TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For Beginners |Simplilearn
8 likes1,386 views
The document provides an overview of using TensorFlow to build deep learning models. It discusses how TensorFlow uses computational graphs to process data and perform computations. Tensors represent multi-dimensional data and are core to TensorFlow's operations. The document also demonstrates how to build simple models like linear regression and recurrent neural networks (RNNs) using TensorFlow. An example RNN model predicts monthly milk production using time series data.
![What is a Tensor?
Tensor is a mathematical object represented as arrays of higher dimensions. These arrays of data with different
dimensions and ranks that are fed as input to the neural network are called Tensors.
Arrays of data with
different dimensions is
fed as input to the
network
Input Layer Hidden Layers Output Layer
a
m
k
q
d
Tensor of Dimensions[5]](https://image.slidesharecdn.com/tensorflowtutorialdeeplearningwithtensorflowtensorflowtutorialforbeginnerssimplilearn-180522061256/85/TensorFlow-Tutorial-Deep-Learning-With-TensorFlow-TensorFlow-Tutorial-For-Beginners-Simplilearn-8-320.jpg)
![What is a Tensor?
Tensor is a mathematical object represented as arrays of higher dimensions. These arrays of data with different
dimensions and ranks that are fed as input to the neural network are called Tensors.
Input Layer Hidden Layers Output Layer
1
6
8
3
9
3
3
4
1
7
4
9
1
5
3
7
1
6
9
2
Tensor of Dimensions[5,4]](https://image.slidesharecdn.com/tensorflowtutorialdeeplearningwithtensorflowtensorflowtutorialforbeginnerssimplilearn-180522061256/85/TensorFlow-Tutorial-Deep-Learning-With-TensorFlow-TensorFlow-Tutorial-For-Beginners-Simplilearn-9-320.jpg)
![What is a Tensor?
Tensor is a mathematical object represented as arrays of higher dimensions. These arrays of data with different
dimensions and ranks that are fed as input to the neural network are called Tensors.
Input Layer Hidden Layers Output Layer
Tensor of Dimensions[3,3,3]](https://image.slidesharecdn.com/tensorflowtutorialdeeplearningwithtensorflowtensorflowtutorialforbeginnerssimplilearn-180522061256/85/TensorFlow-Tutorial-Deep-Learning-With-TensorFlow-TensorFlow-Tutorial-For-Beginners-Simplilearn-10-320.jpg)
![Tensor Rank
The number of dimensions used to represent the data is known as its Rank.
S = 10 Tensor of Rank 0 or a Scalar.
Tensor of Rank 1 or a Vector.V = [10., 11., 12.]
M = [[1, 2, 3],[4, 5, 6]] Tensor of Rank 2 or a Matrix.
T = [[[1],[2],[3]],[[4],[5],[6]],[[7],[8],[9]]] Tensor of Rank 3 or a Tensor](https://image.slidesharecdn.com/tensorflowtutorialdeeplearningwithtensorflowtensorflowtutorialforbeginnerssimplilearn-180522061256/85/TensorFlow-Tutorial-Deep-Learning-With-TensorFlow-TensorFlow-Tutorial-For-Beginners-Simplilearn-11-320.jpg)
![Programming elements in TensorFlow
Variables
Variables allow us to add new trainable parameters to
graph. To define a variable, we use tf.Variable()
command and initialize them before running the graph in
a session.
Example:
W = tf.Variable([.3],dtype=tf.float32)
b = tf.Variable([-.3],dtype=tf.float32)
x = tf.placeholder(tf.float32)
linear_model = W*x+b](https://image.slidesharecdn.com/tensorflowtutorialdeeplearningwithtensorflowtensorflowtutorialforbeginnerssimplilearn-180522061256/85/TensorFlow-Tutorial-Deep-Learning-With-TensorFlow-TensorFlow-Tutorial-For-Beginners-Simplilearn-16-320.jpg)
![Linear Regression using TensorFlow
Let’s work on a regression example to solve a simple equation [y=m*x+b]. We will calculate the slope and the intercept of the
line that best fits our data.
