Simplilearn, profile picture
Uploaded bySimplilearn
17,315 views

Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | Simplilearn

A Convolutional Neural Network (CNN) is a type of neural network that can process grid-like data like images. It works by applying filters to the input image to extract features at different levels of abstraction. The CNN takes the pixel values of an input image as the input layer. Hidden layers like the convolution layer, ReLU layer and pooling layer are applied to extract features from the image. The fully connected layer at the end identifies the object in the image based on the extracted features. CNNs use the convolution operation with small filter matrices that are convolved across the width and height of the input volume to compute feature maps.

Education◦
Related topics:
Deep Learning•

Embed presentation

Convolution Neural Network Tutorial
How image recognition works? Do you know how Deep Learning recognizes the objects in an image? It does it using a Convolution Neural Network Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer
How image recognition works? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer Input layer accepts the pixels of the image as input in the form of arrays 1 2 1 9 2 1 7 40 2 30 11 35 70 11 1 4 3307552613 60 45 50 10 89 23
How image recognition works? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer Hidden layers carry out feature extraction by performing certain calculation and manipulation 1 2 1 9 2 1 7 40 2 30 11 35 70 11 1 4 3307552613 60 45 50 10 89 23
How image recognition works? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer There are multiple hidden layers like Convolution layer, ReLU layer, Pooling layer, etc that perform feature extraction from the image Convolution Layer This layer uses a matrix filter and performs convolution operation to detect patterns in the image 1 0 1 10 0 1 0 1 Matrix Filter
How image recognition works? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer There are multiple hidden layers like Convolution layer, ReLU layer, Pooling layer, etc that perform feature extraction from the image ReLU ReLU activation function is applied to the convolution layer to get a rectified feature map of the image
How image recognition works? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer There are multiple hidden layers like Convolution layer, ReLU layer, Pooling layer, etc that perform feature extraction from the image Pooling Pooling layer also uses multiple filters to detect edges, corners, eyes, feathers, beak, etc
How image recognition works? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer 1 2 1 9 2 1 7 40 2 30 11 35 70 11 1 4 3307552613 60 45 50 10 89 23 Finally there is a fully connected layer that identifies the object in the image Output Layer
What’s in it for you? How CNN recognizes images? What is Convolution neural network? Use case implementation using CNN Introduction to CNN Layers in convolution neural network
Introduction to CNN Yann LeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
Introduction to CNN Yann LeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
Introduction to CNN Yann LeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
Introduction to CNN Yann LeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
What is a Convolution Neural Network? CNN is a feed forward neural network that is generally used to analyze visual images by processing data with grid like topology. A CNN is also known as a “ConvNet” Orchid Rose Flowers of 2 varieties (Orchid/Rose) Identifies the flowers Hidden Layers Input Layer Output Layer
What is a Convolution Neural Network? CNN is a feed forward neural network that is generally used to analyze visual images by processing data with grid like topology. A CNN is also known as a “ConvNet” Convolution operation forms the basis of any Convolution Neural Network In CNN, every image is represented in the form of arrays of pixel values Real Image of the digit 8 Represented in the form of an array 0 0 1 1 0 0 0 0 0 01 1 1 1 1 10 0 0 0 0 1 0 1 0 0 0 0 0 0 Digit 8 represented in the form of pixels of 0’s and 1’s
What is a Convolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution
What is a Convolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] [5, 6, 6] a b* = [17, ] Multiply the arrays element wise 17 b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution
What is a Convolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] a b* = [17, 22 ] Multiply the arrays element wise 17 b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution [5, 6, 6] [3, 4, 15] 22
What is a Convolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] a b* = [17, 22, 39,…….. ] Multiply the arrays element wise 17 b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution [5, 6, 6] [3, 4, 15] 22 [2, 10, 27] 39 ……… ………
How CNN recognizes images? image for the symbol image for the symbol / Consider the following 2 images: When you press , the above image is processed
How CNN recognizes images? image for the symbol image for the symbol / Consider the following 2 images: When you press /, the above image is processed
How CNN recognizes images? Image represented in the form of a matrix of numbers 000000 11 0000000 1 1 1 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 000000 0 0 1 0 Real Image Represented in the form of black and white pixels
