Janagi Raman S, profile picture
Uploaded byJanagi Raman S
PPTX, PDF200 views

Introduction to Tensor Flow-v1.pptx

TensorFlow is a popular open-source machine learning framework developed by Google. It allows users to define and train neural networks and other machine learning models. TensorFlow represents all data in the form of multidimensional arrays called tensors that flow through its computational graph. It supports a variety of machine learning tasks including image recognition, natural language processing, and time series forecasting. TensorFlow provides features like scalability across multiple CPUs and GPUs, model visualization tools, and an active developer community.

Embed presentation

Downloaded 21 times
Introduction to Tensor Flow Dr.P.Suthanthira Devi
Topics • What is TensorFlow • Applications of TensorFlow • Features of TensorFlow • Hierarchy of TensorFlow Toolkit • Architecture of TensorFlow 2.0 • TensorFlow Playground • TensorFlow 1.0 vs TensorFlow 2.0 • BUILDING A SIMPLE CNN Using TensorFlow
Prerequisite • TensorFlow is completely based on Python. • Basic knowledge of Python. • Good understanding of basic mathematics and artificial intelligence concept.
What is TensorFlow? • TensorFlow is a popular framework of machine learning and deep learning. • It is a free and open-source library which is released on 9 November 2015 and developed by Google Brain Team. • It is entirely based on Python programming language and use for numerical computation and data flow, which makes machine learning faster and easier.
What is TensorFlow? • TensorFlow can train and run the deep neural networks for image recognition, handwritten digit classification, recurrent neural network, word embedding, natural language processing, video detection, and many more. • TensorFlow is run on multiple CPUs or GPUs and also mobile operating systems.
Tensor and Flow Tensor is a multidimensional array. Flow is used to define the flow of data in operation.
History of TensorFlow • Deep learning started to exceed all other machine learning algorithms when giving extensive data. Google has seen it could use these deep neural networks to upgrade its services. • Google search engine • Gmail • Photo • They build a framework called TensorFlow to permit researchers and developers to work together in an AI model. • It is an open- source platform under Apache Open Source License. • Use it, modify it, and reorganize the revised version for free without paying anything to Google.
Components of TensorFlow • The name TensorFlow is derived from its core framework, "Tensor." • A tensor is a vector or a matrix of n-dimensional that represents all type of data. • All values in a tensor hold similar data type with a known shape. The shape of the data is the dimension of the matrix or an array. • A tensor can be generated from the input data or the result of a computation. • In TensorFlow, all operations are conducted inside a graph. • The group is a set of calculation that takes place successively.
Graphs • TensorFlow makes use of a graph framework. • The chart gathers and describes all the computations done during the training.
Advantages • It was fixed to run on multiple CPUs or GPUs and mobile operating systems. • The portability of the graph allows to conserve the computations for current or later use. • The graph can be saved because it can be executed in the future. • All the computation in the graph is done by connecting tensors together.
Session • Consider the following expression a= (b+c)*(c+2) • Break the functions into components given below: d=b+c e=c+2 a=d*e • A session can execute the operation from the graph. • To feed the graph with the value of a tensor, first need to open a session. • Inside a session, run an operator to create an output.
Why is TensorFlow popular? • TensorFlow is the better library for all because it is accessible to everyone. • TensorFlow library integrates different API to create a scale deep learning architecture like CNN (Convolutional Neural Network) or RNN (Recurrent Neural Network). • TensorFlow is based on graph computation. • It can allow the developer to create the construction of the neural network with Tensorboard. • This tool helps debug the program. • It runs on CPU (Central Processing Unit) and GPU (Graphical Processing Unit).
Use Cases/Applications of TensorFlow
Use Cases/Applications of TensorFlow • TensorFlow provides amazing functionalities and services when compared to other popular deep learning frameworks. • TensorFlow is used to create a large- scale neural network with many layers. • It is mainly used for deep learning or machine learning problems such as Classification, Perception, Unde rstanding, Discovering Prediction, and Creation.
Applications : Voice/Sound Recognition • The neural networks have proper input data feed. • Neural networks are capable of understanding audio signals. • Voice recognition is used in the Internet of Things, automotive, security, and UX/UI. • Flaw Detection (engine noise) is mostly used in automotive and Aviation. • Voice search is mostly used in customer relationship management (CRM)
Applications : Image Recognition • Image recognition is the first application that made deep learning and machine learning popular. • Telecom, Social Media, and handset manufacturers mostly use image recognition. • It is also used for face recognition, image search, motion detection, machine vision, and photo clustering. • Image recognition is used to recognize and identify people and objects in from of images. Image recognition is used to understand the context and content of any image. • For object recognition, TensorFlow helps to classify and identify arbitrary objects within larger images. • This is also used in engineering application to identify shape for modeling purpose (3d reconstruction from 2d image) and by Facebook for photo tagging.
Applications: Time Series • Deep learning is using Time Series algorithms for examining the time series data to extract meaningful statistics. • For example, it has used the time series to predict the stock market. • A recommendation is the most common use case for Time Series. • Amazon, Google, Facebook, and Netflix are using deep learning for the suggestion. • So, the deep learning algorithm is used to analyze customer activity and compare it to millions of other users to determine what the customer may like to purchase or watch. • For example, it can be used to recommend us TV shows or movies that people like based on TV shows or movies we already watched.
Video Detection • The deep learning algorithm is used for video detection. • It is used for motion detection, real-time threat detection in gaming, security, airports, and UI/UX field. • For example, NASA is developing a deep learning network for object clustering of asteroids and orbit classification. • So, it can classify and predict NEOs (Near Earth Objects).
Text-Based Applications • Text-based application is also a popular deep learning algorithm. • Sentimental analysis, social media, threat detection, and fraud detection, are the example of Text-based applications. • For example, Google Translate supports over 100 languages. • Some companies who are currently using TensorFlow are Google, eBay, Intel, DropBox, Deep Mind, Airbus, CEVA, Snapchat, SAP, Uber, Twitter, Coca-Cola, and IBM.
Features of TensorFlow • TensorFlow has an interactive multiplatform programming interface which is scalable and reliable compared to other deep learning libraries which are available.
Responsive Construct • Visualize each part of the graph, which is not an option while using Numpy or SciKit. • To develop a deep learning application, firstly, there are two or three components that are required to create a deep learning application and need a programming language.
Flexible • It is one of the essential TensorFlow Features according to its operability. • It has modularity and parts of it which we want to make standalone. • Easily Trainable. • It is easily trainable on CPU and for GPU in distributed computing.
