SlideShare a Scribd company logo
1 of 25
© 2019 MUST India
Computer Vision
- By Aditya Bhattacharya
- Data and Cloud Platform Engineer,
West Pharmaceuticals
MUST Research
© 2019 MUST India
About Me
My Associations
My Interests
© 2019 MUST India
Why MUST is a must?
Community Support
Synergy
Platform to showcase your work
Cool projects to work
© 2019 MUST India
• Introduce you to new topics and concepts
• Discuss about practical use cases
• Develop new intuitions
• Improve existing intuitions
• Pro-tips!
Goals of this discussion!
© 2019 MUST India
• Convolutional Neural Networks ( CNN or ConvNets )
• Popular ConvNet Architectures
• Data Augmentation
• Transfer Learning
• Object Detection
• Neural Style Transfer
• Generative Adversarial Networks (GANs)
• Variational Auto Encoders (VAEs)
Topics to be discussed
© 2019 MUST India
- Image Classification
- Object Detection
- Neural Style Transfer
- Image Generation
Typical Computer Vision Problems
Image Generation
Neural Style Transfer
© 2019 MUST India
Why CNN? Why not classical ML approach?
- Classical ML approach requires a lot of research on the dataset for feature engineering
- Requires cleaner dataset for higher accuracy
- Accuracy of the algorithms were not good enough with classical ML approach
- CNNs are far more accurate and reliable and easier to implement
Convolutional Neural Networks (CNN or ConvNets)
© 2019 MUST India
Convolutional Neural Networks (CNN or ConvNets)
How does a convolution work?
original
(n x n) * (f x f) = (n-f+1) x (n – f +1)
Padding and Strided convolution ?
(n x n) * (f x f) = ((n + 2p –f) /s ) +
1) x ((n + 2p –f) /s ) + 1)
Valid Convolution
Same Convolution
© 2019 MUST India
Convolutional Neural Networks (CNN or ConvNets)
Edge Detection
© 2019 MUST India
Convolutional Neural Networks (CNN or ConvNets)
Pooling
Deep Convolution Neural Network
© 2019 MUST India
Popular ConvNet Architectures
ResNet
LeNet
VGG
AlexNet
Inception Net
© 2019 MUST India
Types of operation
• Mirroring
• Random Crop
• Rotation
• Shearing
• Warpig
• Colour Shifting
Data Augmentation
Why Data Augmentation?
• With a smaller dataset over-fitting is a huge
problem.
• Data augmentation helps you to expand your
dataset from available data in an unbiased
way.
© 2019 MUST India
What is transfer learning?
• A deep learning approach to use a pretrained network or
model and fine tune it and re-train with custom labels to
obtain solution for a similar problem.
• Example : Working with ImageNet
Transfer Learning
Why transfer learning?
• CV requires a large dataset, which might not be available
all the time.
• Much faster and reliable approach than training a CNN
from scratch.
© 2019 MUST India
Transfer Learning
• Working on Pre-Trained networks
• Load a pretrained network
• Replace the final layer including the output layer
• Fine tune the weights depending on new task and new data
• Train the network on the data for new task
• Test the accuracy of the new network and tune the model if required.
© 2019 MUST India
Object Detection
Typical challenges with Object Detection:
 Classification with Localization, detect and then
localize
 Bounding box
 Landmark detection
 What typical output your algorithm should look for?
 Whether your image has the particular object (Pc)
 Bounding box coordinates (bx,by)
 Bounding box height and weight (bh,bw)
 Number of classes ( C1, C2, C3 …)
© 2019 MUST India
• Yolo – You Only Look Once
• YOLO divides the input image into an S×S grid. Each grid cell predicts only one object
• For each grid cell, it predicts B boundary boxes and each box has one box confidence
score,
• It detects one object only regardless of the number of boxes B,
• It predicts C conditional class probabilities (one per class for the likeliness of the
object class).
Object Detection with YOLO algorithm
Intersection over union (IoU)
Non-max suppression
© 2019 MUST India
YOLO
YOLO uses sum-squared error between the
predictions and the ground truth to calculate
loss. The loss function composes of:
•the classification loss.
•the localization loss (errors between the
predicted boundary box and the ground truth).
•the confidence loss
© 2019 MUST India
Neural Style Transfer
− Learn features from different layers of
ConvNet
− The key notion behind implementing style
transfer :
 define a loss function to specify what
we want to achieve,
 minimize this loss.
− main loss functions primarily compute the
distance in terms of these different
representations.
Content image + Style Image = Generated image
What we want to achieve?
• Conserve the contents of the original image
• Adopt the style of the reference image.
© 2019 MUST India
How do we define a neural network to perform style
transfer?
 The original 2015 paper by Gatys et al. proposed a neural style
transfer algorithm that does not require a new architecture at
all.
 We can take a pre-trained network (typically on ImageNet) and
define a loss function that will enable us to achieve our end goal
of style transfer and then optimize over that loss function.
What loss function do we use?
• Content loss
• Style loss
• Total-variation loss
Neural Style Transfer
© 2019 MUST India
© 2019 MUST India
Generative Adversarial Networks (GANs)
A GAN is made up of two parts:
- Generator network - Takes as input a random vector (a random
point in the latent space), and decodes it into a synthetic image
- Discriminator network (or adversary) - Takes as input an image
(real or synthetic), and predicts whether the image came from the
training set or was created by the generator network.
© 2019 MUST India
Textbook definition of a VAE - “provides probabilistic descriptions of observations in latent spaces.”
Variational Auto Encoders (VAEs)
• Each input image has features that can
normally be described as single,
discrete values.
• Variational autoencoders describe
these values as probability
distributions.
• Decoders can then sample randomly
from the probability distributions for
input vectors
© 2019 MUST India
Variational Auto Encoders (VAEs)
© 2019 MUST India
Pro-tips!
- Community participation
- Kaggle competitions
- Stop procrastinating! Start working on
projects
- Read research papers
- AI for all!
© 2019 MUST India
Thanks
- By Aditya Bhattacharya
- Data and Cloud Platform Engineer
West Pharmaceuticals
MUST Research
- Questions?
- Want to connect over LinkedIn ?
- Or email me at:
- aditya.bhattacharya2016@gmail.com

