SlideShare a Scribd company logo
1 of 45
Keras: A Python framework for Deep Learning
CA-691
Mohit Kumar
Roll No. - 20961
M.Sc. (Comp. Applications)
(Course Seminar)
INDIANAGRICULTURALSTATISTICSRESEARCH
INSTITUTE,NEWDELHI
1
Contents
• Introduction
• Keras models
• Keras layers
• Image data augmentation
• Keras applications
• Transfer learning
• Keras datasets
• Keras callbacks
• Case study
• Summary
• References
2
Introduction
• Francois Chollet, the author of Keras, says:
“The framework was developed with a focus on enabling fast experimentation.
Being able to go from idea to result with the least possible delay is key to doing
good research.”
• Keras is open source framework written in Python
• ONEIROS ( Open Ended Neuro-Electronic Intelligent Robot OS)
• Released on 27 March 2015 by Francois Chollet
• Contains neural-network building blocks like layers, optimizer,
activation functions
• Support CNN and RNN
3
Introduction …
• Contains datasets and some pre-trained deep learning applications.
• Model check-pointing, early stopping
• Uses libraries TensorFlow, Theano, CNTK as backend, only one at a time
• Backend does all computations
• Keras call backend functions
• Works for both CPU and GPU
Fig: Keras architecture
4
Keras features
• Rapid prototyping-
1. Build neural network with minimal lines of code
2. Build simple or complex neural networks within a few minutes
• Flexibility-
1. Sometime it is desired to define own metrics, layers, a cost
function, Keras provide freedom for the same.
5
Keras models
• Two types of built in models
1. Sequential
2. Functional
All models have following common properties
1. Inputs that contain a list of input tensors
2. Layers, which comprise the model graph
3. Outputs, a list of output tensors.
6
Sequential Model
• It is linear stack of layers
• Output of previous layer is input
to the next layer.
• Create models by stacking one
layer on top of other
• Useful in situation where task is
not complex
• Provides higher level of
abstraction
Fig: An example of sequential model
7
Functional Model
• It define more complex models
• Such as directed acylic graphs
• Multi input output models
• Model with shared layers
• Possible to connect a layer with
any other layer
Fig: An example of functional model 8
Steps in building a model
9
Model methods
1. Compile: It is used to configure model. It accept following parameters
• Optimizer:
• This specifies type of optimiser to use in back-propagation algorithm
• SGD, Adadelta, Adagrad , Adam , Nadam optimizer and many others.
• Loss:
• It is the objective function
• It track losses or the drift from the function during training the model.
• For regression: mean squared error, mean absolute error etc.
• For classification: Categorical cross-entropy, binary cross entropy
• Different loss functions for different outputs
10
Model methods…
• Metrics:
• It is similar to objective function.
• Results from metric aren’t used when training model.
• It specifies the list of metrics that model evaluate during training and testing.
• The commonly used metric is the accuracy metric.
• Possible to specify different metrics for different output
11
Model methods…
2. Fit
 This is the second important method
 It train the model for specified epochs
 It accept the following important arguments
• x: numpy array of training data
• y: numpy array of target data
• batch_size:
1. It specifies the number of samples per gradient update ,by default 32.
2. 32 samples of training data are fed into the model at a single time.
12
Model methods…
• epochs:
• An epoch is an iteration
• It specifies number of times training data is feed to the model.
• validation_split:
• Fraction of the data that is used as validation.
• Validation data is selected from the end samples
• At the end of each epoch, loss and metrics are calculated for this data.
• validation_data:
• shuffle:
13
Keras layers
• It consist of different types of layers used in deep learning such as:
1. Dense layer:
• A Dense layer is fully connected neural network layer
(Ramchoun et al, 2016)
14
Keras Layers…
2. Convolutional layer:
• Mostly used in computer vision.
• It extract features from the input image.
• It preserves the spatial relationships between pixels
• It learn image features using small squares of input data
• Finally, the obtained matrix is known as the feature map
15
Keras Layers …
Figure: Convolutional in Practice
16