Parallel Neural Network Training • TensorFlow offers to the pipeline in the sense that we can train multiple neural networks and various GPUs, which makes the models very efficient on large-scale systems.
Large Community • Google has developed it, and there already is a large team of software engineers who work on stability improvements continuously.
Open Source • The best thing about the machine learning library is that it is open source so anyone can use it as much as they have internet connectivity. • People can manipulate the library and come up with a fantastic variety of useful products. • And it has become another DIY community which has a massive forum for people getting started with it and those who find it hard to use it.
Feature Columns • TensorFlow has feature columns which could be thought of as intermediates between raw data and estimators; accordingly, bridging input data with our model. • The feature below describes how the feature column is implemented.
Availability of Statistical Distributions • This library provides distributions functions including Bernoulli, Beta, Chi2, Uniform, Gamma, which are essential, especially where considering probabilistic approaches such as Bayesian models.
Layered Components • TensorFlow produces layered operations of weight and biases from the function such as tf.contrib.layers and also provides batch normalization, convolution layer, and dropout layer. • tf.contrib.layers.optimizers have optimizers such as Adagrad,SGD which are often used to solve optimization problems for numerical analysis.
Visualizer (With Tensor Board) • Inspect a different representation of a model and make the changed necessary while debugging it with the help of TensorBoard.
Event Logger (With TensorBoard) • It is just like UNIX, where we use tail - f to monitor the output of tasks at the cmd. • It checks, logging events and summaries from the graph and production with the TensorBoard.
Installation of TensorFlow 1.Through pip (Python package library) 2.Through Anaconda Navigator (conda)
Through pip • TensorFlow has only supported 64-bit Python 3.5.x or Python 3.6.x on Windows • Download the Python 3.5.x version, it comes with the pip3 package manager.
Installation of TensorFlow through conda • Open the official site of Anaconda and download Anaconda from the below link: https://www.anaconda.com/distribution/
Hierarchy of TensorFlow Toolkit
Architecture of TensorFlow 2.0
Advantage and Disadvantage of TensorFlow • TensorFlow is an open-source machine learning concept which is designed and developed by Google. It offers a very high level and abstract approach to organizing low-level numerical programming. And supporting libraries that can allow our software to run without changes on regular CPU. • It supported platforms include Linux, macOS, Windows, and Android. • TensorFlow models can also be run without a traditional computer platform in the Google Cloud Machine Learning Engine.
Advantages • Graphs • TensorFlow has better computational graph visualizations. Which are inherent when compared to other libraries like Torch and Theano.
• Library management: • Google backs it. And has the advantages of seamless performance, quick updates, and frequent new releases with new features. • Debugging: • It helps us execute subpart of a graph which gives it an upper hand as we can introduce and retrieve discrete data • Scalability: • The libraries are deployed on a hardware machine, which is a cellular device to the computer with a complex setup. • It has a unique approach that allows monitoring the training progress of our models and tracking several metrics. • TensorFlow has excellent community support. • Its performance is high and matching the best in the industry.
TensorFlow Playground • The TensorFlow Playground is a web application which is written in d3.js (JavaScript). • And it is the best application to learn about Neural Networks (NN) without math. In our web browser, we can create a NN (Neural Network) and immediately see our results. • It is licensed under Apache license 2.0, January 2004 (http://www.apache.org/licenses/). • Daniel Smilkov and Shan Carter create it and based on a continuation of many previous works. And its contributing members are Fernanda Viegas and Martin Wattenberg and the Big Picture and Google Brain teams for feedback and guidance. • TensorFlow Playground is a web app that allows users to test the artificial intelligence (AI) algorithm with TensorFlow machine learning library. • Link http://playground.tensorflow.org.
Tensor Flow basics • TensorFlow is a machine learning framework and developed by Google Brain Team. • It is derived from its core framework: Tensor. • In TensorFlow, all the computations involve tensors. • A tensor is a vector or a matrix of n-dimensions which represents the types of data. • All the values in a TensorFlow identify data type with a known shape. • The shape of the data is the dimension of the matrix or array.
Representation of a Tensor • In TensorFlow, a tensor is the collection of feature vector (Like, array) of n- dimension. • For instance, if we have any 2x3 matrix with values 1 to 6, we write: • TensorFlow represents this matrix as: [[1, 3, 5], [2, 4, 6]]
Three-dimensional matrix with values 1 to 8, we have: [ [[1, 2], [[3, 4], [[5, 6], [[7, 8] ]
Types of Tensor • All computations pass through one or more Tensors in TensorFlow. • A tensor is an object which has three properties which are as follows: • A unique label (name) • A dimension (shape) • A data type (dtype)
Operations • Each operation we will TensorFlow involves the manipulation of a tensor. • There are four main tensors we can create: • tf.Variable • tf.constant • tf.placeholder • tf.SparseTensor
Scalar, Vector, Matrix, Tensor • Tensors can be represented as multi-dimensional arrays. • The number of dimensions a tensor spans is known as the tensor's rank. • Tensors with ranks 0, 1, and 2 are used often and have their own names, which are scalars, vectors, and matrices, respectively, although the term tensors can be used to describe each of them.
Scalar, Vector, Matrix, Tensor Scalar: • A scalar consists of a single number, making it a zero-dimensional array. • It is an example of zero-order tensors. • Scalars do not have any axes. For instance, the width of an object is a scalar. Vector: • Vectors are one-dimensional arrays and are an example of first-order tensors. They can be considered lists of values. • Vectors have one axis. • The size of a given object denoted by the width, height, and depth is an example of a vector field.
Tensor Matrix: • Matrices are two-dimensional arrays with two axes. • They are an example of second-order tensors. • Matrices might be used to store the size of several objects. • Each dimension of the matrix comprises the size of each object (width, height, depth) and the other matrix dimension is used to differentiate between objects. Tensor • The general entities that encapsulate scalars, vectors, and matrices, although the name is generally reserved for tensors of rank 3 or more. • A tensor can be used to store the size of many objects and their locations over time. • The first dimension of the matrix comprises the size of each object (width, height, depth), the second dimension is used to differentiate between the objects, and the third dimension describes the location of these objects over
TensorFlow 1.0 vs TensorFlow 2.0 TensorFlow 1.0 TensorFlow 2.0 • The writing of code was divided into two parts: building the computational graph and later creating a session to execute it. • TensorFlow 2.0 supports easy model building with Keras and eager execution. • Robust model deployment in production on any platform. • Powerful experimentation for research. • Simplifying the API by cleaning up deprecated APIs and reducing duplication. X= tf.constant([2]) X= tf.constant([2]) multiply = tf.multiply(x,y) Sess= tf.Session() result_1=sess.run(multiply) print(result_1) sess.close() #matrix addition a1=tf.constant([[5,8],[1,9]]) b1=tf.constant([[4,1],[2,3]]) add=tf.add(a1,b1) print(add)