More Related Content

What's hot

Machine Learning system architecture – Microsoft Translator, a Case Study : ...
Machine Learning system architecture – Microsoft Translator, a Case Study :  ...Machine Learning system architecture – Microsoft Translator, a Case Study :  ...
Machine Learning system architecture – Microsoft Translator, a Case Study : ...Vishal Chowdhary
 
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...Mark Tabladillo
 
[Research] azure ml anatomy of a machine learning service - Sharat Chikkerur
[Research] azure ml  anatomy of a machine learning service - Sharat Chikkerur[Research] azure ml  anatomy of a machine learning service - Sharat Chikkerur
[Research] azure ml anatomy of a machine learning service - Sharat ChikkerurPAPIs.io
 
Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101QuantUniversity
 
Azure Machine Learning 101
Azure Machine Learning 101Azure Machine Learning 101
Azure Machine Learning 101Andrew Badera
 
Introduction to Azure Machine Learning
Introduction to Azure Machine LearningIntroduction to Azure Machine Learning
Introduction to Azure Machine LearningPaul Prae
 
Ferruzza g automl deck
Ferruzza g   automl deckFerruzza g   automl deck
Ferruzza g automl deckEric Dill
 
Azure Machine Learning 101
Azure Machine Learning 101Azure Machine Learning 101
Azure Machine Learning 101Renato Jovic
 
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson StudioIBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson StudioSvetlana Levitan, PhD
 
Managers guide to effective building of machine learning products
Managers guide to effective building of machine learning productsManagers guide to effective building of machine learning products
Managers guide to effective building of machine learning productsGianmario Spacagna
 
Scaling up Deep Learning by Scaling Down
Scaling up Deep Learning by Scaling DownScaling up Deep Learning by Scaling Down
Scaling up Deep Learning by Scaling DownDatabricks
 
Automatic Model Documentation with H2O
Automatic Model Documentation with H2OAutomatic Model Documentation with H2O
Automatic Model Documentation with H2OSri Ambati
 
Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San Francisco
Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San FranciscoPatrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San Francisco
Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San FranciscoSri Ambati
 
Automated Machine Learning
Automated Machine LearningAutomated Machine Learning
Automated Machine Learningsafa cimenli
 
TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform Seldon
 
Agile Machine Learning for Real-time Recommender Systems
Agile Machine Learning for Real-time Recommender SystemsAgile Machine Learning for Real-time Recommender Systems
Agile Machine Learning for Real-time Recommender SystemsJohann Schleier-Smith
 