Layers in Convolution Neural Network Pooling Layer ReLU LayerConvolution Layer CNN Fully Connected Layer 1 2 34
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 2 3 4 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 1 0 1 1 0 0 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 0 1 1 1 0 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 0 0 1 1 0 1 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 0 1 1 0 0 1 0 0 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 1 0 1 1 0 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 0 1 1 1 1 1 0 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 2 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 0 0 1 0 0 1 0 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 2 3 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 0 1 1 0 1 1 1 1 0 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
Convolution Layer A Convolution Layer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 1 1 1 0 1 0 0 4 3 4 2 4 3 2 3 4 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
ReLU Layer Once the feature maps are extracted, the next step is to move them to a ReLU layer 1050-5-10 0 2 4 6 8 10 R(z) = max(0, z) ReLU Performs element wise operation Sets all negative pixels to 0 Introduces non-linearity to the network The output is a rectified feature map
ReLU Layer Real image is scanned in multiple convolution and ReLU layers for locating features
ReLU Layer Real image is scanned in multiple convolution and ReLU layers for locating features
Note for the instructor While explaining, please mention there are multiple Convolution, ReLU and Pooling layers connected one after another that carry out feature extraction in every layer. The input image is scanned multiple times to generate the input feature map.
Pooling Layer The rectified feature map now goes through a pooling layer. Pooling is a down-sampling operation that reduces the dimensionality of the feature map. 1 2 4 6 2 7 58 3 04 1 2 3 1 7 6 8 4 7 max pooling with 2x2 filters and stride 2 Max(3, 4, 1, 2) = 4 Pooled feature map Rectified feature map
Pooling Layer Identifies the edges, corners and other features of the bird Pooling layer uses different filters to identify different parts of the image like edges, corners, body, feathers, eyes, beak, etc.
Pooling Layer Structure of the Convolution Neural Network so far 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Convolution Pooling Input Image Convolution Layer Pooling Layer ReLU
Flattening 6 8 4 7 Pooled feature map 6 8 4 7 Flattening Flattening is the process of converting all the resultant 2 dimensional arrays from pooled feature map into a single long continuous linear vector.
Flattening Pooling Layer Input Layer Flattening is the process of converting all the resultant 2 dimensional arrays from pooled feature map into a single long continuous linear vector. Flattening
Flattening 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Convolution Pooling Input Image Convolution Layer Pooling Layer Flattening Input to the to final layer Structure of the network so far ReLU
Fully Connected Layer ………… Flattened Matrix The Flattened matrix from the pooling layer is fed as input to the Fully Connected Layer to classify the image
Fully Connected Layer ………… Flattened Matrix Dog Bird Cat The Flattened matrix from the pooling layer is fed as input to the Fully Connected Layer to classify the image Pixels from the flattened matrix fed as input
Fully Connected Layer Dog Bird Cat Identifies the image The Flattened matrix from the pooling layer is fed as input to the Fully Connected Layer to classify the image Pixels from the flattened matrix fed as input
Fully Connected Layer 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Convolution Pooling Input Image Convolution Layer Pooling Layer Flattening ReLU Fully Connected Layer
Fully Connected Layer Lets see the entire process how CNN recognizes a bird Dog Bird Cat Feature Extraction in multiple hidden layers Classification in the output layer Convolution + ReLU + Max Pooling Fully Connected Layer
Use case implementation using CNN We will be using CIFAR-10 data set (from Canadian Institute For Advanced Research) for classifying images across 10 categories 01 03 05 07 09 02 04 06 08 10 airplane automobile bird cat deer dog frog horse ship truck
Use case implementation using CNN 1. Download data set 2. Import the CIFAR data set
Use case implementation using CNN 3. Reading the label names
Use case implementation using CNN 4. Display images using matplotlib
Use case implementation using CNN 4. Display images using matplotlib
Use case implementation using CNN 4. Display images using matplotlib
Use case implementation using CNN 5. Helper function to handle data
Use case implementation using CNN 5. Helper function to handle data
Use case implementation using CNN 6. To use the previous code, run the following 7. Creating the model
Use case implementation using CNN 8. Applying the helper functions
Use case implementation using CNN 8. Create the layers 9. Create the flattened layer by reshaping the pooling layer 10. Create the fully connected layer
Use case implementation using CNN 12. Apply the Loss function 11. Set output to y_pred 13. Create the optimizer 14. Create a variable to initialize all the global tf variables
Use case implementation using CNN 15. Run the model by creating a Graph Session
Key Takeaways
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | Simplilearn