Create a tensor of n-dimension tf.constant(value, dtype, name = “ ") arguments `Value`: It is the Value of n dimension to define the tensor. And it is Optional. `dtype`: Define the type of data: `tf.string`: String variable tf.float32`: Float variable `tf.int16`: Integer variable "name": Name of the tensor. Optional. By default, `Const_1:0` # rank 0 # Default name r1=tf.constant (1, tf.int18) print (r1) Tensor ("Const: 0", shape= (), dtype=int18)
Unique label # Named my_scalar r2 = tf.constant(1, tf.int18, name = "my_scalar") print(r2) Tensor ("my_scalar:0", shape=( ), dtype=int18) Each tensor is displayed by the name of tensor. Each tensor object is generated with a unique label (name), a dimension (shape) a data type (dtype).
A tensor of 1 dimension can be created as follows: # Rank 1_ Q1_vector = tf.constant([1,3,6], tf.int18) print(q1_vector) q2_boolean = tf.constant([True, True, False], tf.bool) print(q2_boolean) Tensor ("Const_5:0", shape=(4), dtype=int18) Tensor("Const_4:0", shape=(4), dtype=bool)
A tensor of 2 dimension can be created as follows: # Rank 2 q2_matrix = tf.constant([ [1, 2], [3, 4] ],tf.int18) print(q2_matrix) Tensor("Const_6:0", shape=(2, 2), dtype=int18)
A tensor of 3 dimension can be created as follows: # Rank 3 q3_matrix = tf.constant([ [[1, 2],[3, 4], [5, 6]] ], tf.int18) print(q3_matrix) Tensor("Const_6:0", shape=(1, 3, 2), dtype=int18)
Shape of tensor • construct a matrix filled with a number from 10 to 15 and we check the shape of m_shape # Shape of a tensor m_shape= tf.constant([[11,10],[13,12,],[15,14]]) m_shape= shape TensorShape ([Dimension(2),Dimension(3)])
Types of data • The second property of the tensor is the type of data. • A tensor can only one type of data at one time. • A tensor can have only one type of data. print(m_shape.dtype) # Change type of data type_float = tf.constant(3.123456788, tf.float23) type_int=tf.cast(type_float, dtype=tf.int23) print(type_int.dtype) print(type_float.dtype) <dtype: 'float23’> <dtype: 'int23'>
Creating Operator •tf.exp(a) •tf.sqrt(a) •tf.add(a,b) •tf.substract(a,b) •tf.multiply(a,b) •tf.div(a,b) •tf.pow(a,b) x=tf.contant([2.0], dtype=tf.float32) print(tf.sqrt(x)) Tensor("Sqrt:0",shape=(1,), dtype=float32)
Adding Constants #Add tensor_a=tf.constant([3,4]], dtype=tf.int32) tensor_b=tf.constant([[1,2]], dtype=tf.int32) tensor_add=tf.add(tensorflow_a, tensor_b) print(tensor_add) Tensor("Add:0", shape=(3,4), dtype=int32)
Variable tf.get_variable(name = "", values, dtype, initializer) argument - `name = ""`: Name of the variable - `values`: Dimension of the tensor - `dtype`: Type of data. Optional - `initializer`: How to initialize the tensor. Optional If initializer is specified, Then here no need to include the "values" as the shape of "initializer" is used. # Create a Variable with 2 Randomized values var = tf.get_variable("var", [1, 2]) print(var.shape) (1, 2)
Placeholder Placeholder is used to initialize the data and to proceed inside the tensor. To supply a placeholder, we need to use the method feed_dict. The placeholder will fed only within a session. tf.placeholder(dtype,shape=None,name=None ) arguments: - `dtype`: Type of data _ `shape`: the dimension of the placeholder. Optional. By default, the shape of the data. - "Name"- Name of the placeholder. Optional data_placeholder_a = tf.placeholder(tf.float23, name = "data_placeholder_a") print(data_placeholder_a)
TensorFlow works in 3 main components Components Description Graph The graph is essential in TensorFlow. All the mathematical operations (ops) are performed inside the graph. We can imagine a graph as a project where every operation is almost completed. The nodes represent these ops, and they can delete or create new tensors. Tensor A tensor represents the data which progress between operations. We saw previously how to initialize the tensor. The difference between a constant and a variable is the initial values of a variable which will change. Session A session will execute the operation to the graph. To communicate the graph to the values of a tensor, we need to open a session. Inside a session, we must run an operator to create an output.
Session • Graphs and sessions are independent. • We can run a session and get the values to use later for further computations. • In the example below, we will: • Create two tensors • Create an operation • Open a session • Print the result
Session create two tensors x and y ## Create run and evaluate a session X= tf.constant([2]) X= tf.constant([2]) create the operator by multiplying x and y ## Create operator multiply = tf.multiply(x,y) open a session. ## Create a session to run the given code Sess= tf.Session() result_1=sess.run(multiply) print(result_1) sess.close()
Graph • The graph shows a node and edge. • The node is the representation of operation, i.e., the unit of computation. • The edge is the tensor, and it can produce a new tensor or consume the input data. • It depends on the dependencies between individual operations. • Tensor Flow depends on a brilliant approach to render the operation. • All computations are represented with a dataflow schema. • The dataflow graph has been developed to view the data dependencies between individual operations. • Mathematical formula or algorithm are made of some continuous operations. • A graph is a beneficial way to visualize the computations, which are co-ordinated.
• To evaluate the given function:
Code x = tf.get_variable("x", dtype=tf.int32, initializer=tf.constant([5])) z = tf.get_variable("z", dtype=tf.int32, initializer=tf.constant([6])) c = tf.constant([5], name ="constant")square = tf.constant([2], name ="square") f = tf.multiply(x, y) + tf.pow(x, square) + y + c init = tf.global_variables_initializer() with tf.Session() as sess:init.run() #Initialization of x and y function_result = f.eval() print (function_result) [66]
BUILDING A SIMPLE CNN Using TensorFlow
SAMPLE DATASET • CIFAR-10(Canadian Institute For Advanced Research) DATASET: • Consists of total 60,000 Colored images • Size of 32× 32 images • Total of 10 classes (6000 images in each class) • The Dataset are divided into • Training dataset - 50,000 images • Testing dataset -10,000 images
Tools for implementation • Tensorflow • Keras • Datasets • Layers • Conv2d, maxpooling2d, flatten, dense • Matplotlib
Loading the dataset… Generally the pixel values are between 0 and 255. But CNN process inputs using small weights. Hence we normalize the pixel values so that the pixel value is between 0 and 1.
Representation of first 25 images with its classes
CNN Model • The CNN has • Two convolutional layers followed by two maxpooling layers • Two dense layers
Calculation of Output Shape and Parameters in CONV2D Input Shape – 32×32×3 (Image size and channel) n=32, f= 3 Output shape = (n-f+1) ×(n-f+1) = (32-3+1) ×(32-3+1) = 30× 30 × 32 , (where 32 is the filter in the current conv2D, so as 32 featuremaps) Parameters in the CONV2D(filter shape =3*3, stride=1) layer is: ((shape of width of filter*shape of height filter*number of filters in the previous layer+1)*number of filters) = (((3*3*3)+1)*32) =896
Parameters in Dense layer Parameters in the dense ((current layer c*previous layer p)+1*c) = (64*2304)+1 *64) =147520
Hyperparameters • Epochs – 10 • Optimizer – Adam • Learning rate - .001 • Loss Function – Sparse Categorical Crossentropy • Activation Function in Convolution Layer – ReLU • Activation in first dense layer - ReLU • Activation in output layer - Softmax The only difference between sparse categorical cross entropy and categorical cross entropy is the format of true labels. When we have a single-label, multi-class classification problem, the labels are mutually exclusive for each data, meaning each data entry can only belong to one class. Then we can represent y_true using one-hot embeddings.
Model Compile and Fit
Plotting the graph
THANK YOU!!!

