--- title: Diabetic Retinopathy Detection App emoji: 🐢 colorFrom: blue colorTo: purple sdk: gradio sdk_version: 4.22.0 app_file: app.py license: mit --- ![diabetic-retinopathy-detection](https://github.com/bhimrazy/diabetic-retinopathy-detection/assets/46085301/bb45b4cf-9441-435f-819a-176226e1ac00) # Diabetic Retinopathy Detection: Utilizing Multiprocessing for Processing Large Datasets and Transfer Learning to Fine-Tune Deep Learning Models Efficiently process large datasets & develop advanced model pipelines for diabetic retinopathy detection. Streamlining diagnosis. ## TL;DR: In this project, we handle large datasets efficiently by downloading, extracting, and preparing them for analysis. Next, we use PyTorch Lightning to develop a powerful system for diabetic retinopathy detection, categorizing images into different stages of the disease. We enhance our model pipeline with various pretrained backbone models and track progress using TensorBoard. Additionally, we create a user-friendly web app to demonstrate our model's capabilities. Our approach aims to streamline both data processing and model development for accurate and accessible diabetic retinopathy diagnosis. ## Gradio - Diabetic Retinopathy Detection App ### Overview Welcome to our Diabetic Retinopathy Detection App! This app utilizes deep learning models to detect diabetic retinopathy in retinal images. Diabetic retinopathy is a common complication of diabetes and early detection is crucial for effective treatment. ### Try It Out Use the interactive interface below to upload retinal images and get predictions on diabetic retinopathy severity. [Open Diabetic Retinopathy Detection App](https://bhimrazy-diabetic-retinopathy-detection.hf.space) [![Gradio App](https://github.com/bhimrazy/diabetic-retinopathy-detection/assets/46085301/4e0788dd-84a1-427e-a38a-e22c2aa86c50)](https://bhimrazy-diabetic-retinopathy-detection.hf.space) ### How to Use 1. Click on the "Open Diabetic Retinopathy Detection App" button above. 2. Upload a retinal image by clicking on the "Upload Image" button. 3. Once the image is uploaded, the model will process it and provide predictions on the severity of diabetic retinopathy. 4. Interpret the results provided by the model. ## License [MIT](./LICENSE) ## Authors - [@bhimrazy](https://www.github.com/bhimrazy)