More Related Content

PDF
Convolutional Neural Network Models - Deep Learning
byMohamed Loey
 
PPTX
cnn ppt.pptx
byrohithprabhas1
 
PPTX
Introduction to CNN
byShuai Zhang
 
PPTX
Image classification using cnn
bySumeraHangi
 
PPTX
Convolutional Neural Network (CNN)
byMuhammad Haroon
 
PPTX
Convolution Neural Network (CNN)
byBasit Rafiq
 
PPTX
Convolutional neural network
byMojammilHusain
 
PDF
Convolutional Neural Networks (CNN)
byGaurav Mittal
 
Convolutional Neural Network Models - Deep Learning
byMohamed Loey
 
cnn ppt.pptx
byrohithprabhas1
 
Introduction to CNN
byShuai Zhang
 
Image classification using cnn
bySumeraHangi
 
Convolutional Neural Network (CNN)
byMuhammad Haroon
 
Convolution Neural Network (CNN)
byBasit Rafiq
 
Convolutional neural network
byMojammilHusain
 
Convolutional Neural Networks (CNN)
byGaurav Mittal
 

What's hot

PPTX
Convolutional Neural Network and Its Applications
byKasun Chinthaka Piyarathna
 
PPTX
Convolution Neural Network (CNN)
bySuraj Aavula
 
PPTX
Cnn
byNirthika Rajendran
 
PPTX
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
bySimplilearn
 
PPTX
Convolutional Neural Networks
byAshray Bhandare
 
PDF
Convolutional neural network
byYan Xu
 
PPTX
CNN and its applications by ketaki
byKetaki Patwari
 
PPTX
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...
bySimplilearn
 
PPTX
Convolutional neural network
byFerdous ahmed
 
PDF
Deep Learning - Convolutional Neural Networks
byChristian Perone
 
PPTX
AlexNet
byBertil Hatt
 
PDF
Introduction to Recurrent Neural Network
byKnoldus Inc.
 
PDF
Deep learning
byKuppusamy P
 
PPTX
Machine Learning - Convolutional Neural Network
byRichard Kuo
 
PPTX
Convolutional Neural Network (CNN) - image recognition
byYUNG-KUEI CHEN
 
PPTX
Deep Learning - CNN and RNN
byAshray Bhandare
 
PDF
An introduction to Deep Learning
byJulien SIMON
 
PPTX
Image classification with Deep Neural Networks
byYogendra Tamang
 
PDF
Introduction to Recurrent Neural Network
byYan Xu
 
PPTX
CONVOLUTIONAL NEURAL NETWORK
byMd Rajib Bhuiyan
 
Convolutional Neural Network and Its Applications
byKasun Chinthaka Piyarathna
 
Convolution Neural Network (CNN)
bySuraj Aavula
 
Cnn
byNirthika Rajendran
 
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
bySimplilearn
 
Convolutional Neural Networks
byAshray Bhandare
 
Convolutional neural network
byYan Xu
 
CNN and its applications by ketaki
byKetaki Patwari
 
Artificial Neural Network | Deep Neural Network Explained | Artificial Neural...
bySimplilearn
 
Convolutional neural network
byFerdous ahmed
 
Deep Learning - Convolutional Neural Networks
byChristian Perone
 
AlexNet
byBertil Hatt
 
Introduction to Recurrent Neural Network
byKnoldus Inc.
 
Deep learning
byKuppusamy P
 
Machine Learning - Convolutional Neural Network
byRichard Kuo
 
Convolutional Neural Network (CNN) - image recognition
byYUNG-KUEI CHEN
 
Deep Learning - CNN and RNN
byAshray Bhandare
 
An introduction to Deep Learning
byJulien SIMON
 
Image classification with Deep Neural Networks
byYogendra Tamang
 
Introduction to Recurrent Neural Network
byYan Xu
 
CONVOLUTIONAL NEURAL NETWORK
byMd Rajib Bhuiyan
 

Similar to Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | Simplilearn

PPTX
Convolutional Neural Network (CNN)of Deep Learning
byalihassaah1994
 
PPTX
build a Convolutional Neural Network (CNN) using TensorFlow in Python
byKv Sagar
 