Keras Layers…
3. Pooling layer
• Also called as subsampling or down-sampling layer
• Pooling reduces the dimensionality of feature map
• Retains the most important information
• There are many types of pooling layers such as
• MaxPooling and AveragePooling
• In case of max pooling, take the largest element from the rectified feature
map within that window.
• In average pooling, average of all elements in that window is taken.
17
Keras Layers …
Figure: Max Pooling Concept
18
Keras Layers …
4. Recurrent layer
• Basic building block of RNN
• This is mostly used in sequential and time series modelling.
5. Embedding layers
• Required when input is text
• These are mostly used in Natural Language Processing.
6. Batch Normalisation layer
• Normalize the activations of the previous layer at each batch
• Applies a transformation that maintains the mean activation close to 0 and
the activation standard deviation close to 1.
19
Image Data Augmentation
• Performance of deep learning neural networks often improves with
the amount of data available
• It artificially expand training dataset by creating modified versions of
images
• It create transformed versions of images in the training dataset that
belong to the same class as the original image.
• Transformation include operations from the field of image
manipulation such as shifts, flips, zooms, rotation etc.
20
21
Keras Applications
• Keras applications are deep learning models
• All these are image classifiers
• These applications are available with pre-trained weights
• Weights are downloaded automatically when instantiating application
• Stored at ~/. Keras/models
• These are different variation of pre-trained neural networks
• Each has its architecture, size, speed, accuracy etc.
22
Keras Applications….
Source: https://keras.io/applications/ 23
Keras Applications…
1. VGGNET:
• Introduced by Simonyan and Zisserman in their 2014 paper
• Very deep convolutional networks for large scale image recognition
• 3×3 convolutional layers stacked on top of each other in increasing depth.
• Reducing volume size is handled by max pooling.
• Two fully-connected layers, each with 4,096 nodes are then followed by a
softmax classifier
24
Keras Applications…
(Simonyan and Zisserman, 2014)
25
Continued
2. RESNET
• Introduced by He et. al in their 2015 paper deep residual learning for image
recognition.
• works on the core idea “identity shortcut connection”
• Add the original input to the output of the convolution block
26
Source He et al.(2015)
27
Keras Applications…
3. INCEPTION:
• The “Inception” architecture was first introduced by Szegedy et al.
in their 2014 paper- Going Deeper with convolutions
• It is a convolutional neural network (CNN) which is 27 layers deep
• It has some interesting layers called the inception layers
• The inception layer is a combination of various layers such as :
• 1×1 Convolutions layers
• 3×3 Convolutional layer and 5×5 layer
• Output filter concatenated into single output vector forming the input of
the next image
28
Keras Applications…
Fig: The idea of an inception module
29
Transfer learning
• A model that have been trained for a particular task is reused as a
base or starting point for other model
• Some smart researchers built models on large image datasets like
ImagNet, Open images, and COCO
• They decided to share their models to the public for reuse
• This prevents the need to train an Image Classifier from scratch again
30
Transfer learning …
• To train an Image classifier that will achieve near or above human
level accuracy on image classification, it is required to have
1. Massive amount of data
2. Large computational power
3. Lots of time
• Since this is a big problem for people with little or no resources
• There is no need for transfer learning if we have
• Large dataset that is quite different from the ones above
• Have large computational power
31
Keras Datasets
• Keras contains various datasets that are used to build neural
networks. The datasets are described below
1. Boston House Pricing dataset:
• It contains 13 attributes of houses of Boston suburbs in the late 1970s
• Used in regression problems
2. CIFAR10:
• It is used for classification problems.
• This dataset contains 50,000 32×32 colour images
• Images are labelled over 10 categories
• 10,000 test images.
32
Keras Datasets …
3. CIFAR100: Same as CIFAR10 but it has 100 categories
4. MNIST:
