Image Classification using DL Methods Version 2

[UTSAVS26]

Pull Request for DL-Simplified 💡

Issue Title: Image Classification using DL Methods Version 2

• Info about the related issue (Aim of the project): The goal of this project is to implement and compare various convolutional neural network (CNN) architectures for image classification tasks using the CIFAR-10 and MNIST datasets. The project will involve evaluating model performance and accuracy across multiple algorithms.
• Name: Utsav Singhal
• GitHub ID: UTSAVS26
• Email ID: [email protected]
• Identify yourself: SWOC Participant

Closes: #995

Describe the add-ons or changes you've made 📃

• Implemented multiple CNN architectures, including LeNet-5, MobileNet, ResNet50, and VGG16, to classify images from the CIFAR-10 and MNIST datasets.
• Preprocessed both datasets, including normalization, resizing, and augmentation.
• Conducted exploratory data analysis (EDA) to visualize the data and check class distribution.
• Trained and tested each model, comparing performance based on accuracy, precision, recall, and F1-score.
• Created visualization tools such as confusion matrices to evaluate model performance.
• Updated README.md with detailed explanations, results, and conclusions.
• Included necessary dependencies in requirements.txt.

Type of change ☑️

What sort of change have you made:

• New feature (non-breaking change which adds functionality)
• Bug fix (non-breaking change which fixes an issue)
• Code style update (formatting, local variables)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested? ⚙️

• The models were trained and evaluated on both the CIFAR-10 and MNIST datasets.
• The accuracy, precision, recall, and F1-score were computed for each model.
• The results were visualized using confusion matrices and performance curves to assess the performance of each CNN architecture.
• The final comparisons between models showed the best performing algorithm for each dataset.

Checklist: ☑️

• My code follows the guidelines of this project.
• I have performed a self-review of my own code.
• I have commented my code, particularly wherever it was hard to understand.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added things that prove my fix is effective or that my feature works.
• Any dependent changes have been merged and published in downstream modules.

[github-actions]

Our team will soon review your PR. Thanks @UTSAVS26 :)

[abhisheks008]

Picture perfect. Your PR is approved and ready to be merged.
@UTSAVS26

[abhisheks008]

Hi @UTSAVS26 please register yourself in the OS-Lead portal. I am not able to add your points there.

[abhisheks008]

Hi @UTSAVS26 please register yourself in the OS-Lead portal. I am not able to add your points there.

[UTSAVS26]

Hi @abhisheks008 I am a PA just like you.