PDF
Overview of Convolutional Neural Networks
byananth
 
PPTX
Mnist report ppt
byRaghunandanJairam
 
PPTX
Introduction to Convolutional Neural Networks
byParrotAI
 
PDF
Mnist report
byRaghunandanJairam
 
PPTX
Introduction-to-CNN (1).pptx
byDEVPARIKH8
 
PPT
digital image processing - convolutional networks
byMuhammad824617
 
PPTX
Introduction to convolutional networks .pptx
byArunNegi37
 
PDF
Convolutional_neural_network mechanism.pptx.pdf
bySwathiSoman5
 
PPTX
convolutional Neural Network in Deep learning
bydrrajeshkannablr
 
PPTX
Deep Computer Vision - 1.pptx
byJawadHaider36
 
PDF
lecture16.pdf000000000000000000000000000
bythed3942
 
PPTX
Convolution Neural Network_Artificial Intelligence_Good.pptx
byAnnavarapuRajavarapr
 
PPTX
machine learning that uses artificial neural networks with multiple hidden la...
byjeevamahalakshmi
 
PPTX
Introduction to Convolutional Neural Networks (CNNs).pptx
byCHRISEVANS269099
 
PPTX
Illustrative Introductory CNN
byYasutoTamura1
 
PPTX
Convolutional Neural Network - Computer Vision.pptx
bykmpslab
 
PPTX
CNN_Presentation to learn the basics of CNN Model.pptx
bybani30122004
 
PDF
Convolutional neural network complete guide
byMLTUT
 
Convolutional Neural Network (CNN)of Deep Learning
byalihassaah1994
 
build a Convolutional Neural Network (CNN) using TensorFlow in Python
byKv Sagar
 
Overview of Convolutional Neural Networks
byananth
 
Mnist report ppt
byRaghunandanJairam
 
Introduction to Convolutional Neural Networks
byParrotAI
 
Mnist report
byRaghunandanJairam
 
Introduction-to-CNN (1).pptx
byDEVPARIKH8
 
digital image processing - convolutional networks
byMuhammad824617
 
Introduction to convolutional networks .pptx
byArunNegi37
 
Convolutional_neural_network mechanism.pptx.pdf
bySwathiSoman5
 
convolutional Neural Network in Deep learning
bydrrajeshkannablr
 
Deep Computer Vision - 1.pptx
byJawadHaider36
 
lecture16.pdf000000000000000000000000000
bythed3942
 
Convolution Neural Network_Artificial Intelligence_Good.pptx
byAnnavarapuRajavarapr
 
machine learning that uses artificial neural networks with multiple hidden la...
byjeevamahalakshmi
 
Introduction to Convolutional Neural Networks (CNNs).pptx
byCHRISEVANS269099
 
Illustrative Introductory CNN
byYasutoTamura1
 
Convolutional Neural Network - Computer Vision.pptx
bykmpslab
 
CNN_Presentation to learn the basics of CNN Model.pptx
bybani30122004
 
Convolutional neural network complete guide
byMLTUT
 

More from Simplilearn

PPTX
SQL INterview Questions .pTop 45 SQL Interview Questions And Answers In 2025 ...
bySimplilearn
 
PPTX
Bagging Vs Boosting In Machine Learning | Ensemble Learning In Machine Learni...
bySimplilearn
 
PPTX
Gen AI Engineer Roadmap For 2025 | How To Become Gen AI Engineer In 2025 | Si...
bySimplilearn
 
PPTX
Kotter's 8-Step Change Model Explained | Kotter's Change Management Model | S...
bySimplilearn
 
PPTX
How To Become An AI And ML Engineer In 2025 | AI Engineer Roadmap | AI ML Car...
bySimplilearn
 
PPTX
Future Of Social Media | Social Media Trends and Strategies 2025 | Instagram ...
bySimplilearn
 
PPTX
AI Engineer Roadmap 2025 | AI Engineer Roadmap For Beginners | AI Engineer Ca...
bySimplilearn
 
PPTX
Cyber Security Roadmap 2025 | How To Become Cyber Security Engineer In 2025 |...
bySimplilearn
 
PPTX
SQL Query Optimization | SQL Query Optimization Techniques | SQL Basics | SQL...
bySimplilearn
 
PPTX
Top 10 Data Analyst Certification For 2025 | Best Data Analyst Certification ...
bySimplilearn
 
PPTX
Top 10 Data Analyst Certification For 2025 | Best Data Analyst Certification ...
bySimplilearn
 
PPTX
Top 10 Data Analyst Projects For 2025 | Data Analyst Projects | Data Analysis...
bySimplilearn
 
PPTX
What Is GitHub Copilot? | How To Use GitHub Copilot? | How does GitHub Copilo...
bySimplilearn
 
