GitHub - Gabriellgpc/computer-vision-dataset-maker: The Power of Florence-2 with OpenVINO & FiftyOne: Real-World Applications in Image Analysis (original) (raw)
Navigation Menu
- GitHub Copilot Write better code with AI
- GitHub Models New Manage and compare prompts
- GitHub Advanced Security Find and fix vulnerabilities
- Actions Automate any workflow
- Codespaces Instant dev environments
- Issues Plan and track work
- Code Review Manage code changes
- Discussions Collaborate outside of code
- Code Search Find more, search less
- Explore
- Pricing
Provide feedback
Saved searches
Use saved searches to filter your results more quickly
Appearance settings
Computer Vision Dataset Maker
You can find a technical article related to this project here The Power of Florence-2 with OpenVINO & FiftyOne: Real-World Applications in Image Analysis
Conda environment
conda create -n cvd-maker python=3.11 -y conda activate cvd-maker pip install -r requirements.txt
TODO
- Make fiftyone dataset
- Add Object detection predictions from OVFlorence to fiftyone dataset
- Add Captioning
- Add Florence-2 embeddings and visualize it on 2D
- [] predictions/labels from florence-2 to yolo format
- [] Quantization to int8 and make it avaible on Huggingface models
- [] Add segmentation label using EfficientSAM or FastSAM, OpenVINO format
Source Material and useful links
About
The Power of Florence-2 with OpenVINO & FiftyOne: Real-World Applications in Image Analysis