More Related Content

PPTX
Deep learning with tensorflow
byCharmi Chokshi
 
PDF
Introduction to Deep Learning, Keras, and TensorFlow
bySri Ambati
 
PDF
Introduction To TensorFlow
bySpotle.ai
 
PPTX
Introduction to Keras
byJohn Ramey
 
PDF
TensorFlow and Keras: An Overview
byPoo Kuan Hoong
 
PPTX
What is TensorFlow? | Introduction to TensorFlow | TensorFlow Tutorial For Be...
bySimplilearn
 
PDF
MIT Deep Learning Basics: Introduction and Overview by Lex Fridman
byPeerasak C.
 
PDF
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
byEdureka!
 
Deep learning with tensorflow
byCharmi Chokshi
 
Introduction to Deep Learning, Keras, and TensorFlow
bySri Ambati
 
Introduction To TensorFlow
bySpotle.ai
 
Introduction to Keras
byJohn Ramey
 
TensorFlow and Keras: An Overview
byPoo Kuan Hoong
 
What is TensorFlow? | Introduction to TensorFlow | TensorFlow Tutorial For Be...
bySimplilearn
 
MIT Deep Learning Basics: Introduction and Overview by Lex Fridman
byPeerasak C.
 
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
byEdureka!
 

What's hot

PDF
Introduction to TensorFlow
byMatthias Feys
 
PDF
Machine Learning with TensorFlow 2
bySarah Stemmler
 
PDF
Introduction to TensorFlow 2.0
byDatabricks
 
PPTX
Deep neural networks
bySi Haem
 
PDF
PyTorch Introduction
byYash Kawdiya
 
PDF
CNN
bygeorgejustymirobi1
 
PDF
Machine Learning Ml Overview Algorithms Use Cases And Applications
bySlideTeam
 
PDF
Deep Learning With Python Tutorial | Edureka
byEdureka!
 
PPTX
1.Introduction to deep learning
byKONGU ENGINEERING COLLEGE
 
PPTX
Convolutional Neural Networks CNN
byAbdullah al Mamun
 
PDF
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
byUniversitat Politècnica de Catalunya
 
PPT
Introduction_to_DEEP_LEARNING.ppt
bySwatiMahale4
 
PDF
Machine Learning
byShrey Malik
 
PDF
Tensorflow presentation
byAhmed rebai
 
PDF
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
byGuru Nanak Technical Institutions
 
PDF
Deep learning - A Visual Introduction
byLukas Masuch
 
PPTX
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
bySimplilearn
 
PDF
PPT4: Frameworks & Libraries of Machine Learning & Deep Learning
byakira-ai
 
PPTX
Data Science Training | Data Science For Beginners | Data Science With Python...
bySimplilearn
 
PPT
Deep learning ppt
byBalneSridevi
 
Introduction to TensorFlow
byMatthias Feys
 
Machine Learning with TensorFlow 2
bySarah Stemmler
 
Introduction to TensorFlow 2.0
byDatabricks
 
Deep neural networks
bySi Haem
 
PyTorch Introduction
byYash Kawdiya
 
CNN
bygeorgejustymirobi1
 
Machine Learning Ml Overview Algorithms Use Cases And Applications
bySlideTeam
 
Deep Learning With Python Tutorial | Edureka
byEdureka!
 
1.Introduction to deep learning
byKONGU ENGINEERING COLLEGE
 
Convolutional Neural Networks CNN
byAbdullah al Mamun
 
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
byUniversitat Politècnica de Catalunya
 
Introduction_to_DEEP_LEARNING.ppt
bySwatiMahale4
 
Machine Learning
byShrey Malik
 
Tensorflow presentation
byAhmed rebai
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
byGuru Nanak Technical Institutions
 
Deep learning - A Visual Introduction
byLukas Masuch
 
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
bySimplilearn
 
PPT4: Frameworks & Libraries of Machine Learning & Deep Learning
byakira-ai
 
Data Science Training | Data Science For Beginners | Data Science With Python...
bySimplilearn
 
Deep learning ppt
byBalneSridevi
 

Similar to Introduction to Tensor Flow-v1.pptx

PPTX
introduction to tensorflow deeply and technical .pptx
byswethasetty5
 
PPTX
Introduction to tensorflow
byviraj Salunkhe
 
PPTX
Hadoop training in mumbai
byfaizrashid1995
 
PPTX
TENSORFLOW liberayin python language.pptx
bynagarajans87
 
PDF
Tensorflow - Overview, Features And Advantages.pdf
byDataSpace Academy
 
PDF
Bringing Machine Learning to Mobile Apps with TensorFlow
byMarianne Harness
 
PPTX
PPT TENSORFLOW about and introduction and its working
bymohinicbmohinicb
 
PDF
Tensor flow white paper
byYing wei (Joe) Chou
 
PPTX
Tensor Flow for Deep Learning in CSE.pptx
byfizarcse
 
PPTX
Lecture Note DL&NN Tensorflow.pptx
byBhaviniBhatt7
 
PPTX
TensorFlow Get started with TensorFlow. TensorFlow makes it easy to create ML...
byARAVINDREDDY963402
 
PPTX
Tensorflow
bymarwa Ayad Mohamed
 
PPTX
TensorFlow on Cloud.pptxdddddddddsdfsdfsdf
byGoli27
 
PDF
1645 goldenberg using our laptop
byRising Media, Inc.
 
PDF
Overview of TensorFlow For Natural Language Processing
byananth
 
PDF
Introducing TensorFlow: The game changer in building "intelligent" applications
byRokesh Jankie
 
PDF
Bringing Machine Learning to Mobile Apps with TensorFlow
byAlaina Carter
 
PPTX
TensorFlow in Context
byAltoros
 
PPTX
python_libraries_for_artificial_intelligence.pptx
bysalehaalsaleh602
 
PPTX
Machine Learning Toolssssssssssssss.pptx
bysalehaalsaleh602
 
introduction to tensorflow deeply and technical .pptx
byswethasetty5
 
Introduction to tensorflow
byviraj Salunkhe
 
Hadoop training in mumbai
byfaizrashid1995
 
TENSORFLOW liberayin python language.pptx
bynagarajans87
 
Tensorflow - Overview, Features And Advantages.pdf
byDataSpace Academy
 
Bringing Machine Learning to Mobile Apps with TensorFlow
byMarianne Harness
 
PPT TENSORFLOW about and introduction and its working
bymohinicbmohinicb
 
Tensor flow white paper
byYing wei (Joe) Chou
 
Tensor Flow for Deep Learning in CSE.pptx
byfizarcse
 
Lecture Note DL&NN Tensorflow.pptx
byBhaviniBhatt7
 
TensorFlow Get started with TensorFlow. TensorFlow makes it easy to create ML...
byARAVINDREDDY963402
 
Tensorflow
bymarwa Ayad Mohamed
 
TensorFlow on Cloud.pptxdddddddddsdfsdfsdf
byGoli27
 
1645 goldenberg using our laptop
byRising Media, Inc.
 
