idanba's picture
Update README.md
9b25ea4 verified
---
library_name: keras
license: agpl-3.0
datasets:
- detection-datasets/coco
---
# Model card for keras_yolov8_480x480_pp
A keras implementation of YOLOv8n object-detection model, based on [Ultralytics](https://github.com/ultralytics/ultralytics).
The model weights were taken from [yolov8n.pt - v0.0.0](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt).
This YOLOv8n Keras implementation includes an additional post-processing layer (non-maximum suppression). For further insights into the model's implementation details, please refer to [MCT Model Garden - yolov8](https://github.com/sony/model_optimization/tree/main/tutorials/mct_model_garden/models_keras/yolov8)
The input resolution was set to 480x480.