RetiZero DR Model
Model description
This repository contains the fine-tuned RetiZero model weights used for diabetic retinopathy classification.
The model is part of the Afterimage project and is used as one of the inference backends for retinal fundus image analysis.
Intended use
This model is intended for research, educational, and prototype inference purposes in diabetic retinopathy grading from retinal fundus images.
Limitations
- This model is not a medical device.
- This model is not intended to replace professional clinical judgment.
- Predictions may be affected by image quality, dataset bias, preprocessing differences, and domain shift.
- Performance may vary on images from sources different from the training or evaluation data.
Training / fine-tuning
This model was fine-tuned for diabetic retinopathy classification as part of the Afterimage project.
Input
- Retinal fundus images
Output
- Diabetic retinopathy classification output
Files
best_retizero_dr.pth: fine-tuned model checkpoint
Authors
Afterimage project
Disclaimer
This repository is provided for research and academic use only.
Model tree for moht24/retizero-dr-model
Unable to build the model tree, the base model loops to the model itself. Learn more.