Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature]: Malaria Detection In Human Body Using Body Cell Images #103

Closed
1 task done
seeratfatima19 opened this issue May 19, 2024 · 12 comments
Closed
1 task done

Comments

@seeratfatima19
Copy link

Is your feature request related to a problem? Please describe.

Hi @SrijanShovit

I propose to add the model of Malaria Detection using the dataset of images of human body cells.
I'll use deep learning model to get to the objective and achieve high accuracy and precision. I have already done work in ML domain so I am experienced to work with NumPy, Pandas, TensorFlow frameworks.

Kindly assign me the issue under the label of GSSoC'24

thanks and regards

Describe the solution you'd like

I'll get the Cell images dataset from Kaggle and use Pandas for most preprocessing and then leverage TensorFlow for classification of images.

Describe alternatives you've considered

No response

Additional context

No response

Code of Conduct

  • I agree to follow this project's Code of Conduct
Copy link

Congratulations, @seeratfatima19! 🎉 Thank you for creating your issue. Your contribution is greatly appreciated and we look forward to working with you to resolve the issue. Keep up the great work!

We will promptly review your changes and offer feedback. Keep up the excellent work! Kindly remember to check our contributing guidelines

@SrijanShovit
Copy link
Owner

Dataset link?

@seeratfatima19
Copy link
Author

@SrijanShovit
Copy link
Owner

Explore some research papers about it. If you can beat them, it's great, otherwise we can only proceed till a nice college project.

@seeratfatima19
Copy link
Author

Okay so what you mean is if I can beat research papers only then I will be assigned this issue?

@SrijanShovit
Copy link
Owner

No.
Case 1: You can beat research papers, then superb bcz this dataset saturates around 97%. You can propose this to conferences. It will be a great addition to you profile when you sit in interviews.
Case 2: You couldn't, then it's just a fantastic ml project of college with web ui.

It's a good challenge if you challenge this dataset, keeping in mind light models for web apps. Just telling by my experience with the dataset.

@seeratfatima19
Copy link
Author

I got you. So please assign me the issue and then when I start working on it, I'll keep experimenting any way I can get its accuracy better than currently existing methods or not.

@SrijanShovit
Copy link
Owner

Go through this discussion on what kind of workflow I expect: #56

@seeratfatima19
Copy link
Author

Yes sure I'll follow the required workflow.

@seeratfatima19
Copy link
Author

@SrijanShovit I just needed to clarify one thing:
as per the workflow you mentioned, should i open separate issues for
-> preprocessing
-> model making and evaluation.

@SrijanShovit
Copy link
Owner

  1. Since the dataset is balanced and large enough, I don't think there is need for any preprocessing.
  2. But you might like to do augmentation and create your version of data and train on that, not on original one.

Proceed with 1, in case we don't succeed, we can take path 2, for which I will create separate issue.

Copy link

This issue has been automatically closed because it has been inactive for more than 7 days. If you believe this is still relevant, feel free to reopen it or create a new one. Thank you!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants