Scribd
Upload
9 views17 pages

Kerasdaksh

The document outlines a lab report for a Deep Learning course using Tensorflow and Keras, submitted by a student named Gargi Gaur. It includes a detailed index of experiments aimed at training various datasets, implementing neural networks, and evaluating models. Each experiment focuses on different aspects of deep learning, such as training on Fashion MNIST and CIFAR-10 datasets, implementing regularization, dropout, and building convolutional neural networks.

Uploaded by

220160203084.gargi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
9 views17 pages

Kerasdaksh

The document outlines a lab report for a Deep Learning course using Tensorflow and Keras, submitted by a student named Gargi Gaur. It includes a detailed index of experiments aimed at training various datasets, implementing neural networks, and evaluating models. Each experiment focuses on different aspects of deep learning, such as training on Fashion MNIST and CIFAR-10 datasets, implementing regularization, dropout, and building convolutional neural networks.

Uploaded by

220160203084.gargi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 17

Deep Learning with Tensorflow and Keras Lab.

CSE4011L

School of Engineering & Sciences

Department of Computer Science and Engineering

Submitted by
Student Name Gargi Gaur
Enrolment No. 220160203085

Programme B Tech CSE

Department SOES

Session/Semester 2022-26/VI

Submitted to
Faculty Name Ms. Sapna Sharma

1
INDEX
S No. Aim of the experiment Page No. Date Teacher’s Signature

1 Training the Fashion MNIST Dataset with 3-5 23.01.25


Tensorflow

2 Compute the function using Tensorflow 6 23.02.25


library (x,y) = x2 + y2+2x+y

3 Implementation of AND gate using 7 06.02.25


Tensorflow by creating a single layer
perceptron
4 Implement Deep Neural Network using 8 06.02.25
Tensorflow and Keras training it on the
CIFAR-10 dataset
5 Implement Deep Neural Network using 9 13.02.25
Tensorflow and Keras, train the DNN with
image 2D or 3D dataset , add
regularisation.
6 Implement a deep neural network using 10 20.02.25
Tensorflow and Keras and train the DNN ,
add dropout neutrons
7 Implement a deep neural network using 11 27.02.25
Tensorflow and Keras, train the DNN with
image 2D or 3D dataset and implement
early stopping.
8 Build convolutional neural network model 12-13 27.02.25
(CNN) (Basic model) for image and other
2D or 3D data
9 Evaluate the model using five-fold 14-15 06.03.25
crossvalidation and Develop an Improved
Model.
10 Develop a model for Text classification 16-17 06.03.25
with an RNN.

Experiment No. 1

Aim: Training the Fashion MNIST Dataset with Tensorflow.

2
Input: Importing the libraries

Output:

Input: Loading the Fashion MNIST dataset

Output:

Input:

Output:
Input: Printing the length of train and test labels

Output:

3
Input: Plotting the train image

Output:

Input:

Output:

4
5
Experiment N
o. 2

Aim: Compute the function using Tensorflow library (x,y) = x2 + y2+2x+y Input:

Output:

Input:

Output:

o. 3

Aim: Implementation of AND gate using Tensorflow by creating a single layer perceptron.

Input:

6
Experiment N

Output:

o. 4

Aim: Implement Deep Neural Network using Tensorflow and Keras training it on the CIFAR-10
dataset.

Input:

7
Experiment N

Output:

8
Experiment N
o. 5

Aim: Implement Deep Neural Network using Tensorflow and Keras, train the DNN with image 2D
or 3D dataset , add regularisation.

Input:

Output:

9
Experiment N
o. 6

Aim: Implement a deep neural network using Tensorflow and Keras and train the DNN , add
dropout neutrons.

Input:

Output:

10
Experiment N
o. 7

Aim: Implement a deep neural network using Tensorflow and Keras, train the DNN with image 2D
or 3D dataset and implement early stopping.

Input:

Output:

11
Experiment N

Aim:
o. 8

Build convolutional neural network model (CNN) (Basic model) for image and other 2D or
3D data.

Input:

12
Output:

13
Experiment N

Aim:
o. 9

Evaluate the model using five-fold cross-validation and Develop an Improved Model.

Input:

14
Output:

o. 10

Develop a model for Text classification with an RNN.

Input:

15
Experiment N

Aim:

Output:

16
17

You might also like