PPTX
Top 7 High Paying AI Certifications Courses For 2025 | Best AI Certifications...
bySimplilearn
 
PPTX
Machine Learning Roadmap 2025 | Machine Learning Engineer Roadmap For Beginne...
bySimplilearn
 
PPTX
Data Cleaning In Data Mining | Step by Step Data Cleaning Process | Data Clea...
bySimplilearn
 
PPTX
Top 50 Scrum Master Interview Questions | Scrum Master Interview Questions & ...
bySimplilearn
 
PPTX
Complete Data Science Roadmap For 2025 | Data Scientist Roadmap For Beginners...
bySimplilearn
 
PPTX
Complete Data Science Roadmap For 2025 | Data Scientist Roadmap For Beginners...
bySimplilearn
 
PPTX
How To Start Influencer Marketing Business | Influencer Marketing For Beginne...
bySimplilearn
 
SQL INterview Questions .pTop 45 SQL Interview Questions And Answers In 2025 ...
bySimplilearn
 
Bagging Vs Boosting In Machine Learning | Ensemble Learning In Machine Learni...
bySimplilearn
 
Gen AI Engineer Roadmap For 2025 | How To Become Gen AI Engineer In 2025 | Si...
bySimplilearn
 
Kotter's 8-Step Change Model Explained | Kotter's Change Management Model | S...
bySimplilearn
 
How To Become An AI And ML Engineer In 2025 | AI Engineer Roadmap | AI ML Car...
bySimplilearn
 
Future Of Social Media | Social Media Trends and Strategies 2025 | Instagram ...
bySimplilearn
 
AI Engineer Roadmap 2025 | AI Engineer Roadmap For Beginners | AI Engineer Ca...
bySimplilearn
 
Cyber Security Roadmap 2025 | How To Become Cyber Security Engineer In 2025 |...
bySimplilearn
 
SQL Query Optimization | SQL Query Optimization Techniques | SQL Basics | SQL...
bySimplilearn
 
Top 10 Data Analyst Certification For 2025 | Best Data Analyst Certification ...
bySimplilearn
 
Top 10 Data Analyst Certification For 2025 | Best Data Analyst Certification ...
bySimplilearn
 
Top 10 Data Analyst Projects For 2025 | Data Analyst Projects | Data Analysis...
bySimplilearn
 
What Is GitHub Copilot? | How To Use GitHub Copilot? | How does GitHub Copilo...
bySimplilearn
 
Top 7 High Paying AI Certifications Courses For 2025 | Best AI Certifications...
bySimplilearn
 
Machine Learning Roadmap 2025 | Machine Learning Engineer Roadmap For Beginne...
bySimplilearn
 
Data Cleaning In Data Mining | Step by Step Data Cleaning Process | Data Clea...
bySimplilearn
 
Top 50 Scrum Master Interview Questions | Scrum Master Interview Questions & ...
bySimplilearn
 
Complete Data Science Roadmap For 2025 | Data Scientist Roadmap For Beginners...
bySimplilearn
 
Complete Data Science Roadmap For 2025 | Data Scientist Roadmap For Beginners...
bySimplilearn
 
How To Start Influencer Marketing Business | Influencer Marketing For Beginne...
bySimplilearn
 

Recently uploaded

PPTX
unit 1 Introduction and Theoretical Foundations of educational technology.pptx
byKavitha Krishnan
 
PDF
Chapter 1 ICAR Intro_Horticulturte_FoH_.pdf
bybisensharad
 
PDF
the dynasty history of Chahmanas Early Medieval India
byPrachiSontakke5
 
PDF
How to Determine the Sample Population Using Slovins', Calmorin's, and Cochra...
byThelma Villaflores
 
PDF
An alumnus of the Swiss Management Center (SMC) University, Kwame Simpe Ofori...
bynservice241
 
PDF
Political Science and its relations with other allied Social Sciences
byDr Raja Mohammed T
 
PDF
Approaches and Methods in Political Science -EVOLUTION OF POLITICAL THOUGHT -...
byDr Raja Mohammed T
 
PDF
Herniation Syndromes - Neuro Imaging Master Series
bySean M. Fox
 
PDF
Meyers and Hudson Vitale "AI Essentials: From Tools to Strategies: A 2025 NIS...
byNational Information Standards Organization (NISO)
 
PPTX
COPD (Chronic obstructive pulmonary disease) by ebadi.pptx
byEbadullah Khan
 
PDF
Education Research in Ireland: Listening to all voices_Selina McCoy.pdf
byEconomic and Social Research Institute
 