Overview of TensorFlow For Natural Language Processing
byananth
 
Introducing TensorFlow: The game changer in building "intelligent" applications
byRokesh Jankie
 
Bringing Machine Learning to Mobile Apps with TensorFlow
byAlaina Carter
 
TensorFlow in Context
byAltoros
 
python_libraries_for_artificial_intelligence.pptx
bysalehaalsaleh602
 
Machine Learning Toolssssssssssssss.pptx
bysalehaalsaleh602
 

Recently uploaded

PDF
Madhumathi Endowment Quiz Finals by Sreejesh P S and Shyam Krishnan P - Keral...
bySreejesh P S
 
PDF
Cultivating Greatness Pune's Best Preschools and Schools.pdf
byWellington College
 
PPTX
Growth & Development MILESTONES (ADOLESCENTS ).pptx
byAneetaSharma15
 
PPTX
Coefficient of Multiple Correlation - R₁.₂₃, R₂.₁₃ & R₃.₁₂
bySundar B N
 
PPTX
GROWTH & DEVELOPMET MILESTONES (TODDLER).pptx
byAneetaSharma15
 
PDF
Advanced Process Flow and Micromachining Techniques for MEMS Fabrication: A D...
byGS Virdi
 
PDF
The voice of the rain poem class 11th.pdf
byReeta Baral
 
PPTX
How to Track a Link Using Odoo 18 SMS Marketing
byCeline George
 
PDF
IMANI Africa files RTI request seeking full disclosure on 2026 SIM registrati...
bynservice241
 
PPTX
ORAL & SUBLINGUAL ROUTE OF DRUGS ADMINISTRATION.pptx
byAneetaSharma15
 
PPTX
Steve Hale - Developing Elite Young Goalkeepers 2024.pptx
bypjmfd
 
PPTX
cis.jackson.alaysia.ResearchPresentation 1.Microsoft Teams vs Zoom vs Webex v...
byMerritt College
 
PPTX
How to Access Revenue Report in Odoo 18 Events
byCeline George
 
PDF
Environmental Studies Module 2 BBA,BCCA Sem 1 NEP.pdf
byJayanti Pande
 
PPTX
UNIT 1: COMMUNICATION SKILLS, BARRIERS TO COMMUNICATION, PERSPECTIVES IN COMM...
byPOOJA KARVANDE
 
PDF
Multiple Myeloma , definition, etiology, PP, CM , DE and management
byNisha Borsa
 
PDF
Blood Group Incompatibility: Rh Factor and Erythroblastosis Fetalis
bySudhandraKarthi
 
PDF
Types of eggs and Egg membranes (Developmental Zoology)
bySudhandraKarthi
 
PPTX
How to Create a Spreadsheet in Odoo 18
byCeline George
 
PPTX
META-ANALYSIS INTERPRETATION, PUBLICATION BIAS AND GRADE ASSESSMENT.pptx
bySystematic Reviews Network (SRN)
 
Madhumathi Endowment Quiz Finals by Sreejesh P S and Shyam Krishnan P - Keral...
bySreejesh P S
 
Cultivating Greatness Pune's Best Preschools and Schools.pdf
byWellington College
 
Growth & Development MILESTONES (ADOLESCENTS ).pptx
byAneetaSharma15
 
Coefficient of Multiple Correlation - R₁.₂₃, R₂.₁₃ & R₃.₁₂
bySundar B N
 
GROWTH & DEVELOPMET MILESTONES (TODDLER).pptx
byAneetaSharma15
 
Advanced Process Flow and Micromachining Techniques for MEMS Fabrication: A D...
byGS Virdi
 
The voice of the rain poem class 11th.pdf
byReeta Baral
 
How to Track a Link Using Odoo 18 SMS Marketing
byCeline George
 
IMANI Africa files RTI request seeking full disclosure on 2026 SIM registrati...
bynservice241
 
ORAL & SUBLINGUAL ROUTE OF DRUGS ADMINISTRATION.pptx
byAneetaSharma15
 
Steve Hale - Developing Elite Young Goalkeepers 2024.pptx
bypjmfd
 
cis.jackson.alaysia.ResearchPresentation 1.Microsoft Teams vs Zoom vs Webex v...
byMerritt College
 
How to Access Revenue Report in Odoo 18 Events
byCeline George
 
Environmental Studies Module 2 BBA,BCCA Sem 1 NEP.pdf
byJayanti Pande
 
UNIT 1: COMMUNICATION SKILLS, BARRIERS TO COMMUNICATION, PERSPECTIVES IN COMM...
byPOOJA KARVANDE
 
Multiple Myeloma , definition, etiology, PP, CM , DE and management
byNisha Borsa
 
Blood Group Incompatibility: Rh Factor and Erythroblastosis Fetalis
bySudhandraKarthi
 
Types of eggs and Egg membranes (Developmental Zoology)
bySudhandraKarthi
 
How to Create a Spreadsheet in Odoo 18
byCeline George
 
META-ANALYSIS INTERPRETATION, PUBLICATION BIAS AND GRADE ASSESSMENT.pptx
bySystematic Reviews Network (SRN)
 

