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 create -n cvd-maker python=3.11 -y
conda activate cvd-maker
pip install -r requirements.txt
- 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