PDF
MEDINIPUR QUIZ PREMIER LEAGUE PRACTICE QUIZ SET
bySaheb Mallik
 
PPTX
Quotation description in Odoo 19 Website
byCeline George
 
PDF
the famous sun temple at konark, balck pagoda, orissa
byPrachiSontakke5
 
PPTX
introduction to clinical pharmacology.pptx
byAneetaSharma15
 
PPTX
Types_of_Volcanoes_Presentation.pptx Science 8 Matatag
byNekoChan623496
 
PPTX
Lupus nephritis updates of managment....
bydrmostafa2110
 
PPTX
Enhanced_Delivery_of_Guidance_Services_in_School.pptx
bylucillepaitone12
 
PPTX
DEVELOPMENTL BIOLOGY hormonal control of metamorphosis.
byKajal Kashyap
 
PDF
the jain temples at mount abu Dilwara temples
byPrachiSontakke5
 
unit 1 Introduction and Theoretical Foundations of educational technology.pptx
byKavitha Krishnan
 
Chapter 1 ICAR Intro_Horticulturte_FoH_.pdf
bybisensharad
 
the dynasty history of Chahmanas Early Medieval India
byPrachiSontakke5
 
How to Determine the Sample Population Using Slovins', Calmorin's, and Cochra...
byThelma Villaflores
 
An alumnus of the Swiss Management Center (SMC) University, Kwame Simpe Ofori...
bynservice241
 
Political Science and its relations with other allied Social Sciences
byDr Raja Mohammed T
 
Approaches and Methods in Political Science -EVOLUTION OF POLITICAL THOUGHT -...
byDr Raja Mohammed T
 
Herniation Syndromes - Neuro Imaging Master Series
bySean M. Fox
 
Meyers and Hudson Vitale "AI Essentials: From Tools to Strategies: A 2025 NIS...
byNational Information Standards Organization (NISO)
 
COPD (Chronic obstructive pulmonary disease) by ebadi.pptx
byEbadullah Khan
 
Education Research in Ireland: Listening to all voices_Selina McCoy.pdf
byEconomic and Social Research Institute
 
