This repository provides tools and scripts for fine-tuning the Segment Anything Model (SAM). SAM is a state-of-the-art model for image segmentation tasks.
This repository contains two fine-tuned versions of SAM:
- SAM1: Complete fine-tuned model optimized for mitochondria segmentation
- SAM2: Work in progress - enhanced version with additional capabilities (not yet complete)
- Fine-tune SAM on custom datasets.
- Easily configurable pipeline for training and evaluation.
- Support for various datasets and augmentation techniques.
- Multiple model variants with different specializations.
- Clone the repository:
git clone https://github.com/your-username/fine-tune-sam.git cd fine-tune-sam - Install dependencies:
pip install -r requirements.txt
- Prepare your dataset:
- Ensure your dataset is in the required format.
- Update the configuration file with the dataset path.
Contributions are welcome! Please open an issue or submit a pull request for any improvements or bug fixes.