Machine Learning January 2018 - Ho Chi Minh City
 
GDSC Unsri - From Zero to Hero with TensorFlow.pptx
GDSC Unsri - From Zero to Hero with TensorFlow.pptxGDSC Unsri - From Zero to Hero with TensorFlow.pptx
GDSC Unsri - From Zero to Hero with TensorFlow.pptx
 
Week3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptxWeek3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptx
 
Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...
Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...
Key Insights Of Using Deep Learning To Analyze Healthcare Data | Workshop Fro...
 
Machine learning with TensorFlow
Machine learning with TensorFlow  Machine learning with TensorFlow
Machine learning with TensorFlow
 
Automation, intelligence and knowledge modelling
Automation, intelligence and knowledge modellingAutomation, intelligence and knowledge modelling
Automation, intelligence and knowledge modelling
 
Machine learning || Introduction || Main Components || Examples || Techniques
Machine learning || Introduction || Main Components || Examples || TechniquesMachine learning || Introduction || Main Components || Examples || Techniques
Machine learning || Introduction || Main Components || Examples || Techniques
 
100_Days_of_Data_Science
100_Days_of_Data_Science100_Days_of_Data_Science
100_Days_of_Data_Science
 
Deep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and HypeDeep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and Hype
 

More from SC5.io

AWS Machine Learning & Google Cloud Machine Learning
AWS Machine Learning & Google Cloud Machine LearningAWS Machine Learning & Google Cloud Machine Learning
AWS Machine Learning & Google Cloud Machine Learning
SC5.io
 
Practical AI for Business: Bandit Algorithms
Practical AI for Business: Bandit AlgorithmsPractical AI for Business: Bandit Algorithms
Practical AI for Business: Bandit Algorithms
SC5.io
 
Decision trees & random forests
Decision trees & random forestsDecision trees & random forests
Decision trees & random forests
SC5.io
 
Bandit Algorithms
Bandit AlgorithmsBandit Algorithms
Bandit Algorithms
SC5.io
 
Machine Learning Using Cloud Services
Machine Learning Using Cloud ServicesMachine Learning Using Cloud Services
Machine Learning Using Cloud Services
SC5.io
 
Angular.js Primer in Aalto University
Angular.js Primer in Aalto UniversityAngular.js Primer in Aalto University
Angular.js Primer in Aalto University
SC5.io
 
Miten design-muutosjohtaminen hyödyttää yrityksiä?
Miten design-muutosjohtaminen hyödyttää yrityksiä?Miten design-muutosjohtaminen hyödyttää yrityksiä?
Miten design-muutosjohtaminen hyödyttää yrityksiä?
SC5.io
 
Securing the client side web
Securing the client side webSecuring the client side web
Securing the client side web
SC5.io
 
Engineering HTML5 Applications for Better Performance
Engineering HTML5 Applications for Better PerformanceEngineering HTML5 Applications for Better Performance
Engineering HTML5 Applications for Better Performance
SC5.io
 
2013 10-02-backbone-robots-aarhus
2013 10-02-backbone-robots-aarhus2013 10-02-backbone-robots-aarhus
2013 10-02-backbone-robots-aarhus
SC5.io
 
2013 10-02-html5-performance-aarhus
2013 10-02-html5-performance-aarhus2013 10-02-html5-performance-aarhus
2013 10-02-html5-performance-aarhus
SC5.io
 
2013 04-02-server-side-backbone
2013 04-02-server-side-backbone2013 04-02-server-side-backbone
2013 04-02-server-side-backbone
SC5.io
 
Building single page applications
Building single page applicationsBuilding single page applications
Building single page applications
SC5.io
 

More from SC5.io (13)

AWS Machine Learning & Google Cloud Machine Learning
AWS Machine Learning & Google Cloud Machine LearningAWS Machine Learning & Google Cloud Machine Learning
AWS Machine Learning & Google Cloud Machine Learning
 
Practical AI for Business: Bandit Algorithms
Practical AI for Business: Bandit AlgorithmsPractical AI for Business: Bandit Algorithms
Practical AI for Business: Bandit Algorithms
 
Decision trees & random forests
Decision trees & random forestsDecision trees & random forests
Decision trees & random forests
 
Bandit Algorithms
Bandit AlgorithmsBandit Algorithms
Bandit Algorithms
 
Machine Learning Using Cloud Services
Machine Learning Using Cloud ServicesMachine Learning Using Cloud Services
Machine Learning Using Cloud Services
 
Angular.js Primer in Aalto University
Angular.js Primer in Aalto UniversityAngular.js Primer in Aalto University
Angular.js Primer in Aalto University
 
Miten design-muutosjohtaminen hyödyttää yrityksiä?
Miten design-muutosjohtaminen hyödyttää yrityksiä?Miten design-muutosjohtaminen hyödyttää yrityksiä?
Miten design-muutosjohtaminen hyödyttää yrityksiä?
 