AI with Azure Machine Learning
AI with Azure Machine LearningAI with Azure Machine Learning
AI with Azure Machine LearningGeert Baeke
 
The Rise of Vector Data
The Rise of Vector DataThe Rise of Vector Data
The Rise of Vector DataDatabricks
 
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineRsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineSanjana Chowdhury
 

What's hot (20)

Machine Learning system architecture – Microsoft Translator, a Case Study : ...
Machine Learning system architecture – Microsoft Translator, a Case Study :  ...Machine Learning system architecture – Microsoft Translator, a Case Study :  ...
Machine Learning system architecture – Microsoft Translator, a Case Study : ...
 
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
 
[Research] azure ml anatomy of a machine learning service - Sharat Chikkerur
[Research] azure ml  anatomy of a machine learning service - Sharat Chikkerur[Research] azure ml  anatomy of a machine learning service - Sharat Chikkerur
[Research] azure ml anatomy of a machine learning service - Sharat Chikkerur
 
Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101Automatic machine learning (AutoML) 101
Automatic machine learning (AutoML) 101
 
Ai use cases
Ai use casesAi use cases
Ai use cases
 
Azure Machine Learning 101
Azure Machine Learning 101Azure Machine Learning 101
Azure Machine Learning 101
 
Introduction to Azure Machine Learning
Introduction to Azure Machine LearningIntroduction to Azure Machine Learning
Introduction to Azure Machine Learning
 
Ferruzza g automl deck
Ferruzza g   automl deckFerruzza g   automl deck
Ferruzza g automl deck
 
Azure Machine Learning 101
Azure Machine Learning 101Azure Machine Learning 101
Azure Machine Learning 101
 
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson StudioIBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
 
Managers guide to effective building of machine learning products
Managers guide to effective building of machine learning productsManagers guide to effective building of machine learning products
Managers guide to effective building of machine learning products
 
Scaling up Deep Learning by Scaling Down
Scaling up Deep Learning by Scaling DownScaling up Deep Learning by Scaling Down
Scaling up Deep Learning by Scaling Down
 
Automatic Model Documentation with H2O
Automatic Model Documentation with H2OAutomatic Model Documentation with H2O
Automatic Model Documentation with H2O
 
Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San Francisco
Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San FranciscoPatrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San Francisco
Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San Francisco
 
Automated Machine Learning
Automated Machine LearningAutomated Machine Learning
Automated Machine Learning
 
TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform
 
Agile Machine Learning for Real-time Recommender Systems
Agile Machine Learning for Real-time Recommender SystemsAgile Machine Learning for Real-time Recommender Systems
Agile Machine Learning for Real-time Recommender Systems
 
AI with Azure Machine Learning
AI with Azure Machine LearningAI with Azure Machine Learning
AI with Azure Machine Learning
 
The Rise of Vector Data
The Rise of Vector DataThe Rise of Vector Data
The Rise of Vector Data
 
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineRsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
 

Similar to Computer vision-must-nit-silchar-ml-hackathon-2019

Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonAditya Bhattacharya
 
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...Edge AI and Vision Alliance
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningAli Alkan
 
Edge AI Framework for Healthcare Applications
Edge AI Framework for Healthcare ApplicationsEdge AI Framework for Healthcare Applications
Edge AI Framework for Healthcare ApplicationsDebmalya Biswas
 
CAR DAMAGE DETECTION USING DEEP LEARNING
CAR DAMAGE DETECTION USING DEEP LEARNINGCAR DAMAGE DETECTION USING DEEP LEARNING
CAR DAMAGE DETECTION USING DEEP LEARNINGIRJET Journal
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...Edge AI and Vision Alliance
 
Photo Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted FeaturesPhoto Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted FeaturesIRJET Journal
 
IRJET- Semantic Segmentation using Deep Learning
IRJET- Semantic Segmentation using Deep LearningIRJET- Semantic Segmentation using Deep Learning
IRJET- Semantic Segmentation using Deep LearningIRJET Journal
 
Emerging trends in Artificial intelligence - A deeper review
Emerging trends in Artificial intelligence - A deeper reviewEmerging trends in Artificial intelligence - A deeper review
Emerging trends in Artificial intelligence - A deeper reviewGopi Krishna Nuti
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learningpratik pratyay
 
