NashidulSarker/pulmonary-diagnostics-ai

Pulmonary Diagnostics AI 🫁

A web application designed for chest X-ray classification (Normal, COVID-19, Tuberculosis, and Viral Pneumonia) using a trained DenseNet-121 model. It uses OpenAI's CLIP model to validate that uploaded images are indeed chest X-rays before making predictions.

Running Locally

1. 1.Create a virtual environment and activate it:

   python -m venv .venv
   # Windows:
   .\.venv\Scripts\Activate.ps1
   # Linux/macOS:
   source .venv/bin/activate

1. 1.Install dependencies:

   pip install -r requirements.txt

1. 1.Launch the Gradio web app:

   python gradio_app.py

Deploying to Hugging Face Spaces

This repository is pre-configured for deployment to Hugging Face Spaces.

Option A: Uploading via the Web UI (Easiest)

1. 1.Go to Hugging Face Spaces and click Create new Space.
2. 2.Give it a name, select Gradio as the SDK, and choose a free CPU basic tier (or GPU).
3. 3.Navigate to the Files tab in your new Space and click Add file -> Upload files.
4. 4.Drag and drop the following files/folders from your project:
5. 5.gradio_app.py
6. 6.requirements.txt
7. 7.README.md
8. 8.CNN_joint.pth
9. 9.Models/ (entire directory)

Option B: Deploying via Git (Recommended for updates)

Since CNN_joint.pth is around 28 MB, you must use Git LFS (Large File Storage) when pushing via Git:

1. 1.Initialize Git and Git LFS:

   git init
   git lfs install
   git lfs track "*.pth"
   git add .gitattributes

1. 1.Add your Hugging Face Space repository as a remote and push:

   git remote add origin https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE_NAME
   git add .
   git commit -m "Initial commit with model and app"
   git push -u origin main