Astronomical Object Detection Tool

[Advita9]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title : Astronomical Object Detection Tool

🔴 Aim : A tool to detect an astronomical object using images

🔴 Dataset : Kaggle Astronomy Image Classification Dataset

🔴 Approach : Creating a 6 layer CNN for object detection

---

📍 Follow the Guidelines to Contribute in 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 in 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 issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

✅ To be Mentioned while taking the issue :

• Full name : Advita Shrivastava
• GitHub Profile Link : @Advita9
• Email ID : [email protected]
• Participant ID (if applicable):
• Approach for this Project : Convolutional Neural Networks
• What is your participant role? (Mention the Open Source program): Contributor at GSSOC

---

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! 😊

[Advita9]

I would like to undertake thir project

Full name : Advita Shrivastava
GitHub Profile Link : @Advita9
Email ID : [email protected]
Participant ID (if applicable):
Approach for this Project : Convolutional Neural Networks
What is your participant role? (Mention the Open Source program): Contributor at GSSOC

[abhisheks008]

Can you please elaborate on the approach/models you are planning to implement here for this project?

[Advita9]

Can you please elaborate on the approach/models you are planning to implement here for this project?

I am implementing a convolutional neural network (CNN) with 5 convolutional layers followed by fully connected layers for classification. The model uses data augmentation techniques such as random rotation and normalization, and is trained using PyTorch Lightning. I plan to track performance metrics like accuracy and visualize results with confusion matrices to improve the model.

[abhisheks008]

Apart from CNN what are the other models you are planning to implement for this problem statement and dataset. As this repository mainly suggests to implement 3-4 models for each problem statement and find out the best fitted one based on the accuracy scores. Generally students who are new to this open source and deep learning need to explore more on the topics, hence implementing various models will help those people to understand the variety of the models they can implement using the same dataset.

@Advita9 looking forward to hearing from you.

[Advita9]

I am also planning to incorporate ResNet-18, VGG-16 and MobielNetV2 in my training.

[Advita9]

is this

I am also planning to incorporate ResNet-18, VGG-16 and MobielNetV2 in my training.

Is this alright?

@abhisheks008

[Advita9]

@abhisheks008 just tagging you again, if approved I can submit code.

[abhisheks008]

Assigned @Advita9