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...IRJET Journal
 
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character RecognitionIRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character RecognitionIRJET Journal
 
“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...
“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...
“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...Edge AI and Vision Alliance
 
[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient Simulation[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient SimulationDongwonSon1
 
AISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the EdgeAISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the EdgeBill Liu
 
“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...
“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...
“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...Edge AI and Vision Alliance
 
IRJET - Gender and Age Prediction using Wideresnet Architecture
IRJET - Gender and Age Prediction using Wideresnet ArchitectureIRJET - Gender and Age Prediction using Wideresnet Architecture
IRJET - Gender and Age Prediction using Wideresnet ArchitectureIRJET Journal
 
AICamp - Dr Ramine Tinati - Making Computer Vision Real
AICamp - Dr Ramine Tinati - Making Computer Vision RealAICamp - Dr Ramine Tinati - Making Computer Vision Real
AICamp - Dr Ramine Tinati - Making Computer Vision RealRamine Tinati
 

Similar to Computer vision-must-nit-silchar-ml-hackathon-2019 (20)

Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
 
Edge AI Framework for Healthcare Applications
Edge AI Framework for Healthcare ApplicationsEdge AI Framework for Healthcare Applications
Edge AI Framework for Healthcare Applications
 
CAR DAMAGE DETECTION USING DEEP LEARNING
CAR DAMAGE DETECTION USING DEEP LEARNINGCAR DAMAGE DETECTION USING DEEP LEARNING
CAR DAMAGE DETECTION USING DEEP LEARNING
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
 
Photo Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted FeaturesPhoto Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted Features
 
IRJET- Semantic Segmentation using Deep Learning
IRJET- Semantic Segmentation using Deep LearningIRJET- Semantic Segmentation using Deep Learning
IRJET- Semantic Segmentation using Deep Learning
 
slide-171212080528.pptx
slide-171212080528.pptxslide-171212080528.pptx
slide-171212080528.pptx
 
Emerging trends in Artificial intelligence - A deeper review
Emerging trends in Artificial intelligence - A deeper reviewEmerging trends in Artificial intelligence - A deeper review
Emerging trends in Artificial intelligence - A deeper review
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learning
 
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
 
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character RecognitionIRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
 
“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...
“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...
“DNN Training Data: How to Know What You Need and How to Get It,” a Presentat...
 
[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient Simulation[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient Simulation
 
CBIR by deep learning
CBIR by deep learningCBIR by deep learning
CBIR by deep learning
 
AISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the EdgeAISF19 - Unleash Computer Vision at the Edge
AISF19 - Unleash Computer Vision at the Edge
 
“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...
“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...
“Accelerating Newer ML Models Using the Qualcomm AI Stack,” a Presentation fr...
 
IRJET - Gender and Age Prediction using Wideresnet Architecture
IRJET - Gender and Age Prediction using Wideresnet ArchitectureIRJET - Gender and Age Prediction using Wideresnet Architecture
IRJET - Gender and Age Prediction using Wideresnet Architecture
 
AICamp - Dr Ramine Tinati - Making Computer Vision Real
AICamp - Dr Ramine Tinati - Making Computer Vision RealAICamp - Dr Ramine Tinati - Making Computer Vision Real
AICamp - Dr Ramine Tinati - Making Computer Vision Real
 

More from Aditya Bhattacharya

Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023Aditya Bhattacharya
 
Explainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretableExplainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretableAditya Bhattacharya
 
Time series Segmentation & Anomaly Detection
Time series Segmentation & Anomaly DetectionTime series Segmentation & Anomaly Detection
Time series Segmentation & Anomaly DetectionAditya Bhattacharya
 
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...Aditya Bhattacharya
 
Aditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
Aditya Bhattacharya Chest XRay Image Analysis Using Deep LearningAditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
Aditya Bhattacharya Chest XRay Image Analysis Using Deep LearningAditya Bhattacharya
 

More from Aditya Bhattacharya (6)

Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
 
ODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AIODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AI
 
Explainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretableExplainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretable
 
Time series Segmentation & Anomaly Detection
Time series Segmentation & Anomaly DetectionTime series Segmentation & Anomaly Detection
Time series Segmentation & Anomaly Detection
 
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
 
Aditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
Aditya Bhattacharya Chest XRay Image Analysis Using Deep LearningAditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
Aditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
 