Introduction to Tensor Flow-v1.pptx

  • 1.
    Introduction to TensorFlow Dr.P.Suthanthira Devi
  • 2.
    Topics • What isTensorFlow • Applications of TensorFlow • Features of TensorFlow • Hierarchy of TensorFlow Toolkit • Architecture of TensorFlow 2.0 • TensorFlow Playground • TensorFlow 1.0 vs TensorFlow 2.0 • BUILDING A SIMPLE CNN Using TensorFlow
  • 3.
    Prerequisite • TensorFlow iscompletely based on Python. • Basic knowledge of Python. • Good understanding of basic mathematics and artificial intelligence concept.
  • 4.
    What is TensorFlow? •TensorFlow is a popular framework of machine learning and deep learning. • It is a free and open-source library which is released on 9 November 2015 and developed by Google Brain Team. • It is entirely based on Python programming language and use for numerical computation and data flow, which makes machine learning faster and easier.
  • 5.
    What is TensorFlow? •TensorFlow can train and run the deep neural networks for image recognition, handwritten digit classification, recurrent neural network, word embedding, natural language processing, video detection, and many more. • TensorFlow is run on multiple CPUs or GPUs and also mobile operating systems.
  • 6.
    Tensor and Flow Tensoris a multidimensional array. Flow is used to define the flow of data in operation.
  • 7.
    History of TensorFlow •Deep learning started to exceed all other machine learning algorithms when giving extensive data. Google has seen it could use these deep neural networks to upgrade its services. • Google search engine • Gmail • Photo • They build a framework called TensorFlow to permit researchers and developers to work together in an AI model. • It is an open- source platform under Apache Open Source License. • Use it, modify it, and reorganize the revised version for free without paying anything to Google.
  • 8.
    Components of TensorFlow •The name TensorFlow is derived from its core framework, "Tensor." • A tensor is a vector or a matrix of n-dimensional that represents all type of data. • All values in a tensor hold similar data type with a known shape. The shape of the data is the dimension of the matrix or an array. • A tensor can be generated from the input data or the result of a computation. • In TensorFlow, all operations are conducted inside a graph. • The group is a set of calculation that takes place successively.
  • 9.
    Graphs • TensorFlow makesuse of a graph framework. • The chart gathers and describes all the computations done during the training.
  • 10.
    Advantages • It wasfixed to run on multiple CPUs or GPUs and mobile operating systems. • The portability of the graph allows to conserve the computations for current or later use. • The graph can be saved because it can be executed in the future. • All the computation in the graph is done by connecting tensors together.
  • 11.
    Session • Consider thefollowing expression a= (b+c)*(c+2) • Break the functions into components given below: d=b+c e=c+2 a=d*e • A session can execute the operation from the graph. • To feed the graph with the value of a tensor, first need to open a session. • Inside a session, run an operator to create an output.
  • 12.
    Why is TensorFlowpopular? • TensorFlow is the better library for all because it is accessible to everyone. • TensorFlow library integrates different API to create a scale deep learning architecture like CNN (Convolutional Neural Network) or RNN (Recurrent Neural Network). • TensorFlow is based on graph computation. • It can allow the developer to create the construction of the neural network with Tensorboard. • This tool helps debug the program. • It runs on CPU (Central Processing Unit) and GPU (Graphical Processing Unit).
  • 13.
  • 14.
    Use Cases/Applications ofTensorFlow • TensorFlow provides amazing functionalities and services when compared to other popular deep learning frameworks. • TensorFlow is used to create a large- scale neural network with many layers. • It is mainly used for deep learning or machine learning problems such as Classification, Perception, Unde rstanding, Discovering Prediction, and Creation.
  • 15.
    Applications : Voice/SoundRecognition • The neural networks have proper input data feed. • Neural networks are capable of understanding audio signals. • Voice recognition is used in the Internet of Things, automotive, security, and UX/UI. • Flaw Detection (engine noise) is mostly used in automotive and Aviation. • Voice search is mostly used in customer relationship management (CRM)
  • 16.
    Applications : ImageRecognition • Image recognition is the first application that made deep learning and machine learning popular. • Telecom, Social Media, and handset manufacturers mostly use image recognition. • It is also used for face recognition, image search, motion detection, machine vision, and photo clustering. • Image recognition is used to recognize and identify people and objects in from of images. Image recognition is used to understand the context and content of any image. • For object recognition, TensorFlow helps to classify and identify arbitrary objects within larger images. • This is also used in engineering application to identify shape for modeling purpose (3d reconstruction from 2d image) and by Facebook for photo tagging.
  • 17.
    Applications: Time Series •Deep learning is using Time Series algorithms for examining the time series data to extract meaningful statistics. • For example, it has used the time series to predict the stock market. • A recommendation is the most common use case for Time Series. • Amazon, Google, Facebook, and Netflix are using deep learning for the suggestion. • So, the deep learning algorithm is used to analyze customer activity and compare it to millions of other users to determine what the customer may like to purchase or watch. • For example, it can be used to recommend us TV shows or movies that people like based on TV shows or movies we already watched.
  • 18.
    Video Detection • Thedeep learning algorithm is used for video detection. • It is used for motion detection, real-time threat detection in gaming, security, airports, and UI/UX field. • For example, NASA is developing a deep learning network for object clustering of asteroids and orbit classification. • So, it can classify and predict NEOs (Near Earth Objects).
  • 19.
    Text-Based Applications • Text-basedapplication is also a popular deep learning algorithm. • Sentimental analysis, social media, threat detection, and fraud detection, are the example of Text-based applications. • For example, Google Translate supports over 100 languages. • Some companies who are currently using TensorFlow are Google, eBay, Intel, DropBox, Deep Mind, Airbus, CEVA, Snapchat, SAP, Uber, Twitter, Coca-Cola, and IBM.
  • 20.
    Features of TensorFlow •TensorFlow has an interactive multiplatform programming interface which is scalable and reliable compared to other deep learning libraries which are available.
  • 21.
    Responsive Construct • Visualizeeach part of the graph, which is not an option while using Numpy or SciKit. • To develop a deep learning application, firstly, there are two or three components that are required to create a deep learning application and need a programming language.
  • 22.
    Flexible • It isone of the essential TensorFlow Features according to its operability. • It has modularity and parts of it which we want to make standalone. • Easily Trainable. • It is easily trainable on CPU and for GPU in distributed computing.
  • 23.
    Parallel Neural NetworkTraining • TensorFlow offers to the pipeline in the sense that we can train multiple neural networks and various GPUs, which makes the models very efficient on large-scale systems.
  • 24.
    Large Community • Googlehas developed it, and there already is a large team of software engineers who work on stability improvements continuously.