MEDINIPUR QUIZ PREMIER LEAGUE PRACTICE QUIZ SET
bySaheb Mallik
 
Quotation description in Odoo 19 Website
byCeline George
 
the famous sun temple at konark, balck pagoda, orissa
byPrachiSontakke5
 
introduction to clinical pharmacology.pptx
byAneetaSharma15
 
Types_of_Volcanoes_Presentation.pptx Science 8 Matatag
byNekoChan623496
 
Lupus nephritis updates of managment....
bydrmostafa2110
 
Enhanced_Delivery_of_Guidance_Services_in_School.pptx
bylucillepaitone12
 
DEVELOPMENTL BIOLOGY hormonal control of metamorphosis.
byKajal Kashyap
 
the jain temples at mount abu Dilwara temples
byPrachiSontakke5
 

Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | Simplilearn

  • 1.
  • 2.
    How image recognitionworks? Do you know how Deep Learning recognizes the objects in an image? It does it using a Convolution Neural Network Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer
  • 3.
    How image recognitionworks? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer Input layer accepts the pixels of the image as input in the form of arrays 1 2 1 9 2 1 7 40 2 30 11 35 70 11 1 4 3307552613 60 45 50 10 89 23
  • 4.
    How image recognitionworks? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer Hidden layers carry out feature extraction by performing certain calculation and manipulation 1 2 1 9 2 1 7 40 2 30 11 35 70 11 1 4 3307552613 60 45 50 10 89 23
  • 5.
    How image recognitionworks? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer There are multiple hidden layers like Convolution layer, ReLU layer, Pooling layer, etc that perform feature extraction from the image Convolution Layer This layer uses a matrix filter and performs convolution operation to detect patterns in the image 1 0 1 10 0 1 0 1 Matrix Filter
  • 6.
    How image recognitionworks? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer There are multiple hidden layers like Convolution layer, ReLU layer, Pooling layer, etc that perform feature extraction from the image ReLU ReLU activation function is applied to the convolution layer to get a rectified feature map of the image
  • 7.
    How image recognitionworks? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer Output Layer There are multiple hidden layers like Convolution layer, ReLU layer, Pooling layer, etc that perform feature extraction from the image Pooling Pooling layer also uses multiple filters to detect edges, corners, eyes, feathers, beak, etc
  • 8.
    How image recognitionworks? Let’s see how CNN identifies the image of a bird Pixels of image fed as input Dog Bird Cat Hidden Layers Input Layer 1 2 1 9 2 1 7 40 2 30 11 35 70 11 1 4 3307552613 60 45 50 10 89 23 Finally there is a fully connected layer that identifies the object in the image Output Layer
  • 9.
    What’s in itfor you? How CNN recognizes images? What is Convolution neural network? Use case implementation using CNN Introduction to CNN Layers in convolution neural network
  • 10.
    Introduction to CNN YannLeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
  • 11.
    Introduction to CNN YannLeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
  • 12.
    Introduction to CNN YannLeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
  • 13.
    Introduction to CNN YannLeCun Pioneer of Convolution Neural Network Director of Facbook’s AI Research Group Built the first Convolution Neural Network called LeNet in 1988 It was used for character recognition tasks like reading zip codes, digits
  • 14.
    What is aConvolution Neural Network? CNN is a feed forward neural network that is generally used to analyze visual images by processing data with grid like topology. A CNN is also known as a “ConvNet” Orchid Rose Flowers of 2 varieties (Orchid/Rose) Identifies the flowers Hidden Layers Input Layer Output Layer
  • 15.
    What is aConvolution Neural Network? CNN is a feed forward neural network that is generally used to analyze visual images by processing data with grid like topology. A CNN is also known as a “ConvNet” Convolution operation forms the basis of any Convolution Neural Network In CNN, every image is represented in the form of arrays of pixel values Real Image of the digit 8 Represented in the form of an array 0 0 1 1 0 0 0 0 0 01 1 1 1 1 10 0 0 0 0 1 0 1 0 0 0 0 0 0 Digit 8 represented in the form of pixels of 0’s and 1’s
  • 16.
    What is aConvolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution
  • 17.
    What is aConvolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] [5, 6, 6] a b* = [17, ] Multiply the arrays element wise 17 b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution
  • 18.
    What is aConvolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] a b* = [17, 22 ] Multiply the arrays element wise 17 b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution [5, 6, 6] [3, 4, 15] 22
  • 19.
    What is aConvolution Neural Network? Let’s understand the convolution operation using 2 matrices a and b of 1 dimension a b* Sum the product b = [1, 2, 3] a = [5, 3, 2, 5, 9, 7] a b* = [17, 22, 39,…….. ] Multiply the arrays element wise 17 b = [1, 2, 3] a = [5, 3, 7, 5, 9, 7] Matrix a and b Convolution [5, 6, 6] [3, 4, 15] 22 [2, 10, 27] 39 ……… ………
  • 20.
    How CNN recognizesimages? image for the symbol image for the symbol / Consider the following 2 images: When you press , the above image is processed
  • 21.
    How CNN recognizesimages? image for the symbol image for the symbol / Consider the following 2 images: When you press /, the above image is processed
  • 22.
    How CNN recognizesimages? Image represented in the form of a matrix of numbers 000000 11 0000000 1 1 1 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 000000 0 0 1 0 Real Image Represented in the form of black and white pixels
  • 23.
    Layers in ConvolutionNeural Network Pooling Layer ReLU LayerConvolution Layer CNN Fully Connected Layer 1 2 34
