Object and Bounding Box Detection Vision Fine tuning

➡️ Florence 2 Colab Notebook: https://colab.research.google.com/dri...
➡️ Get Life-time Access to the Complete Scripts (and future improvements): https://Trelis.com/ADVANCED-vision/
➡️ One-click fine-tuning and LLM templates: https://github.com/TrelisResearch/one...
➡️ Trelis Newsletter: https://blog.Trelis.com
➡️ Resources/Support/Discord: https://Trelis.com/About
➡️ Thumbnail made with this tutorial:    • Fine Tune Flux Diffusion Models with ...  

VIDEO RESOURCES:
Slides: https://docs.google.com/presentation/...
Chess Dataset: https://huggingface.co/datasets/Treli...
Chess Dataset w/ bounding boxes: https://huggingface.co/datasets/Treli...
Florence paper: https://arxiv.org/pdf/2311.06242
Florence base model on HF: https://huggingface.co/microsoft/Flor...
Thumbnail created using Flux Schnell in this video:    • Fine Tune Flux Diffusion Models with ...  

TIMESTAMPS:
0:00 Object and Bounding Box Detection with Vision Models
0:42 Video Overview
2:15 Florence 2 Architecture
8:03 How bounding boxes and segmentation work
12:55 Inferencing Florence 2 in Google Colab. Bounding boxes and segmentation.
21:17 Annotating a custom dataset with bounding boxes.
28:06 Fine-tuning Florence 2 on bounding boxes. Notebook demo.
41:41 Setting up LoRA adapters
44:12 How to choose learning rate and training arguments
48:40 Fine-tuning results and performance
49:43 Video Resources