1. Setting up some artificial data for regression](https://image.slidesharecdn.com/tensorflowtutorialdeeplearningwithtensorflowtensorflowtutorialforbeginnerssimplilearn-180522061256/85/TensorFlow-Tutorial-Deep-Learning-With-TensorFlow-TensorFlow-Tutorial-For-Beginners-Simplilearn-19-320.jpg)
TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For Beginners |Simplilearn
- 2. Detecting Diabetic Retinopathy Diabetic Retinopathy is the fastest growing cause of blindness in the world. Deep Learning algorithms using TensorFlow are capable of interpreting signs of Diabetic Retinopathy in retinal photographs. 128,000 images of eye retina’s Fed to a Neural Network for training New image of eye retina Identifies Healthy and Diseased eye
- 3. What’s in it for you? What is Deep Learning? What is TensorFlow? Top Deep Learning Libraries Why use TensorFlow? Building a Computational Graph Programming Elements in TensorFlow Introducing Recurrent Neural Networks Use case implementation of RNN using TensorFlow
- 4. What is Deep learning? Subset of Machine Learning and works on the structure and functions of a human brain Learns from unstructured data and performs complex computations Uses a Neural Net with multiple layers to train an algorithm Deep Learning Input Layer Hidden Layers Output Layer
- 5. Popular libraries for Deep Learning TensorFlow Deep Learning 4 Java TheanoTorch Keras Deep Learning Libraries
- 6. Why use TensorFlow? Provides both C++ and Python API’s that makes it easier to work on TensorFlow reduces the chances of errors by 55% to 85% Teams can run TensorFlow on large scale server farms embedded on devices, CPUs, GPUs, TPUs, etc TensorFlow allows you to train models faster as it has faster compilation time
- 7. What is TensorFlow? TensorFlow Open source library developed by Google brain team in 2012 Developed initially to run large sets of numerical computations Uses Data Flow graphs to process data and perform computations Takes data in the form of arrays of potentially higher dimensions and ranks
- 8. What is a Tensor? Tensor is a mathematical object represented as arrays of higher dimensions. These arrays of data with different dimensions and ranks that are fed as input to the neural network are called Tensors. Arrays of data with different dimensions is fed as input to the network Input Layer Hidden Layers Output Layer a m k q d Tensor of Dimensions[5]
- 9. What is a Tensor? Tensor is a mathematical object represented as arrays of higher dimensions. These arrays of data with different dimensions and ranks that are fed as input to the neural network are called Tensors. Input Layer Hidden Layers Output Layer 1 6 8 3 9 3 3 4 1 7 4 9 1 5 3 7 1 6 9 2 Tensor of Dimensions[5,4]
- 10. What is a Tensor? Tensor is a mathematical object represented as arrays of higher dimensions. These arrays of data with different dimensions and ranks that are fed as input to the neural network are called Tensors. Input Layer Hidden Layers Output Layer Tensor of Dimensions[3,3,3]
- 11. Tensor Rank The number of dimensions used to represent the data is known as its Rank. S = 10 Tensor of Rank 0 or a Scalar. Tensor of Rank 1 or a Vector.V = [10., 11., 12.] M = [[1, 2, 3],[4, 5, 6]] Tensor of Rank 2 or a Matrix. T = [[[1],[2],[3]],[[4],[5],[6]],[[7],[8],[9]]] Tensor of Rank 3 or a Tensor
- 12. Tensor Data type Data Type Python Type Description DF_FLOAT tf.float32 32 bits floating point DF_DOUBLE tf.float64 64 bits floating point DT_INT8 tf.int8 8 bits signed integer DT_INT16 tf.int16 16 bits signed integer DT_INT32 tf.int32 32 bits signed integer DT_INT64 tf.int64 64 bits signed integer DT_UINT8 tf.unit8 8 bits unsigned integer DT_STRING tf.string Variable length byte arrays DT_BOOL tf.bool Boolean In addition to rank and shape, Tensors have a data type. Following is the list of the data type:
- 13. Building a Computation Graph Everything in TensorFlow is based on creating a computational graph. It has a network of nodes, with each node performing an operation like addition, multiplication or evaluating some multivariate equation. input input add mul mul a b c d e 5 3 4 2 7 1 2 84 In TensorFlow, a computation is described using a Data Flow graph Nodes represent mathematical operation and edge represents tensors
- 14. Building a Computation Graph Lets compute a function F of 3 variables a, b, c : F(a,b,c) = 5(a+bc) p = bc q = a + p F = 5*q a=4 b=3 c=5 p = bc q = a + p F = 5*q 15 19 95
- 15. Programming elements in TensorFlow Constants Constants are parameters whose value does not change. To define a constant, we use tf.constant() command. Example: a = tf.constant(2.0, tf.float32) b = tf.constant(3.0) Print(a, b)
- 16. Programming elements in TensorFlow Variables Variables allow us to add new trainable parameters to graph. To define a variable, we use tf.Variable() command and initialize them before running the graph in a session. Example: W = tf.Variable([.3],dtype=tf.float32) b = tf.Variable([-.3],dtype=tf.float32) x = tf.placeholder(tf.float32) linear_model = W*x+b
- 17. Programming elements in TensorFlow Placeholder Placeholders allow us to feed data to a tensorflow model from outside a model. It permits a value to be assigned later. To define a placeholder, we use tf.placeholder() command. Example: a = tf.placeholder(tf.float32) b = a*2 with tf.Session() as sess: result = sess.run(b,feed_dict={a:3.0}) print result feed_dict specifies tensors that provide concrete values to the placeholders