Recently uploaded

Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Call Girls in Nagpur High Profile
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxupamatechverse
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...roncy bisnoi
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlysanyuktamishra911
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdfankushspencer015
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )Tsuyoshi Horigome
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduitsrknatarajan
 
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)Suman Mia
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130Suhani Kapoor
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escortsranjana rawat
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordAsst.prof M.Gokilavani
 

Recently uploaded (20)

Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
 
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and RoutesRoadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
 

Computer vision-must-nit-silchar-ml-hackathon-2019

  • 1. © 2019 MUST India Computer Vision - By Aditya Bhattacharya - Data and Cloud Platform Engineer, West Pharmaceuticals MUST Research
  • 2. © 2019 MUST India About Me My Associations My Interests
  • 3. © 2019 MUST India Why MUST is a must? Community Support Synergy Platform to showcase your work Cool projects to work
  • 4. © 2019 MUST India • Introduce you to new topics and concepts • Discuss about practical use cases • Develop new intuitions • Improve existing intuitions • Pro-tips! Goals of this discussion!
  • 5. © 2019 MUST India • Convolutional Neural Networks ( CNN or ConvNets ) • Popular ConvNet Architectures • Data Augmentation • Transfer Learning • Object Detection • Neural Style Transfer • Generative Adversarial Networks (GANs) • Variational Auto Encoders (VAEs) Topics to be discussed
  • 6. © 2019 MUST India - Image Classification - Object Detection - Neural Style Transfer - Image Generation Typical Computer Vision Problems Image Generation Neural Style Transfer
  • 7. © 2019 MUST India Why CNN? Why not classical ML approach? - Classical ML approach requires a lot of research on the dataset for feature engineering - Requires cleaner dataset for higher accuracy - Accuracy of the algorithms were not good enough with classical ML approach - CNNs are far more accurate and reliable and easier to implement Convolutional Neural Networks (CNN or ConvNets)
  • 8. © 2019 MUST India Convolutional Neural Networks (CNN or ConvNets) How does a convolution work? original (n x n) * (f x f) = (n-f+1) x (n – f +1) Padding and Strided convolution ? (n x n) * (f x f) = ((n + 2p –f) /s ) + 1) x ((n + 2p –f) /s ) + 1) Valid Convolution Same Convolution
  • 9. © 2019 MUST India Convolutional Neural Networks (CNN or ConvNets) Edge Detection
  • 10. © 2019 MUST India Convolutional Neural Networks (CNN or ConvNets) Pooling Deep Convolution Neural Network
  • 11. © 2019 MUST India Popular ConvNet Architectures ResNet LeNet VGG AlexNet Inception Net
  • 12. © 2019 MUST India Types of operation • Mirroring • Random Crop • Rotation • Shearing • Warpig • Colour Shifting Data Augmentation Why Data Augmentation? • With a smaller dataset over-fitting is a huge problem. • Data augmentation helps you to expand your dataset from available data in an unbiased way.
  • 13. © 2019 MUST India What is transfer learning? • A deep learning approach to use a pretrained network or model and fine tune it and re-train with custom labels to obtain solution for a similar problem. • Example : Working with ImageNet Transfer Learning Why transfer learning? • CV requires a large dataset, which might not be available all the time. • Much faster and reliable approach than training a CNN from scratch.
  • 14. © 2019 MUST India Transfer Learning • Working on Pre-Trained networks • Load a pretrained network • Replace the final layer including the output layer • Fine tune the weights depending on new task and new data • Train the network on the data for new task • Test the accuracy of the new network and tune the model if required.
  • 15. © 2019 MUST India Object Detection Typical challenges with Object Detection:  Classification with Localization, detect and then localize  Bounding box  Landmark detection  What typical output your algorithm should look for?  Whether your image has the particular object (Pc)  Bounding box coordinates (bx,by)  Bounding box height and weight (bh,bw)  Number of classes ( C1, C2, C3 …)
  • 16. © 2019 MUST India • Yolo – You Only Look Once • YOLO divides the input image into an S×S grid. Each grid cell predicts only one object • For each grid cell, it predicts B boundary boxes and each box has one box confidence score, • It detects one object only regardless of the number of boxes B, • It predicts C conditional class probabilities (one per class for the likeliness of the object class). Object Detection with YOLO algorithm Intersection over union (IoU) Non-max suppression
  • 17. © 2019 MUST India YOLO YOLO uses sum-squared error between the predictions and the ground truth to calculate loss. The loss function composes of: •the classification loss. •the localization loss (errors between the predicted boundary box and the ground truth). •the confidence loss
  • 18. © 2019 MUST India Neural Style Transfer − Learn features from different layers of ConvNet − The key notion behind implementing style transfer :  define a loss function to specify what we want to achieve,  minimize this loss. − main loss functions primarily compute the distance in terms of these different representations. Content image + Style Image = Generated image What we want to achieve? • Conserve the contents of the original image • Adopt the style of the reference image.
  • 19. © 2019 MUST India How do we define a neural network to perform style transfer?  The original 2015 paper by Gatys et al. proposed a neural style transfer algorithm that does not require a new architecture at all.  We can take a pre-trained network (typically on ImageNet) and define a loss function that will enable us to achieve our end goal of style transfer and then optimize over that loss function. What loss function do we use? • Content loss • Style loss • Total-variation loss Neural Style Transfer
  • 20. © 2019 MUST India
  • 21. © 2019 MUST India Generative Adversarial Networks (GANs) A GAN is made up of two parts: - Generator network - Takes as input a random vector (a random point in the latent space), and decodes it into a synthetic image - Discriminator network (or adversary) - Takes as input an image (real or synthetic), and predicts whether the image came from the training set or was created by the generator network.
  • 22. © 2019 MUST India Textbook definition of a VAE - “provides probabilistic descriptions of observations in latent spaces.” Variational Auto Encoders (VAEs) • Each input image has features that can normally be described as single, discrete values. • Variational autoencoders describe these values as probability distributions. • Decoders can then sample randomly from the probability distributions for input vectors
  • 23. © 2019 MUST India Variational Auto Encoders (VAEs)
  • 24. © 2019 MUST India Pro-tips! - Community participation - Kaggle competitions - Stop procrastinating! Start working on projects - Read research papers - AI for all!
  • 25. © 2019 MUST India Thanks - By Aditya Bhattacharya - Data and Cloud Platform Engineer West Pharmaceuticals MUST Research - Questions? - Want to connect over LinkedIn ? - Or email me at: - aditya.bhattacharya2016@gmail.com