• This dataset contains 60,000 28×28 greyscale images of 10 digits
• Also include 10,000 test images.
5. Fashion-MNIST:
• This dataset is used for classification problems.
• This dataset contains 60,000 28×28 greyscale images of 10 categories, along
with 10,000 test images
6. IMDB movie reviews data:
• Dataset of 25,000 movies reviews from IMDB
• labelled by sentiment (positive/negative).
7. Reuters newswire topics classification:
• Dataset of 11,228 newswires from Reuters, labelled over 46 topics
33
Keras Callbacks
• A callback is a set of functions to be applied at any given stages of the
training procedure
• Used to get an internal view or statistics of the model during training
• A list of callbacks are passed to the fit method of Sequential or Model
class
• There are different types of callbacks performing different operations
1. History:
 1. This call-back is automatically applied to every keras model
 2. History object is returned by the fit method of model.
34
Keras callbacks …
2. ModelCheckPoint:
 This callback save the model after every epoch to a specified path
 The advantage of this callback is that if model training is stopped due to any
reason, then model will automatically saved to the disk.
3. EarlyStopping:
 1. This callback stop training when a monitored quantity stopped improving
 2. Important parameter are
• Quantity to be monitored
• Patience, number of epochs with no improvement after which training will stop.
35
Keras Callbacks …
4. TensorBoard:
 It is a visualization tool
 This callback write a log for TensorBoard which allow to visualize dynamic
graph of training and test metrics
36
Case Study
• Image classifier developed using keras
• Web application is developed using Python’s flask framework
• Dataset contains 8032 images belongs to 8 classes such as
• Banana, Corn, Daisy, Fig, Jackfruit, Lemon, Orange, and Pomegranate
• ResNet50 model is used for transfer learning
• This model is image classifier for 1000 classes
• Above 8 classes also belongs to these 1000 classes.
• ResNet50 model’s last layer is used for classification
• To develop new model, last layer’s trainable property is set to False
• Then a new dense layer is added with 8 units 37
Case Study…
Fig: ResNet50 model’s architecture 38
Case Study…
• Keras callbacks early stopping and model checkpoints are applied
• Validation loss is monitored with patience value 3
• An epoch with minimum validation loss value, will be saved to disk
• During training of model image data is augmented
• Model was set to run for 15 epochs
• Model was early stopped at 10th epoch because validation loss didn’t
decrease for 3 successive epochs from 8, 9 and 10th
• Model achieved training accuracy 0.7930 and validation accuracy
0.8418
39
Case Study …
Fig: Model Accuracy Fig: Model Loss
40
Case Study…
Fig: Parameters of developed model
41
Summary
• Keras is open source framework written in Python
• Easy and fast prototyping
• Runs seamlessly on both CPU and GPU
• Support both CNN and RNN
• Keras models
• Image data augmentation
• Keras callbacks
42
Summary…
• Keras applications
• Transfer learning
• Keras datasets
43
References
• Chollet, F. (2017). Xception: Deep learning with depthwise separable
convolutions. In Proceedings of the IEEE conference on computer vision and
pattern recognition (pp. 1251-1258).
• F. Chollet. Keras. https://github.com/fchollet/keras, 2015.
• Gulli, A., & Pal, S. (2017). Deep Learning with Keras. Packt Publishing Ltd.
• He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image
recognition. In Proceedings of the IEEE conference on computer vision and pattern
recognition (pp. 770-778).
• J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale
Hierarchical Image Database. In CVPR09, 2009
44
References
• Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network
training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
• Perceptron: Architecture Optimization and Training. IJIMAI, 4(1), 26-30.
• Ramchoun, H., Idrissi, M. A. J., Ghanou, Y., & Ettaouil, M. (2016). Multilayer
Perceptron: Architecture Optimization and Training. IJIMAI, 4(1), 26-30.
• Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-
scale image recognition. arXiv preprint arXiv:1409.1556.
• Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A.
(2015). Going deeper with convolutions. In Proceedings of the IEEE conference on
computer vision and pattern recognition (pp. 1-9).
45