  • 24.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 2 3 4 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 25.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 1 0 1 1 0 0 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 26.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 0 1 1 1 0 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 27.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 0 0 1 1 0 1 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 28.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 0 1 1 0 0 1 0 0 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 29.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 1 0 1 1 0 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 30.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 0 1 1 1 1 1 0 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 31.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 2 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 0 0 1 0 0 1 0 1 1 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 32.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels 4 3 4 2 4 3 2 3 x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 0 1 1 0 1 1 1 1 0 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 33.
    Convolution Layer A ConvolutionLayer has a number of filters that perform convolution operation Every image is considered as a matrix of pixel values. Consider the following 5 5 image whose pixel values are only 0 and 1* 1 0 1 10 0 1 0 1 Filter 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Image pixels x 1 x0 x 1 x0 x 1 x0 x 1 x0 x 1 1 1 1 1 1 0 1 0 0 4 3 4 2 4 3 2 3 4 Convolved Feature Sliding the filter matrix over the image and computing the dot product to detect patterns
  • 34.
    ReLU Layer Once thefeature maps are extracted, the next step is to move them to a ReLU layer 1050-5-10 0 2 4 6 8 10 R(z) = max(0, z) ReLU Performs element wise operation Sets all negative pixels to 0 Introduces non-linearity to the network The output is a rectified feature map
  • 35.
    ReLU Layer Real imageis scanned in multiple convolution and ReLU layers for locating features
  • 36.
    ReLU Layer Real imageis scanned in multiple convolution and ReLU layers for locating features
  • 37.
    Note for theinstructor While explaining, please mention there are multiple Convolution, ReLU and Pooling layers connected one after another that carry out feature extraction in every layer. The input image is scanned multiple times to generate the input feature map.
  • 38.
    Pooling Layer The rectifiedfeature map now goes through a pooling layer. Pooling is a down-sampling operation that reduces the dimensionality of the feature map. 1 2 4 6 2 7 58 3 04 1 2 3 1 7 6 8 4 7 max pooling with 2x2 filters and stride 2 Max(3, 4, 1, 2) = 4 Pooled feature map Rectified feature map
  • 39.
    Pooling Layer Identifies theedges, corners and other features of the bird Pooling layer uses different filters to identify different parts of the image like edges, corners, body, feathers, eyes, beak, etc.
  • 40.
    Pooling Layer Structure ofthe Convolution Neural Network so far 1 1 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Convolution Pooling Input Image Convolution Layer Pooling Layer ReLU
  • 41.
    Flattening 6 8 4 7 Pooledfeature map 6 8 4 7 Flattening Flattening is the process of converting all the resultant 2 dimensional arrays from pooled feature map into a single long continuous linear vector.
  • 42.
    Flattening Pooling Layer InputLayer Flattening is the process of converting all the resultant 2 dimensional arrays from pooled feature map into a single long continuous linear vector. Flattening
  • 43.
    Flattening 1 1 10 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Convolution Pooling Input Image Convolution Layer Pooling Layer Flattening Input to the to final layer Structure of the network so far ReLU
  • 44.
    Fully Connected Layer …………Flattened Matrix The Flattened matrix from the pooling layer is fed as input to the Fully Connected Layer to classify the image
  • 45.
    Fully Connected Layer …………Flattened Matrix Dog Bird Cat The Flattened matrix from the pooling layer is fed as input to the Fully Connected Layer to classify the image Pixels from the flattened matrix fed as input
  • 46.
    Fully Connected Layer Dog Bird Cat Identifiesthe image The Flattened matrix from the pooling layer is fed as input to the Fully Connected Layer to classify the image Pixels from the flattened matrix fed as input
  • 47.
    Fully Connected Layer 11 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 0 1 0 0 Convolution Pooling Input Image Convolution Layer Pooling Layer Flattening ReLU Fully Connected Layer
  • 48.
    Fully Connected Layer Letssee the entire process how CNN recognizes a bird Dog Bird Cat Feature Extraction in multiple hidden layers Classification in the output layer Convolution + ReLU + Max Pooling Fully Connected Layer
  • 49.
    Use case implementationusing CNN We will be using CIFAR-10 data set (from Canadian Institute For Advanced Research) for classifying images across 10 categories 01 03 05 07 09 02 04 06 08 10 airplane automobile bird cat deer dog frog horse ship truck
  • 50.
    Use case implementationusing CNN 1. Download data set 2. Import the CIFAR data set
  • 51.
    Use case implementationusing CNN 3. Reading the label names
  • 52.
    Use case implementationusing CNN 4. Display images using matplotlib
  • 53.
    Use case implementationusing CNN 4. Display images using matplotlib
  • 54.
    Use case implementationusing CNN 4. Display images using matplotlib
  • 55.
    Use case implementationusing CNN 5. Helper function to handle data
  • 56.
    Use case implementationusing CNN 5. Helper function to handle data
  • 57.
    Use case implementationusing CNN 6. To use the previous code, run the following 7. Creating the model
  • 58.
    Use case implementationusing CNN 8. Applying the helper functions
  • 59.
    Use case implementationusing CNN 8. Create the layers 9. Create the flattened layer by reshaping the pooling layer 10. Create the fully connected layer
  • 60.
    Use case implementationusing CNN 12. Apply the Loss function 11. Set output to y_pred 13. Create the optimizer 14. Create a variable to initialize all the global tf variables
  • 61.
    Use case implementationusing CNN 15. Run the model by creating a Graph Session
  • 62.

Editor's Notes