|
|
---
|
|
|
tags:
|
|
|
- yolov5
|
|
|
- yolo
|
|
|
- vision
|
|
|
- object-detection
|
|
|
- pytorch
|
|
|
license: mit
|
|
|
base_model:
|
|
|
- Ultralytics/YOLOv5
|
|
|
---
|
|
|
|
|
|
# Model Card for BillboardAdvertDetectionYOLOV5
|
|
|
<img src="img/image_collage.png" />
|
|
|
|
|
|
|
|
|
Computer vision object detection model to detect billboard advertising.
|
|
|
|
|
|
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
|
|
|
|
|
|
## Model Details
|
|
|
|
|
|
### Model Description
|
|
|
|
|
|
As the adoption of augmented reality (AR) headsets proliferates, the ways in which consumers will experience content will change considerably, which means a radical shift away from the current state of billboard advertising.
|
|
|
|
|
|
This is to show how to create a computer vision model for applications such as ad-blocking in everyday life.
|
|
|
|
|
|
- **Developed by:** Lewis James
|
|
|
- **Model type:** Computer Vision
|
|
|
- **Transfer learning from model YOLOv5:** [Hugging Face](https://huggingface.co/Ultralytics/YOLOv5)
|
|
|
|
|
|
### Model Sources
|
|
|
|
|
|
- **Repository:** [GitHub](https://github.com/lewisExternal/BillboardAdvertDetection)
|
|
|
- **Blog:** [Medium](https://medium.com/@ljamesdatascience/billboard-advert-detection-using-transfer-learning-with-yolo-9405d6aeb943)
|
|
|
|
|
|
### Results
|
|
|
| Class | Images | Instances | P | R | mAP50 |
|
|
|
| :---: | :----: | :-------: | :---: | :---: | :---: |
|
|
|
| all | 71 | 99 | 0.805 | 0.828 | 0.818 |
|
|
|
|
|
|
|
|
|
## Model Card Contact
|
|
|
|
|
|
Connect with me via [LinkedIn](https://www.linkedin.com/in/lewisjames1/) |
