YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.
YOLO-V5 : Git Repo - https://github.com/ultralytics/yolov5
Used a dataset which is already annotated and with two class that is Electric Car and Electric Bus. Got the dataset from kaggle. Link - https://www.kaggle.com/positivepc/object-detection
We can do the data annotation from RoboloFlow as per our Requirement. RoboFlow provide many things like data annotation, data preparation, data augmentation, file converter etc.
Check it - https://roboflow.com/
Here, we will use Google Drive and Google Colab to train the model.
MODEL There are several models in YOLO-V5, a glimpse into that.
For detail information go through all the .ipynb files for more training approach.
File or folder (weights, training and testing results etc.) structure.
DLM - this folder has contain weights and result for first .ipynb training.
DLM_01 - this folder has contain weights and result for second .ipynb training.