Image classification using CNN

Image Classification
Using CNN and Tensorflow
Team members
➔ Noura Hussein Fekry
@noura_7ussein
➔ Mohamed Mahmoud Shehata
@Shehata
Project Description
Building a model to classify images into their appropriate
categories using the CIFAR-10 dataset.
Using CNN (python 3.6 and tensorflow)
● TensorFlow is an open-source software library for
dataflow programming across a range of tasks. It is a
symbolic math library, and is also used for machine
learning applications such as neural networks.
The CIFAR-10 Dataset
The CIFAR-10 dataset contains 60
thousand images of various objects like:
Airplanes, Cars, Birds, trucks, deers, dogs,
frogs, horses, cats and ships.
The Images are (32*32*3)
It contains 50 thousand images as a training
data and 10 thousand testing data.
Phases
Preprocess Data
Phase
CNN Phase
Getting the data
Preprocessing
functions
Building the network
Training the network
Model Testing
Preprocess functions
● Normalization
Transforming image X into a NumPy array.
● One Hot Encoded
Labeling the images into 0 or 1, by indexing the classes,
giving 1 to the class and 0 to the rest of the classes.
● Randomize the data
Making sure that the data is as random as possible, to insure maximum randomization
So, why did we use a CNN?
In machine learning, a convolutional neural network is a
class of deep, feed-forward artificial neural networks that
has successfully been applied to analyzing visual imagery.
CNNs use a variation of multilayer perceptrons designed to
require minimal preprocessing. They are also known as shift
invariant or space invariant artificial neural networks
(SIANN), based on their shared-weights architecture and
translation invariance characteristics.
CNN Building Blocks
● Convolutional Layer
● Pooling Layer
● ReLU Layer
● Fully Connected Layer
● Loss Layer
CNN’s design consists of Convolutional, pooling, fully
connected and weights.
Building the network
➔ Input
➔ Convolution and Max Pooling layer
➔ Flatten Layer
➔ Fully Connected Layer
➔ Output Layer
Training the neural
net
● Single Optimization
● Hyperparameters
● Training on a single CIFAR-10 Batch
● Fully Trained Model
Testing Model
● Accuracy: 71.44%
● Softmax Predictions
Test Samples
Resources:
● https://en.wikipedia.org/wiki/Convolu
tional_neural_network
● https://www.youtube.com/watch?v=F
Tr3n7uBIuE
Thank you.
1 de 14

Recomendados

Image classification using convolutional neural network por
Image classification using convolutional neural networkImage classification using convolutional neural network
Image classification using convolutional neural networkKIRAN R
5.6K visualizações54 slides
Convolutional Neural Network and Its Applications por
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsKasun Chinthaka Piyarathna
4.6K visualizações23 slides
Convolution Neural Network (CNN) por
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Suraj Aavula
13.5K visualizações22 slides
Convolutional neural network por
Convolutional neural networkConvolutional neural network
Convolutional neural networkMojammilHusain
1.1K visualizações11 slides
Convolutional Neural Networks (CNN) por
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Gaurav Mittal
58.5K visualizações70 slides
Image classification with Deep Neural Networks por
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
7.5K visualizações29 slides

Mais conteúdo relacionado

Mais procurados

Convolutional Neural Network Models - Deep Learning por
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningBenha University
12.6K visualizações83 slides
Deep Learning - Convolutional Neural Networks por
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksChristian Perone
71.4K visualizações86 slides
CNN and its applications by ketaki por
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketakiKetaki Patwari
1.7K visualizações50 slides
Convolutional Neural Networks por
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural NetworksAshray Bhandare
16.1K visualizações80 slides
Image Classification using deep learning por
Image Classification using deep learning Image Classification using deep learning
Image Classification using deep learning Asma-AH
559 visualizações36 slides
Convolutional Neural Network (CNN) por
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Muhammad Haroon
824 visualizações16 slides

Mais procurados(20)