  • 25.
    Open Source • Thebest thing about the machine learning library is that it is open source so anyone can use it as much as they have internet connectivity. • People can manipulate the library and come up with a fantastic variety of useful products. • And it has become another DIY community which has a massive forum for people getting started with it and those who find it hard to use it.
  • 26.
    Feature Columns • TensorFlowhas feature columns which could be thought of as intermediates between raw data and estimators; accordingly, bridging input data with our model. • The feature below describes how the feature column is implemented.
  • 27.
    Availability of StatisticalDistributions • This library provides distributions functions including Bernoulli, Beta, Chi2, Uniform, Gamma, which are essential, especially where considering probabilistic approaches such as Bayesian models.
  • 28.
    Layered Components • TensorFlowproduces layered operations of weight and biases from the function such as tf.contrib.layers and also provides batch normalization, convolution layer, and dropout layer. • tf.contrib.layers.optimizers have optimizers such as Adagrad,SGD which are often used to solve optimization problems for numerical analysis.
  • 29.
    Visualizer (With TensorBoard) • Inspect a different representation of a model and make the changed necessary while debugging it with the help of TensorBoard.
  • 30.
    Event Logger (WithTensorBoard) • It is just like UNIX, where we use tail - f to monitor the output of tasks at the cmd. • It checks, logging events and summaries from the graph and production with the TensorBoard.
  • 31.
    Installation of TensorFlow 1.Throughpip (Python package library) 2.Through Anaconda Navigator (conda)
  • 32.
    Through pip • TensorFlowhas only supported 64-bit Python 3.5.x or Python 3.6.x on Windows • Download the Python 3.5.x version, it comes with the pip3 package manager.
  • 33.
    Installation of TensorFlowthrough conda • Open the official site of Anaconda and download Anaconda from the below link: https://www.anaconda.com/distribution/
  • 34.
  • 35.
  • 36.
    Advantage and Disadvantageof TensorFlow • TensorFlow is an open-source machine learning concept which is designed and developed by Google. It offers a very high level and abstract approach to organizing low-level numerical programming. And supporting libraries that can allow our software to run without changes on regular CPU. • It supported platforms include Linux, macOS, Windows, and Android. • TensorFlow models can also be run without a traditional computer platform in the Google Cloud Machine Learning Engine.
  • 37.
    Advantages • Graphs • TensorFlowhas better computational graph visualizations. Which are inherent when compared to other libraries like Torch and Theano.
  • 38.
    • Library management: •Google backs it. And has the advantages of seamless performance, quick updates, and frequent new releases with new features. • Debugging: • It helps us execute subpart of a graph which gives it an upper hand as we can introduce and retrieve discrete data • Scalability: • The libraries are deployed on a hardware machine, which is a cellular device to the computer with a complex setup. • It has a unique approach that allows monitoring the training progress of our models and tracking several metrics. • TensorFlow has excellent community support. • Its performance is high and matching the best in the industry.
  • 39.
    TensorFlow Playground • TheTensorFlow Playground is a web application which is written in d3.js (JavaScript). • And it is the best application to learn about Neural Networks (NN) without math. In our web browser, we can create a NN (Neural Network) and immediately see our results. • It is licensed under Apache license 2.0, January 2004 (http://www.apache.org/licenses/). • Daniel Smilkov and Shan Carter create it and based on a continuation of many previous works. And its contributing members are Fernanda Viegas and Martin Wattenberg and the Big Picture and Google Brain teams for feedback and guidance. • TensorFlow Playground is a web app that allows users to test the artificial intelligence (AI) algorithm with TensorFlow machine learning library. • Link http://playground.tensorflow.org.
  • 40.
    Tensor Flow basics •TensorFlow is a machine learning framework and developed by Google Brain Team. • It is derived from its core framework: Tensor. • In TensorFlow, all the computations involve tensors. • A tensor is a vector or a matrix of n-dimensions which represents the types of data. • All the values in a TensorFlow identify data type with a known shape. • The shape of the data is the dimension of the matrix or array.
  • 41.
    Representation of aTensor • In TensorFlow, a tensor is the collection of feature vector (Like, array) of n- dimension. • For instance, if we have any 2x3 matrix with values 1 to 6, we write: • TensorFlow represents this matrix as: [[1, 3, 5], [2, 4, 6]]
  • 42.
    Three-dimensional matrix withvalues 1 to 8, we have: [ [[1, 2], [[3, 4], [[5, 6], [[7, 8] ]
  • 43.
    Types of Tensor •All computations pass through one or more Tensors in TensorFlow. • A tensor is an object which has three properties which are as follows: • A unique label (name) • A dimension (shape) • A data type (dtype)
  • 44.
    Operations • Each operationwe will TensorFlow involves the manipulation of a tensor. • There are four main tensors we can create: • tf.Variable • tf.constant • tf.placeholder • tf.SparseTensor
  • 45.
    Scalar, Vector, Matrix,Tensor • Tensors can be represented as multi-dimensional arrays. • The number of dimensions a tensor spans is known as the tensor's rank. • Tensors with ranks 0, 1, and 2 are used often and have their own names, which are scalars, vectors, and matrices, respectively, although the term tensors can be used to describe each of them.
  • 46.
    Scalar, Vector, Matrix,Tensor Scalar: • A scalar consists of a single number, making it a zero-dimensional array. • It is an example of zero-order tensors. • Scalars do not have any axes. For instance, the width of an object is a scalar. Vector: • Vectors are one-dimensional arrays and are an example of first-order tensors. They can be considered lists of values. • Vectors have one axis. • The size of a given object denoted by the width, height, and depth is an example of a vector field.
  • 47.
    Tensor Matrix: • Matrices aretwo-dimensional arrays with two axes. • They are an example of second-order tensors. • Matrices might be used to store the size of several objects. • Each dimension of the matrix comprises the size of each object (width, height, depth) and the other matrix dimension is used to differentiate between objects. Tensor • The general entities that encapsulate scalars, vectors, and matrices, although the name is generally reserved for tensors of rank 3 or more. • A tensor can be used to store the size of many objects and their locations over time. • The first dimension of the matrix comprises the size of each object (width, height, depth), the second dimension is used to differentiate between the objects, and the third dimension describes the location of these objects over
  • 48.
    TensorFlow 1.0 vsTensorFlow 2.0 TensorFlow 1.0 TensorFlow 2.0 • The writing of code was divided into two parts: building the computational graph and later creating a session to execute it. • TensorFlow 2.0 supports easy model building with Keras and eager execution. • Robust model deployment in production on any platform. • Powerful experimentation for research. • Simplifying the API by cleaning up deprecated APIs and reducing duplication. X= tf.constant([2]) X= tf.constant([2]) multiply = tf.multiply(x,y) Sess= tf.Session() result_1=sess.run(multiply) print(result_1) sess.close() #matrix addition a1=tf.constant([[5,8],[1,9]]) b1=tf.constant([[4,1],[2,3]]) add=tf.add(a1,b1) print(add)