Editor's Notes

  1. Notes: Images have been taken from: https://raw.githubusercontent.com/torch/torch.github.io/master/blog/_posts/images/out.gif https://i.stack.imgur.com/mFBCV.png https://cdn-images-1.medium.com/max/1600/0*JTxhYFzNFZ0xlWlB.png
  2. Reference image has been taken from: https://medium.freecodecamp.org/an-intuitive-guide-to-convolutional-neural-networks-260c2de0a050
  3. Reference image has been taken from: https://medium.freecodecamp.org/an-intuitive-guide-to-convolutional-neural-networks-260c2de0a050
  4. Reference image has been taken from: https://medium.freecodecamp.org/an-intuitive-guide-to-convolutional-neural-networks-260c2de0a050 https://www.owlnet.rice.edu/~elec539/Projects97/morphjrks/moredge.html
  5. Reference image has been taken from: https://medium.freecodecamp.org/an-intuitive-guide-to-convolutional-neural-networks-260c2de0a050 https://i.stack.imgur.com/QZsRB.png
  6. https://cdn-images-1.medium.com/max/1200/1*C8hNiOqur4OJyEZmC7OnzQ.png https://www.kdnuggets.com/2018/05/data-augmentation-deep-learning-limited-data.html
  7. https://www.mathworks.com/discovery/transfer-learning.html
  8. https://www.mathworks.com/discovery/transfer-learning.html
  9. https://medium.com/@jonathan_hui/real-time-object-detection-with-yolo-yolov2-28b1b93e2088 https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/single-shot-detectors/yolo.html
  10. https://www.matthewwilson.co/tomtom https://www.pyimagesearch.com/2018/08/27/neural-style-transfer-with-opencv/
  11. https://www.pyimagesearch.com/2018/08/27/neural-style-transfer-with-opencv/
  12. https://www.spindox.it/en/blog/generative-adversarial-neural-networks/ Deep Learning with Python by Chollet
  13. https://towardsdatascience.com/what-the-heck-are-vae-gans-17b86023588a
  14. https://towardsdatascience.com/what-the-heck-are-vae-gans-17b86023588a