This project will detect cars in one image using the YOLO model. Many of the ideas in this notebook are described in the two YOLO papers: Redmon et al., 2016 (https://arxiv.org/abs/1506.02640) and Redmon and Farhadi, 2016 (https://arxiv.org/abs/1612.08242).
Because the YOLO model is very computationally expensive to train, I will load pre-trained weights to use.
In this project I used the dataset from drive.ai
Two main work have done：
- Use object detection on a car detection dataset
- Deal with bounding boxes
the architecture as follows:
- TensorFlow
- python 3 or later
- python packages : Keras, numpy, scipy, pandas, PIL
- download the weights yolo.h5 on the website
python cardetection.py
the resuals as follows:
