Image Classification using Convolutional Neural Networks

[UTSAVS26]

ML-Crate Repository (Proposing new issue)

🔴 [Project Addition]: Image Classification using Convolutional Neural Networks (CNN)

🔴 Description: Create a CNN-based model for image classification. You could use a popular dataset like CIFAR-10 or MNIST. Develop a web interface to upload images and get classification results.

🔴 Dataset Link: CIFAR-10 Dataset or MNIST Dataset

🔴 Approach:

• Implement a Convolutional Neural Network (CNN) model for image classification using a popular dataset (CIFAR-10 or MNIST).
• Use data preprocessing and augmentation techniques to enhance the model's performance.
• Compare the CNN model with at least one other image classification algorithm to highlight its effectiveness.
• Develop a web interface where users can upload images and receive classification results.
• Perform thorough exploratory data analysis (EDA) before model creation to understand the dataset's characteristics.

======================================================================================
📍 Follow the Guidelines to Contribute to the Project:
You need to create a separate folder named as the Project Title.
Inside that folder, there will be four main components:

• Images: To store the required images.
• Dataset: To store the dataset or information/source about the dataset.
• Model: To store the machine learning model you've created using the dataset.
• requirements.txt: This file will contain the required packages/libraries to run the project on other machines.
  Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

======================================================================================
🔴🟡 Points to Note:

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include the issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before starting to contribute.

======================================================================================
✅ To be Mentioned while taking the issue:

• Full Name: Utsav Singhal

• GitHub Profile Link: https://github.com/UTSAVS26

• Email ID: [email protected]

• Participant ID (If not, then put NA): Contributor

• Approach for this Project:

  • Implement a CNN model for image classification using the CIFAR-10 or MNIST dataset.
  • Perform data preprocessing and augmentation.
  • Compare the CNN model with another classification algorithm.
  • Develop a web interface for image upload and classification results.
  • Conduct EDA to understand the dataset.

• What is your participant role? (Mention the Open Source Program name. Eg. HRSoC, GSSoC, GSOC etc.): SSOC

======================================================================================
Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

What are the 3-4 models you are planning to implement here?
@UTSAVS26

[UTSAVS26]

Hi @abhisheks008 thank you for assigning this issue to me.
I am planning to implement these models right now:

1. Simple CNN Model
2. VGG-16 Model
3. ResNet-50 Model
4. LeNet-5 Model
5. InceptionV3 Model
6. DenseNet Model
7. MobileNet Model
8. Comparison Model (e.g., Random Forest or SVM with HOG features)
9. AlexNet Model
10. EfficientNet Model

And if any models failed based on the preprocessing and EDA I do then I will leave that model right now and work on that model later on.

[abhisheks008]

Hi @abhisheks008 thank you for assigning this issue to me. I am planning to implement these models right now:

1. Simple CNN Model
2. VGG-16 Model
3. ResNet-50 Model
4. LeNet-5 Model
5. InceptionV3 Model
6. DenseNet Model
7. MobileNet Model
8. Comparison Model (e.g., Random Forest or SVM with HOG features)
9. AlexNet Model
10. EfficientNet Model

And if any models failed based on the preprocessing and EDA I do then I will leave that model right now and work on that model later on.

Go ahead with the models.