Convolutional Neural Network Models - Deep Learning por Benha University
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
Benha University12.6K visualizações
Deep Learning - Convolutional Neural Networks por Christian Perone
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
Christian Perone71.4K visualizações
CNN and its applications by ketaki por Ketaki Patwari
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketaki
Ketaki Patwari1.7K visualizações
Convolutional Neural Networks por Ashray Bhandare
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
Ashray Bhandare16.1K visualizações
Image Classification using deep learning por Asma-AH
Image Classification using deep learning Image Classification using deep learning
Image Classification using deep learning
Asma-AH559 visualizações
Convolutional Neural Network (CNN) por Muhammad Haroon
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
Muhammad Haroon824 visualizações
Convolutional Neural Network por Vignesh Suresh
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
Vignesh Suresh261 visualizações
CNN Tutorial por Sungjoon Choi
CNN TutorialCNN Tutorial
CNN Tutorial
Sungjoon Choi5.6K visualizações
Convolution Neural Network (CNN) por Basit Rafiq
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
Basit Rafiq581 visualizações
Deep Learning - CNN and RNN por Ashray Bhandare
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNN
Ashray Bhandare5.9K visualizações
Image classification using cnn por Debarko De
Image classification using cnnImage classification using cnn
Image classification using cnn
Debarko De1.1K visualizações
CNNs: from the Basics to Recent Advances por Dmytro Mishkin
CNNs: from the Basics to Recent AdvancesCNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent Advances
Dmytro Mishkin3.9K visualizações
cnn ppt.pptx por rohithprabhas1
cnn ppt.pptxcnn ppt.pptx
cnn ppt.pptx
rohithprabhas1289 visualizações
Convolutional neural network por Yan Xu
Convolutional neural network Convolutional neural network
Convolutional neural network
Yan Xu5.3K visualizações
Deep Learning in Computer Vision por Sungjoon Choi
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer Vision
Sungjoon Choi10.4K visualizações
CONVOLUTIONAL NEURAL NETWORK por Md Rajib Bhuiyan
CONVOLUTIONAL NEURAL NETWORKCONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORK
Md Rajib Bhuiyan710 visualizações
Deep learning ppt por BalneSridevi
Deep learning pptDeep learning ppt
Deep learning ppt
BalneSridevi1.2K visualizações
CIFAR-10 por satyam_madala
CIFAR-10CIFAR-10
CIFAR-10
satyam_madala2K visualizações
Introduction to Deep learning por leopauly
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
leopauly1.7K visualizações

Similar a Image classification using CNN

Distributed Deep Learning on AWS with Apache MXNet por
Distributed Deep Learning on AWS with Apache MXNetDistributed Deep Learning on AWS with Apache MXNet
Distributed Deep Learning on AWS with Apache MXNetAmazon Web Services
827 visualizações41 slides
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report por
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSitakanta Mishra
172 visualizações6 slides
Introduction To Tensorflow por
Introduction To TensorflowIntroduction To Tensorflow
Introduction To TensorflowRayyan Khalid
79 visualizações19 slides
Neural Networks and Deep Learning: An Intro por
Neural Networks and Deep Learning: An IntroNeural Networks and Deep Learning: An Intro
Neural Networks and Deep Learning: An IntroFariz Darari
944 visualizações64 slides
Startup.Ml: Using neon for NLP and Localization Applications por
Startup.Ml: Using neon for NLP and Localization Applications Startup.Ml: Using neon for NLP and Localization Applications
Startup.Ml: Using neon for NLP and Localization Applications Intel Nervana
1.5K visualizações69 slides
Deep Dive on Deep Learning (June 2018) por
Deep Dive on Deep Learning (June 2018)Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Julien SIMON
56.4K visualizações52 slides

Similar a Image classification using CNN(20)