More Related Content

What's hot

Introduction to PyTorch
Introduction to PyTorchIntroduction to PyTorch
Introduction to PyTorchJun Young Park
 
Tensorflow presentation
Tensorflow presentationTensorflow presentation
Tensorflow presentationAhmed rebai
 
An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)Thomas da Silva Paula
 
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)Fellowship at Vodafone FutureLab
 
Keras: Deep Learning Library for Python
Keras: Deep Learning Library for PythonKeras: Deep Learning Library for Python
Keras: Deep Learning Library for PythonRafi Khan
 
Introduction to TensorFlow
Introduction to TensorFlowIntroduction to TensorFlow
Introduction to TensorFlowMatthias Feys
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflowCharmi Chokshi
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningMohamed Loey
 
Convolutional neural network
Convolutional neural network Convolutional neural network
Convolutional neural network Yan Xu
 
Introduction of Deep Learning
Introduction of Deep LearningIntroduction of Deep Learning
Introduction of Deep LearningMyungjin Lee
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Intro to Neo4j and Graph Databases
Intro to Neo4j and Graph DatabasesIntro to Neo4j and Graph Databases
Intro to Neo4j and Graph DatabasesNeo4j
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetSungminYou
 
Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Muhammad Ishaq
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & OpportunityiTrain
 

What's hot (20)

Deep learning
Deep learningDeep learning
Deep learning
 
LeNet-5
LeNet-5LeNet-5
LeNet-5
 
Introduction to PyTorch
Introduction to PyTorchIntroduction to PyTorch
Introduction to PyTorch
 
Tensorflow presentation
Tensorflow presentationTensorflow presentation
Tensorflow presentation
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)
 
Introduction to Deep Learning
Introduction to Deep Learning Introduction to Deep Learning
Introduction to Deep Learning
 
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
 
Keras: Deep Learning Library for Python
Keras: Deep Learning Library for PythonKeras: Deep Learning Library for Python
Keras: Deep Learning Library for Python
 
Introduction to TensorFlow
Introduction to TensorFlowIntroduction to TensorFlow
Introduction to TensorFlow
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
Convolutional neural network
Convolutional neural network Convolutional neural network
Convolutional neural network
 
Introduction of Deep Learning
Introduction of Deep LearningIntroduction of Deep Learning
Introduction of Deep Learning
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Deep Learning
Deep Learning Deep Learning
Deep Learning
 
Intro to Neo4j and Graph Databases
Intro to Neo4j and Graph DatabasesIntro to Neo4j and Graph Databases
Intro to Neo4j and Graph Databases
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNet
 
Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...
 
Deep Learning: Application & Opportunity
Deep Learning: Application & OpportunityDeep Learning: Application & Opportunity
Deep Learning: Application & Opportunity
 

Similar to Deep learning with keras

Deep learning summary
Deep learning summaryDeep learning summary
Deep learning summaryankit_ppt
 
YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...
YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...
YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...JacobSilbiger1
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA Taiwan
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceTakrim Ul Islam Laskar
 
Transfer Learning (20230516)
Transfer Learning (20230516)Transfer Learning (20230516)
Transfer Learning (20230516)FEG
 
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Sujit Pal
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for BeginnersSanghamitra Deb
 
JRs presentation-few-shot-learning-overview @ AI4Media WP5 workshop
JRs presentation-few-shot-learning-overview @ AI4Media WP5 workshopJRs presentation-few-shot-learning-overview @ AI4Media WP5 workshop
JRs presentation-few-shot-learning-overview @ AI4Media WP5 workshopHannes Fassold
 
Teach a neural network to read handwriting
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwritingVipul Kaushal
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyNUPUR YADAV
 
Distilling dark knowledge from neural networks
Distilling dark knowledge from neural networksDistilling dark knowledge from neural networks
Distilling dark knowledge from neural networksAlexander Korbonits
 
10 Things I Wish I Dad Known Before Scaling Deep Learning Solutions
10 Things I Wish I Dad Known Before Scaling Deep Learning Solutions10 Things I Wish I Dad Known Before Scaling Deep Learning Solutions
10 Things I Wish I Dad Known Before Scaling Deep Learning SolutionsJesus Rodriguez
 
Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]SubhradeepMaji
 
Convolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular ArchitecturesConvolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular Architecturesananth
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksHannes Hapke
 
Introduction to Mahout and Machine Learning
Introduction to Mahout and Machine LearningIntroduction to Mahout and Machine Learning
Introduction to Mahout and Machine LearningVarad Meru
 

Similar to Deep learning with keras (20)

Deep learning summary
Deep learning summaryDeep learning summary
Deep learning summary
 
YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...
YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...
YU CS Summer 2021 Project | TensorFlow Street Image Classification and Object...
 
Mnist soln
Mnist solnMnist soln
Mnist soln
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
 
Transfer Learning (20230516)
Transfer Learning (20230516)Transfer Learning (20230516)
Transfer Learning (20230516)
 
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for Beginners
 
JRs presentation-few-shot-learning-overview @ AI4Media WP5 workshop
JRs presentation-few-shot-learning-overview @ AI4Media WP5 workshopJRs presentation-few-shot-learning-overview @ AI4Media WP5 workshop
JRs presentation-few-shot-learning-overview @ AI4Media WP5 workshop
 