- 18. Programming elements in TensorFlow Session A session is run to evaluate the nodes. This is called as the TensorFlow runtime. Example: a = tf.constant(2.0) b = tf.constant(4.0) c = a+b # Launch Session sess = tf.Session() # Evaluate the tensor c print(sess.run(c)) Running a Computation Graph a b c 4.0 2.0 Addition 6.0
- 19. Linear Regression using TensorFlow Let’s work on a regression example to solve a simple equation [y=m*x+b]. We will calculate the slope and the intercept of the line that best fits our data. 1. Setting up some artificial data for regression
- 20. Linear Regression using TensorFlow 2. Plot the Data
- 21. Linear Regression using TensorFlow 3. Assign the variables 4. Apply the Cost Function
- 22. Linear Regression using TensorFlow 5. Apply the Optimization function 6. Initialize the variables 7. Create the session and run the computation
- 23. Linear Regression using TensorFlow 8. Print the slope and intercept
- 24. Linear Regression using TensorFlow 9. Evaluate the results
- 25. Introducing Recurrent Neural Networks In a Feed-Forward Network like CNN/ANN, information flows only in forward direction, from the input nodes, through the hidden layers (if any) and to the output nodes. There are no cycles or loops in the network. Input Layer Hidden Layers Output Layer Feed-Forward Network Yellow Patch Petals length and width Sepals length and width Output Iris Not Iris
- 26. Introducing Recurrent Neural Networks Recurrent Neural Networks are used to handle sequential time series data because it is able to memorize the inputs. At a particular time step, RNN accepts previous output result along with the current input to generate the output at that time step. Recurrent Neural Network h x y w Rotate the neural network vertically and compress the layers
- 27. How does a Recurrent Neural Network look like? h x y w Unfold ht-1 xt-1 yt-1 ht xt yt ht+1 xt+1 yt+1 w ww w Input at time t Output at time t Hidden state at time t ht = f (ht-1 ,xtw ) ht = new state fw = function with parameter w ht-1 = old state xt = input vector at time step t
- 28. Types of RNN While Feed-Forward Networks map one input to one output, Recurrent Neural Networks can map one to many, many to one and many to many. One to One One to Many Many to One Many to Many
- 29. Types of RNN While Feed-Forward Networks map one input to one output, Recurrent Neural Networks can map one to many, many to one and many to many. One to One One to Many Many to One Many to Many • Known as the Vanilla Neural Network. Used for regular machine learning problems 1 output 1 input
- 30. Types of RNN While Feed-Forward Networks map one input to one output, Recurrent Neural Networks can map one to many, many to one and many to many. One to One One to Many Many to One Many to Many • Used for image captioning. Given an image, it generate a sequence of words, captioning the image multiple outputs 1 input
- 31. Types of RNN While Feed-Forward Networks map one input to one output, Recurrent Neural Networks can map one to many, many to one and many to many. One to One One to Many Many to One Many to Many • Used to carry out Sentiment Analysis. Given a set of words, it tells you the sentiment present 1 output multiple inputs
- 32. Types of RNN While Feed-Forward Networks map one input to one output, Recurrent Neural Networks can map one to many, many to one and many to many. One to One One to Many Many to One Many to Many • Used in Machine Translation. Given a sets of words in one language, it translates it to another multiple inputs multiple outputs
- 33. Use case implementation of RNN Lets look at a use case of predicting the monthly milk production per cow in pounds using a time series data Based on Data between Jan 1962 to Dec 1975 How much milk production can we expect in a month?
- 34. Use case implementation of RNN 1. Import the necessary libraries 2. Read the dataset and print the head of it
- 35. Use case implementation of RNN 3. Convert the index to time series 4. Plot the time series data
- 36. Use case implementation of RNN 5. Perform the train test split on the data
- 37. Use case implementation of RNN 6. Scale the data using standard Machine Learning process 7. Applying the batch function
- 38. Use case implementation of RNN 8. Setting up the RNN model
- 39. Use case implementation of RNN 9. Create Placeholders for X and y 10. Applying the loss function and optimizer 11. Initialize the Global variables 12. Create an instance of tf.train.Saver()
- 40. Use case implementation of RNN 13. Create the session and run it
- 41. Use case implementation of RNN 14. Display the Test Data
- 42. Use case implementation of RNN 15. Create a seed training_instance to predict the last 12 months milk production from the training data
- 43. Use case implementation of RNN 16. Displaying the results of the prediction
- 44. Use case implementation of RNN 17. Reshape the results 18. Create a new column on the test data called Generated
- 45. Use case implementation of RNN 19. View the test_set dataframe
- 46. Use case implementation of RNN 20. Plot the predicted result and the actual result
- 47. Key Takeaways