Distributed Deep Learning on AWS with Apache MXNet por Amazon Web Services
Distributed Deep Learning on AWS with Apache MXNetDistributed Deep Learning on AWS with Apache MXNet
Distributed Deep Learning on AWS with Apache MXNet
Amazon Web Services827 visualizações
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report por Sitakanta Mishra
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Sitakanta Mishra172 visualizações
Introduction To Tensorflow por Rayyan Khalid
Introduction To TensorflowIntroduction To Tensorflow
Introduction To Tensorflow
Rayyan Khalid79 visualizações
Neural Networks and Deep Learning: An Intro por Fariz Darari
Neural Networks and Deep Learning: An IntroNeural Networks and Deep Learning: An Intro
Neural Networks and Deep Learning: An Intro
Fariz Darari944 visualizações
Startup.Ml: Using neon for NLP and Localization Applications por Intel Nervana
Startup.Ml: Using neon for NLP and Localization Applications Startup.Ml: Using neon for NLP and Localization Applications
Startup.Ml: Using neon for NLP and Localization Applications
Intel Nervana1.5K visualizações
Deep Dive on Deep Learning (June 2018) por Julien SIMON
Deep Dive on Deep Learning (June 2018)Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)
Julien SIMON56.4K visualizações
Introducing Deep learning with Matlab por Massimo Talia
Introducing Deep learning with MatlabIntroducing Deep learning with Matlab
Introducing Deep learning with Matlab
Massimo Talia1.2K visualizações
Synthetic dialogue generation with Deep Learning por S N
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep Learning
S N778 visualizações
Neural Networks with Google TensorFlow por Darshan Patel
Neural Networks with Google TensorFlowNeural Networks with Google TensorFlow
Neural Networks with Google TensorFlow
Darshan Patel55K visualizações
Looking into the Black Box - A Theoretical Insight into Deep Learning Networks por Dinesh V
Looking into the Black Box - A Theoretical Insight into Deep Learning NetworksLooking into the Black Box - A Theoretical Insight into Deep Learning Networks
Looking into the Black Box - A Theoretical Insight into Deep Learning Networks
Dinesh V287 visualizações
Rethinking computation: A processor architecture for machine intelligence por Intel Nervana
Rethinking computation: A processor architecture for machine intelligenceRethinking computation: A processor architecture for machine intelligence
Rethinking computation: A processor architecture for machine intelligence
Intel Nervana1.5K visualizações
Training course lect1 por Noor Dhiya
Training course lect1Training course lect1
Training course lect1
Noor Dhiya15 visualizações
CNN.pptx.pdf por Knoldus Inc.
CNN.pptx.pdfCNN.pptx.pdf
CNN.pptx.pdf
Knoldus Inc.34 visualizações
A Neural Network that Understands Handwriting por Shivam Sawhney
A Neural Network that Understands HandwritingA Neural Network that Understands Handwriting
A Neural Network that Understands Handwriting
Shivam Sawhney49 visualizações
Introduction to Deep Learning and neon at Galvanize por Intel Nervana
Introduction to Deep Learning and neon at GalvanizeIntroduction to Deep Learning and neon at Galvanize
Introduction to Deep Learning and neon at Galvanize
Intel Nervana1.4K visualizações
Automatic Attendace using convolutional neural network Face Recognition por vatsal199567
Automatic Attendace using convolutional neural network Face RecognitionAutomatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face Recognition
vatsal199567532 visualizações
B.tech_project_ppt.pptx por supratikmondal6
B.tech_project_ppt.pptxB.tech_project_ppt.pptx
B.tech_project_ppt.pptx
supratikmondal69 visualizações
IRJET-Breast Cancer Detection using Convolution Neural Network por IRJET Journal
IRJET-Breast Cancer Detection using Convolution Neural NetworkIRJET-Breast Cancer Detection using Convolution Neural Network
IRJET-Breast Cancer Detection using Convolution Neural Network
IRJET Journal83 visualizações
Deep learning with Keras por QuantUniversity
Deep learning with KerasDeep learning with Keras
Deep learning with Keras
QuantUniversity6.6K visualizações