Teach a neural network to read handwriting
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwriting
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Distilling dark knowledge from neural networks
Distilling dark knowledge from neural networksDistilling dark knowledge from neural networks
Distilling dark knowledge from neural networks
 
cnn ppt.pptx
cnn ppt.pptxcnn ppt.pptx
cnn ppt.pptx
 
10 Things I Wish I Dad Known Before Scaling Deep Learning Solutions
10 Things I Wish I Dad Known Before Scaling Deep Learning Solutions10 Things I Wish I Dad Known Before Scaling Deep Learning Solutions
10 Things I Wish I Dad Known Before Scaling Deep Learning Solutions
 
TensorFlow.pptx
TensorFlow.pptxTensorFlow.pptx
TensorFlow.pptx
 
Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]
 
Convolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular ArchitecturesConvolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular Architectures
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
 
ppt.pdf
ppt.pdfppt.pdf
ppt.pdf
 
Introduction to Mahout and Machine Learning
Introduction to Mahout and Machine LearningIntroduction to Mahout and Machine Learning
Introduction to Mahout and Machine Learning
 

Recently uploaded

Gartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxGartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxchadhar227
 
Statistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbersStatistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numberssuginr1
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...nirzagarg
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样wsppdmt
 
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...gajnagarg
 
Ranking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRanking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRajesh Mondal
 
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...HyderabadDolls
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabiaahmedjiabur940
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...HyderabadDolls
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...nirzagarg
 
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book nowVadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book nowgargpaaro
 
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...kumargunjan9515
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...gajnagarg
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...nirzagarg
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraGovindSinghDasila
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubaikojalkojal131
 
7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.pptibrahimabdi22
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareGraham Ware
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Valters Lauzums
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdfkhraisr
 

Recently uploaded (20)

Gartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxGartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptx
 
Statistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbersStatistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbers
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
 
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
 
Ranking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRanking and Scoring Exercises for Research
Ranking and Scoring Exercises for Research
 
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
 
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book nowVadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
 
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubai
 
7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham Ware
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf
 