Securing the client side web
Securing the client side webSecuring the client side web
Securing the client side web
 
Engineering HTML5 Applications for Better Performance
Engineering HTML5 Applications for Better PerformanceEngineering HTML5 Applications for Better Performance
Engineering HTML5 Applications for Better Performance
 
2013 10-02-backbone-robots-aarhus
2013 10-02-backbone-robots-aarhus2013 10-02-backbone-robots-aarhus
2013 10-02-backbone-robots-aarhus
 
2013 10-02-html5-performance-aarhus
2013 10-02-html5-performance-aarhus2013 10-02-html5-performance-aarhus
2013 10-02-html5-performance-aarhus
 
2013 04-02-server-side-backbone
2013 04-02-server-side-backbone2013 04-02-server-side-backbone
2013 04-02-server-side-backbone
 
Building single page applications
Building single page applicationsBuilding single page applications
Building single page applications
 

Recently uploaded

一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
74nqk8xf
 
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data LakeViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
Walaa Eldin Moustafa
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
apvysm8
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
kuntobimo2016
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
g4dpvqap0
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
rwarrenll
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Kiwi Creative
 
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
v7oacc3l
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
jitskeb
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
bopyb
 
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdfUdemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Fernanda Palhano
 
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
Timothy Spann
 
Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
vikram sood
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
74nqk8xf
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
Social Samosa
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
Sachin Paul
 
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
zsjl4mimo
 
End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024
Lars Albertsson
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
Social Samosa
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
sameer shah
 

Recently uploaded (20)

一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
 
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data LakeViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data Lake
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
 
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
 
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdfUdemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
 
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
 
Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
 
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
 
End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
 

Transfer learning with Custom Vision

  • 1. TRANSFER LEARNING Max Pagels, Data Science Specialist @maxpagels, linkedin.com/in/maxpagels/
  • 2. MACHINE LEARNING NEEDS DATA TO WORK The more, the better. But what if you don’t have a lot of data to work with, and no time to collect more? Is ML still an option?
  • 3. IN SOME CASES, YES. For general regression and classification problems such as face detection and image recognition, there are lots (but still not enough) of freely available datasets online that you can use to train your own models.
  • 4. MNIST 70,000 28x28px labelled images of handwritten digits 0-9
  • 5. FASHION MNIST 70,000 28x28px labelled images of clothing items (ten classes)
  • 6. VGG FACE DATASET Portrait images of 2,622 identities
  • 7. CIFAR-10 60,000 32x32px colour images belonging to one of ten classes (airplane, automobile, cat, deer etc.)
  • 8. CIFAR-100 60,000 32x32px colour images belonging to one of a hundred different classes
  • 9. GTD Data from more than 170,000 terrorist attacks worldwide, 1970-2016
  • 10. FOOD 101 101,000 images of 101 types of food items
  • 11. YOUTUBE-8M Over 7 million YouTube videos across 4716 classes
  • 12. LOTS MORE ON KAGGLE https://www.kaggle.com/datasets
  • 13. INSTEAD OF TRAINING MODELS YOURSELF, YOU CAN ALSO USE PRE-TRAINED ONES If you use a well known dataset such as MNIST or CIFAR-10, chances are someone’s already trained a neural network, random forest, or some other learning algorithm on it with high accuracy.
  • 14. BUT WHAT IF WE HAVE A SPECIFIC PROBLEM FOR WHICH NO PRE-TRAINED MODEL EXISTS? Can we somehow leverage the information learned by some pre-trained model and adapt it to our specific use case?
  • 15. EXAMPLE Say we want to build a food classifier that reliably determine if an image contains one of two Finnish dishes: fried baltic herring or fried perch? A model pre-trained on Food 101 has learned a lot about what a fish looks like, but the dataset doesn’t include images of fried baltic herring or fried perch. Could we use the wisdom the model has learned about fish in order to make building our custom model easier?
  • 16. YES, AND IT’S CALLED TRANSFER LEARNING The basic idea is to take a pre-trained model that has already learning useful representations and tailor it to a custom use case.
  • 17. TRANSFER LEARNING, IN A NUTSHELL Say you have a pre-trained neural network that you would like to adapt to your use case. To do transfer learning: 1. Chop off the neurons in the last layer of the model 2. Replace neurons with new ones, one neuron per class you want to predict (or just one neuron in total if doing regression) 3. Finish training using a dataset of labelled images specific to your problem Why would you want to do this?
  • 18. ONE MAJOR REASON You need less labelled data. A lot less. Usually, 50-100 labelled examples is more than enough.
  • 19. HOW DOES ONE IMPLEMENT TRANSFER LEARNING? You can do transfer learning quite easily in code using Keras, MXNet, TensorFlow, CNTK etc: download pre-trained model, freeze weights, remove last layer, add new layer. There are, however, ready-made, zero-coding-required cloud services that can do it for you.
  • 21. THANK YOU! Special thanks to Ari Bornstein from Microsoft for the inspiration! QUESTIONS?