Último

Cross-network in Google Analytics 4.pdf por
Cross-network in Google Analytics 4.pdfCross-network in Google Analytics 4.pdf
Cross-network in Google Analytics 4.pdfGA4 Tutorials
6 visualizações7 slides
[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented Generation por
[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented Generation[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented Generation
[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented GenerationDataScienceConferenc1
5 visualizações29 slides
ColonyOS por
ColonyOSColonyOS
ColonyOSJohanKristiansson6
9 visualizações17 slides
PROGRAMME.pdf por
PROGRAMME.pdfPROGRAMME.pdf
PROGRAMME.pdfHiNedHaJar
17 visualizações13 slides
UNEP FI CRS Climate Risk Results.pptx por
UNEP FI CRS Climate Risk Results.pptxUNEP FI CRS Climate Risk Results.pptx
UNEP FI CRS Climate Risk Results.pptxpekka28
11 visualizações51 slides
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docx por
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docxRIO GRANDE SUPPLY COMPANY INC, JAYSON.docx
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docxJaysonGarabilesEspej
6 visualizações3 slides

Último(20)

Cross-network in Google Analytics 4.pdf por GA4 Tutorials
Cross-network in Google Analytics 4.pdfCross-network in Google Analytics 4.pdf
Cross-network in Google Analytics 4.pdf
GA4 Tutorials6 visualizações
[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented Generation por DataScienceConferenc1
[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented Generation[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented Generation
[DSC Europe 23] Spela Poklukar & Tea Brasanac - Retrieval Augmented Generation
DataScienceConferenc15 visualizações
PROGRAMME.pdf por HiNedHaJar
PROGRAMME.pdfPROGRAMME.pdf
PROGRAMME.pdf
HiNedHaJar17 visualizações
UNEP FI CRS Climate Risk Results.pptx por pekka28
UNEP FI CRS Climate Risk Results.pptxUNEP FI CRS Climate Risk Results.pptx
UNEP FI CRS Climate Risk Results.pptx
pekka2811 visualizações
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docx por JaysonGarabilesEspej
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docxRIO GRANDE SUPPLY COMPANY INC, JAYSON.docx
RIO GRANDE SUPPLY COMPANY INC, JAYSON.docx
JaysonGarabilesEspej6 visualizações
CRIJ4385_Death Penalty_F23.pptx por yvettemm100
CRIJ4385_Death Penalty_F23.pptxCRIJ4385_Death Penalty_F23.pptx
CRIJ4385_Death Penalty_F23.pptx
yvettemm1006 visualizações
Supercharging your Data with Azure AI Search and Azure OpenAI por Peter Gallagher
Supercharging your Data with Azure AI Search and Azure OpenAISupercharging your Data with Azure AI Search and Azure OpenAI
Supercharging your Data with Azure AI Search and Azure OpenAI
Peter Gallagher37 visualizações
Building Real-Time Travel Alerts por Timothy Spann
Building Real-Time Travel AlertsBuilding Real-Time Travel Alerts
Building Real-Time Travel Alerts
Timothy Spann109 visualizações
Introduction to Microsoft Fabric.pdf por ishaniuudeshika
Introduction to Microsoft Fabric.pdfIntroduction to Microsoft Fabric.pdf
Introduction to Microsoft Fabric.pdf
ishaniuudeshika24 visualizações
[DSC Europe 23] Zsolt Feleki - Machine Translation should we trust it.pptx por DataScienceConferenc1
[DSC Europe 23] Zsolt Feleki - Machine Translation should we trust it.pptx[DSC Europe 23] Zsolt Feleki - Machine Translation should we trust it.pptx
[DSC Europe 23] Zsolt Feleki - Machine Translation should we trust it.pptx
DataScienceConferenc15 visualizações
Vikas 500 BIG DATA TECHNOLOGIES LAB.pdf por vikas12611618
Vikas 500 BIG DATA TECHNOLOGIES LAB.pdfVikas 500 BIG DATA TECHNOLOGIES LAB.pdf
Vikas 500 BIG DATA TECHNOLOGIES LAB.pdf
vikas126116188 visualizações
Understanding Hallucinations in LLMs - 2023 09 29.pptx por Greg Makowski
Understanding Hallucinations in LLMs - 2023 09 29.pptxUnderstanding Hallucinations in LLMs - 2023 09 29.pptx
Understanding Hallucinations in LLMs - 2023 09 29.pptx
Greg Makowski13 visualizações
Short Story Assignment by Kelly Nguyen por kellynguyen01
Short Story Assignment by Kelly NguyenShort Story Assignment by Kelly Nguyen
Short Story Assignment by Kelly Nguyen
kellynguyen0118 visualizações
How Leaders See Data? (Level 1) por Narendra Narendra
How Leaders See Data? (Level 1)How Leaders See Data? (Level 1)
How Leaders See Data? (Level 1)
Narendra Narendra13 visualizações
3196 The Case of The East River por ErickANDRADE90
3196 The Case of The East River3196 The Case of The East River
3196 The Case of The East River
ErickANDRADE9011 visualizações
Data structure and algorithm. por Abdul salam
Data structure and algorithm. Data structure and algorithm.
Data structure and algorithm.
Abdul salam 18 visualizações
RuleBookForTheFairDataEconomy.pptx por noraelstela1
RuleBookForTheFairDataEconomy.pptxRuleBookForTheFairDataEconomy.pptx
RuleBookForTheFairDataEconomy.pptx
noraelstela167 visualizações
Chapter 3b- Process Communication (1) (1)(1) (1).pptx por ayeshabaig2004
Chapter 3b- Process Communication (1) (1)(1) (1).pptxChapter 3b- Process Communication (1) (1)(1) (1).pptx
Chapter 3b- Process Communication (1) (1)(1) (1).pptx
ayeshabaig20045 visualizações