Deep learning with keras

  • 1. Keras: A Python framework for Deep Learning CA-691 Mohit Kumar Roll No. - 20961 M.Sc. (Comp. Applications) (Course Seminar) INDIANAGRICULTURALSTATISTICSRESEARCH INSTITUTE,NEWDELHI 1
  • 2. Contents • Introduction • Keras models • Keras layers • Image data augmentation • Keras applications • Transfer learning • Keras datasets • Keras callbacks • Case study • Summary • References 2
  • 3. Introduction • Francois Chollet, the author of Keras, says: “The framework was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.” • Keras is open source framework written in Python • ONEIROS ( Open Ended Neuro-Electronic Intelligent Robot OS) • Released on 27 March 2015 by Francois Chollet • Contains neural-network building blocks like layers, optimizer, activation functions • Support CNN and RNN 3
  • 4. Introduction … • Contains datasets and some pre-trained deep learning applications. • Model check-pointing, early stopping • Uses libraries TensorFlow, Theano, CNTK as backend, only one at a time • Backend does all computations • Keras call backend functions • Works for both CPU and GPU Fig: Keras architecture 4
  • 5. Keras features • Rapid prototyping- 1. Build neural network with minimal lines of code 2. Build simple or complex neural networks within a few minutes • Flexibility- 1. Sometime it is desired to define own metrics, layers, a cost function, Keras provide freedom for the same. 5
  • 6. Keras models • Two types of built in models 1. Sequential 2. Functional All models have following common properties 1. Inputs that contain a list of input tensors 2. Layers, which comprise the model graph 3. Outputs, a list of output tensors. 6
  • 7. Sequential Model • It is linear stack of layers • Output of previous layer is input to the next layer. • Create models by stacking one layer on top of other • Useful in situation where task is not complex • Provides higher level of abstraction Fig: An example of sequential model 7
  • 8. Functional Model • It define more complex models • Such as directed acylic graphs • Multi input output models • Model with shared layers • Possible to connect a layer with any other layer Fig: An example of functional model 8
  • 9. Steps in building a model 9
  • 10. Model methods 1. Compile: It is used to configure model. It accept following parameters • Optimizer: • This specifies type of optimiser to use in back-propagation algorithm • SGD, Adadelta, Adagrad , Adam , Nadam optimizer and many others. • Loss: • It is the objective function • It track losses or the drift from the function during training the model. • For regression: mean squared error, mean absolute error etc. • For classification: Categorical cross-entropy, binary cross entropy • Different loss functions for different outputs 10
  • 11. Model methods… • Metrics: • It is similar to objective function. • Results from metric aren’t used when training model. • It specifies the list of metrics that model evaluate during training and testing. • The commonly used metric is the accuracy metric. • Possible to specify different metrics for different output 11
  • 12. Model methods… 2. Fit  This is the second important method  It train the model for specified epochs  It accept the following important arguments • x: numpy array of training data • y: numpy array of target data • batch_size: 1. It specifies the number of samples per gradient update ,by default 32. 2. 32 samples of training data are fed into the model at a single time. 12
  • 13. Model methods… • epochs: • An epoch is an iteration • It specifies number of times training data is feed to the model. • validation_split: • Fraction of the data that is used as validation. • Validation data is selected from the end samples • At the end of each epoch, loss and metrics are calculated for this data. • validation_data: • shuffle: 13
  • 14. Keras layers • It consist of different types of layers used in deep learning such as: 1. Dense layer: • A Dense layer is fully connected neural network layer (Ramchoun et al, 2016) 14
  • 15. Keras Layers… 2. Convolutional layer: • Mostly used in computer vision. • It extract features from the input image. • It preserves the spatial relationships between pixels • It learn image features using small squares of input data • Finally, the obtained matrix is known as the feature map 15
  • 16. Keras Layers … Figure: Convolutional in Practice 16
  • 17. Keras Layers… 3. Pooling layer • Also called as subsampling or down-sampling layer • Pooling reduces the dimensionality of feature map • Retains the most important information • There are many types of pooling layers such as • MaxPooling and AveragePooling • In case of max pooling, take the largest element from the rectified feature map within that window. • In average pooling, average of all elements in that window is taken. 17
  • 18. Keras Layers … Figure: Max Pooling Concept 18
  • 19. Keras Layers … 4. Recurrent layer • Basic building block of RNN • This is mostly used in sequential and time series modelling. 5. Embedding layers • Required when input is text • These are mostly used in Natural Language Processing. 6. Batch Normalisation layer • Normalize the activations of the previous layer at each batch • Applies a transformation that maintains the mean activation close to 0 and the activation standard deviation close to 1. 19
  • 20. Image Data Augmentation • Performance of deep learning neural networks often improves with the amount of data available • It artificially expand training dataset by creating modified versions of images • It create transformed versions of images in the training dataset that belong to the same class as the original image. • Transformation include operations from the field of image manipulation such as shifts, flips, zooms, rotation etc. 20
  • 21. 21
  • 22. Keras Applications • Keras applications are deep learning models • All these are image classifiers • These applications are available with pre-trained weights • Weights are downloaded automatically when instantiating application • Stored at ~/. Keras/models • These are different variation of pre-trained neural networks • Each has its architecture, size, speed, accuracy etc. 22
  • 24. Keras Applications… 1. VGGNET: • Introduced by Simonyan and Zisserman in their 2014 paper • Very deep convolutional networks for large scale image recognition • 3×3 convolutional layers stacked on top of each other in increasing depth. • Reducing volume size is handled by max pooling. • Two fully-connected layers, each with 4,096 nodes are then followed by a softmax classifier 24
