This repository will have ally my code using AI vistion capabilities using opencv
If you are looking for my AI RAG implimentation using Llama2 and PDF ducment loading look at my project here https://github.com/antonjan/local_ai_with_pdf
pip3 install -r requirements.txt
pip3 install opencv-python
pip install opencv-python
The COCO dataset contains over 330,000 images with more than 2.5 million object instances labeled across 80 categories.
The dataset can be downloaded from the official COCO website (http://cocodataset.org/#download).
python3 ./car_detector.py
python3 ./face_detection.py
You should now have a file face_detected.png
open face_detected.png to see the face that was detected
Converting pdfs with images embedid in them to text by using OCR then the brogram will create the text output
here is the link to the code [PDF image to Text converter](https://pages.github.com/