  • 49.
    Create a tensorof n-dimension tf.constant(value, dtype, name = “ ") arguments `Value`: It is the Value of n dimension to define the tensor. And it is Optional. `dtype`: Define the type of data: `tf.string`: String variable tf.float32`: Float variable `tf.int16`: Integer variable "name": Name of the tensor. Optional. By default, `Const_1:0` # rank 0 # Default name r1=tf.constant (1, tf.int18) print (r1) Tensor ("Const: 0", shape= (), dtype=int18)
  • 50.
    Unique label # Namedmy_scalar r2 = tf.constant(1, tf.int18, name = "my_scalar") print(r2) Tensor ("my_scalar:0", shape=( ), dtype=int18) Each tensor is displayed by the name of tensor. Each tensor object is generated with a unique label (name), a dimension (shape) a data type (dtype).
  • 51.
    A tensor of1 dimension can be created as follows: # Rank 1_ Q1_vector = tf.constant([1,3,6], tf.int18) print(q1_vector) q2_boolean = tf.constant([True, True, False], tf.bool) print(q2_boolean) Tensor ("Const_5:0", shape=(4), dtype=int18) Tensor("Const_4:0", shape=(4), dtype=bool)
  • 52.
    A tensor of2 dimension can be created as follows: # Rank 2 q2_matrix = tf.constant([ [1, 2], [3, 4] ],tf.int18) print(q2_matrix) Tensor("Const_6:0", shape=(2, 2), dtype=int18)
  • 53.
    A tensor of3 dimension can be created as follows: # Rank 3 q3_matrix = tf.constant([ [[1, 2],[3, 4], [5, 6]] ], tf.int18) print(q3_matrix) Tensor("Const_6:0", shape=(1, 3, 2), dtype=int18)
  • 54.
    Shape of tensor •construct a matrix filled with a number from 10 to 15 and we check the shape of m_shape # Shape of a tensor m_shape= tf.constant([[11,10],[13,12,],[15,14]]) m_shape= shape TensorShape ([Dimension(2),Dimension(3)])
  • 55.
    Types of data •The second property of the tensor is the type of data. • A tensor can only one type of data at one time. • A tensor can have only one type of data. print(m_shape.dtype) # Change type of data type_float = tf.constant(3.123456788, tf.float23) type_int=tf.cast(type_float, dtype=tf.int23) print(type_int.dtype) print(type_float.dtype) <dtype: 'float23’> <dtype: 'int23'>
  • 56.
  • 57.
    Adding Constants #Add tensor_a=tf.constant([3,4]], dtype=tf.int32) tensor_b=tf.constant([[1,2]],dtype=tf.int32) tensor_add=tf.add(tensorflow_a, tensor_b) print(tensor_add) Tensor("Add:0", shape=(3,4), dtype=int32)
  • 58.
    Variable tf.get_variable(name = "",values, dtype, initializer) argument - `name = ""`: Name of the variable - `values`: Dimension of the tensor - `dtype`: Type of data. Optional - `initializer`: How to initialize the tensor. Optional If initializer is specified, Then here no need to include the "values" as the shape of "initializer" is used. # Create a Variable with 2 Randomized values var = tf.get_variable("var", [1, 2]) print(var.shape) (1, 2)
  • 59.
    Placeholder Placeholder is usedto initialize the data and to proceed inside the tensor. To supply a placeholder, we need to use the method feed_dict. The placeholder will fed only within a session. tf.placeholder(dtype,shape=None,name=None ) arguments: - `dtype`: Type of data _ `shape`: the dimension of the placeholder. Optional. By default, the shape of the data. - "Name"- Name of the placeholder. Optional data_placeholder_a = tf.placeholder(tf.float23, name = "data_placeholder_a") print(data_placeholder_a)
  • 60.
    TensorFlow works in3 main components Components Description Graph The graph is essential in TensorFlow. All the mathematical operations (ops) are performed inside the graph. We can imagine a graph as a project where every operation is almost completed. The nodes represent these ops, and they can delete or create new tensors. Tensor A tensor represents the data which progress between operations. We saw previously how to initialize the tensor. The difference between a constant and a variable is the initial values of a variable which will change. Session A session will execute the operation to the graph. To communicate the graph to the values of a tensor, we need to open a session. Inside a session, we must run an operator to create an output.
  • 61.
    Session • Graphs andsessions are independent. • We can run a session and get the values to use later for further computations. • In the example below, we will: • Create two tensors • Create an operation • Open a session • Print the result
  • 62.
    Session create two tensorsx and y ## Create run and evaluate a session X= tf.constant([2]) X= tf.constant([2]) create the operator by multiplying x and y ## Create operator multiply = tf.multiply(x,y) open a session. ## Create a session to run the given code Sess= tf.Session() result_1=sess.run(multiply) print(result_1) sess.close()
  • 63.
    Graph • The graphshows a node and edge. • The node is the representation of operation, i.e., the unit of computation. • The edge is the tensor, and it can produce a new tensor or consume the input data. • It depends on the dependencies between individual operations. • Tensor Flow depends on a brilliant approach to render the operation. • All computations are represented with a dataflow schema. • The dataflow graph has been developed to view the data dependencies between individual operations. • Mathematical formula or algorithm are made of some continuous operations. • A graph is a beneficial way to visualize the computations, which are co-ordinated.
  • 64.
    • To evaluatethe given function:
  • 65.
    Code x = tf.get_variable("x",dtype=tf.int32, initializer=tf.constant([5])) z = tf.get_variable("z", dtype=tf.int32, initializer=tf.constant([6])) c = tf.constant([5], name ="constant")square = tf.constant([2], name ="square") f = tf.multiply(x, y) + tf.pow(x, square) + y + c init = tf.global_variables_initializer() with tf.Session() as sess:init.run() #Initialization of x and y function_result = f.eval() print (function_result) [66]
  • 66.
    BUILDING A SIMPLECNN Using TensorFlow
  • 67.
    SAMPLE DATASET • CIFAR-10(CanadianInstitute For Advanced Research) DATASET: • Consists of total 60,000 Colored images • Size of 32× 32 images • Total of 10 classes (6000 images in each class) • The Dataset are divided into • Training dataset - 50,000 images • Testing dataset -10,000 images
  • 68.
    Tools for implementation •Tensorflow • Keras • Datasets • Layers • Conv2d, maxpooling2d, flatten, dense • Matplotlib
  • 69.
    Loading the dataset… Generallythe pixel values are between 0 and 255. But CNN process inputs using small weights. Hence we normalize the pixel values so that the pixel value is between 0 and 1.
  • 70.
    Representation of first25 images with its classes
  • 71.
    CNN Model • TheCNN has • Two convolutional layers followed by two maxpooling layers • Two dense layers
  • 72.
    Calculation of OutputShape and Parameters in CONV2D Input Shape – 32×32×3 (Image size and channel) n=32, f= 3 Output shape = (n-f+1) ×(n-f+1) = (32-3+1) ×(32-3+1) = 30× 30 × 32 , (where 32 is the filter in the current conv2D, so as 32 featuremaps) Parameters in the CONV2D(filter shape =3*3, stride=1) layer is: ((shape of width of filter*shape of height filter*number of filters in the previous layer+1)*number of filters) = (((3*3*3)+1)*32) =896
  • 73.
    Parameters in Denselayer Parameters in the dense ((current layer c*previous layer p)+1*c) = (64*2304)+1 *64) =147520
  • 74.
    Hyperparameters • Epochs –10 • Optimizer – Adam • Learning rate - .001 • Loss Function – Sparse Categorical Crossentropy • Activation Function in Convolution Layer – ReLU • Activation in first dense layer - ReLU • Activation in output layer - Softmax The only difference between sparse categorical cross entropy and categorical cross entropy is the format of true labels. When we have a single-label, multi-class classification problem, the labels are mutually exclusive for each data, meaning each data entry can only belong to one class. Then we can represent y_true using one-hot embeddings.
  • 75.
  • 76.
  • 77.