Spaces:
Running
Running
title: Insect Model Zoo | |
emoji: ππ¬ | |
colorFrom: blue | |
colorTo: green | |
sdk: gradio | |
sdk_version: 4.36.1 | |
app_file: app.py | |
pinned: false | |
license: apache-2.0 | |
short_description: Comparing InsectSAM, Yolov8, Detectron2 | |
## https://insectsam.live | |
## What is InsectSAM? | |
InsectSAM is an open-source machine learning model tailored for the DIOPSIS camera systems and ARISE algorithms, dedicated to Insect Biodiversity Detection and Monitoring in the Netherlands. | |
![whatisinsectsam](https://insectsam.live/assets/images/undraw_docusaurus_mountain-e42b6f2eba6f6cca2d69178e66414779.png) | |
## How does it work? | |
Based on Meta AI segment-anything, InsectSAM is fine-tuned to accurately segment insects from complex backgrounds. It boosts the precision and efficiency of biodiversity monitoring algorithms, especially in scenarios with diverse backgrounds that attract insects. | |
![howdoesitwork](https://insectsam.live/assets/images/undraw_docusaurus_react-616141633fe960e3f853b86fef751af9.png) | |
## Technologies Used | |
Python, PyTorch, Hugging Face Transformers, OpenCV, and more. InsectSAM is designed to be easily integrated into existing DIOPSIS and ARISE algorithms, providing a seamless experience for researchers and developers. | |
![tech](https://insectsam.live/assets/images/undraw_docusaurus_stack-957770c8948b116dc310df4dbcf9bb34.png) |