Image classification using CNN

  • 2. Team members ➔ Noura Hussein Fekry @noura_7ussein ➔ Mohamed Mahmoud Shehata @Shehata
  • 3. Project Description Building a model to classify images into their appropriate categories using the CIFAR-10 dataset. Using CNN (python 3.6 and tensorflow) ● TensorFlow is an open-source software library for dataflow programming across a range of tasks. It is a symbolic math library, and is also used for machine learning applications such as neural networks.
  • 4. The CIFAR-10 Dataset The CIFAR-10 dataset contains 60 thousand images of various objects like: Airplanes, Cars, Birds, trucks, deers, dogs, frogs, horses, cats and ships. The Images are (32*32*3) It contains 50 thousand images as a training data and 10 thousand testing data.
  • 5. Phases Preprocess Data Phase CNN Phase Getting the data Preprocessing functions Building the network Training the network Model Testing
  • 6. Preprocess functions ● Normalization Transforming image X into a NumPy array. ● One Hot Encoded Labeling the images into 0 or 1, by indexing the classes, giving 1 to the class and 0 to the rest of the classes. ● Randomize the data Making sure that the data is as random as possible, to insure maximum randomization
  • 7. So, why did we use a CNN? In machine learning, a convolutional neural network is a class of deep, feed-forward artificial neural networks that has successfully been applied to analyzing visual imagery. CNNs use a variation of multilayer perceptrons designed to require minimal preprocessing. They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics.
  • 8. CNN Building Blocks ● Convolutional Layer ● Pooling Layer ● ReLU Layer ● Fully Connected Layer ● Loss Layer
  • 9. CNN’s design consists of Convolutional, pooling, fully connected and weights.
  • 10. Building the network ➔ Input ➔ Convolution and Max Pooling layer ➔ Flatten Layer ➔ Fully Connected Layer ➔ Output Layer
  • 11. Training the neural net ● Single Optimization ● Hyperparameters ● Training on a single CIFAR-10 Batch ● Fully Trained Model Testing Model ● Accuracy: 71.44% ● Softmax Predictions

Notas do Editor

  1. Source: https://en.wikipedia.org/wiki/Convolutional_neural_network