  • 25. Keras Applications… (Simonyan and Zisserman, 2014) 25
  • 26. Continued 2. RESNET • Introduced by He et. al in their 2015 paper deep residual learning for image recognition. • works on the core idea “identity shortcut connection” • Add the original input to the output of the convolution block 26
  • 27. Source He et al.(2015) 27
  • 28. Keras Applications… 3. INCEPTION: • The “Inception” architecture was first introduced by Szegedy et al. in their 2014 paper- Going Deeper with convolutions • It is a convolutional neural network (CNN) which is 27 layers deep • It has some interesting layers called the inception layers • The inception layer is a combination of various layers such as : • 1×1 Convolutions layers • 3×3 Convolutional layer and 5×5 layer • Output filter concatenated into single output vector forming the input of the next image 28
  • 29. Keras Applications… Fig: The idea of an inception module 29
  • 30. Transfer learning • A model that have been trained for a particular task is reused as a base or starting point for other model • Some smart researchers built models on large image datasets like ImagNet, Open images, and COCO • They decided to share their models to the public for reuse • This prevents the need to train an Image Classifier from scratch again 30
  • 31. Transfer learning … • To train an Image classifier that will achieve near or above human level accuracy on image classification, it is required to have 1. Massive amount of data 2. Large computational power 3. Lots of time • Since this is a big problem for people with little or no resources • There is no need for transfer learning if we have • Large dataset that is quite different from the ones above • Have large computational power 31
  • 32. Keras Datasets • Keras contains various datasets that are used to build neural networks. The datasets are described below 1. Boston House Pricing dataset: • It contains 13 attributes of houses of Boston suburbs in the late 1970s • Used in regression problems 2. CIFAR10: • It is used for classification problems. • This dataset contains 50,000 32×32 colour images • Images are labelled over 10 categories • 10,000 test images. 32
  • 33. Keras Datasets … 3. CIFAR100: Same as CIFAR10 but it has 100 categories 4. MNIST: • This dataset contains 60,000 28×28 greyscale images of 10 digits • Also include 10,000 test images. 5. Fashion-MNIST: • This dataset is used for classification problems. • This dataset contains 60,000 28×28 greyscale images of 10 categories, along with 10,000 test images 6. IMDB movie reviews data: • Dataset of 25,000 movies reviews from IMDB • labelled by sentiment (positive/negative). 7. Reuters newswire topics classification: • Dataset of 11,228 newswires from Reuters, labelled over 46 topics 33
  • 34. Keras Callbacks • A callback is a set of functions to be applied at any given stages of the training procedure • Used to get an internal view or statistics of the model during training • A list of callbacks are passed to the fit method of Sequential or Model class • There are different types of callbacks performing different operations 1. History:  1. This call-back is automatically applied to every keras model  2. History object is returned by the fit method of model. 34
  • 35. Keras callbacks … 2. ModelCheckPoint:  This callback save the model after every epoch to a specified path  The advantage of this callback is that if model training is stopped due to any reason, then model will automatically saved to the disk. 3. EarlyStopping:  1. This callback stop training when a monitored quantity stopped improving  2. Important parameter are • Quantity to be monitored • Patience, number of epochs with no improvement after which training will stop. 35
  • 36. Keras Callbacks … 4. TensorBoard:  It is a visualization tool  This callback write a log for TensorBoard which allow to visualize dynamic graph of training and test metrics 36
  • 37. Case Study • Image classifier developed using keras • Web application is developed using Python’s flask framework • Dataset contains 8032 images belongs to 8 classes such as • Banana, Corn, Daisy, Fig, Jackfruit, Lemon, Orange, and Pomegranate • ResNet50 model is used for transfer learning • This model is image classifier for 1000 classes • Above 8 classes also belongs to these 1000 classes. • ResNet50 model’s last layer is used for classification • To develop new model, last layer’s trainable property is set to False • Then a new dense layer is added with 8 units 37
  • 38. Case Study… Fig: ResNet50 model’s architecture 38
  • 39. Case Study… • Keras callbacks early stopping and model checkpoints are applied • Validation loss is monitored with patience value 3 • An epoch with minimum validation loss value, will be saved to disk • During training of model image data is augmented • Model was set to run for 15 epochs • Model was early stopped at 10th epoch because validation loss didn’t decrease for 3 successive epochs from 8, 9 and 10th • Model achieved training accuracy 0.7930 and validation accuracy 0.8418 39
  • 40. Case Study … Fig: Model Accuracy Fig: Model Loss 40
  • 41. Case Study… Fig: Parameters of developed model 41
  • 42. Summary • Keras is open source framework written in Python • Easy and fast prototyping • Runs seamlessly on both CPU and GPU • Support both CNN and RNN • Keras models • Image data augmentation • Keras callbacks 42
  • 43. Summary… • Keras applications • Transfer learning • Keras datasets 43
  • 44. References • Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251-1258). • F. Chollet. Keras. https://github.com/fchollet/keras, 2015. • Gulli, A., & Pal, S. (2017). Deep Learning with Keras. Packt Publishing Ltd. • He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778). • J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09, 2009 44
  • 45. References • Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167. • Perceptron: Architecture Optimization and Training. IJIMAI, 4(1), 26-30. • Ramchoun, H., Idrissi, M. A. J., Ghanou, Y., & Ettaouil, M. (2016). Multilayer Perceptron: Architecture Optimization and Training. IJIMAI, 4(1), 26-30. • Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large- scale image recognition. arXiv preprint arXiv:1409.1556. • Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9). 45