license: gpl-3.0
pipeline_tag: object-detection
tags:
- AIoT
- QNN
- LLM
YOLOv6m: Object Detection
YOLOv6 is an advanced real-time object detection model based on the "You Only Look Once" framework. It achieves faster inference speeds while maintaining high accuracy, making it suitable for various edge devices and high-performance servers. YOLOv6 enhances its ability to detect small objects and improves the model's generalization performance by optimizing the network architecture and introducing new loss functions. Additionally, YOLOv6 supports multi-scale training, ensuring excellent performance across different resolutions. It is widely applied in areas such as video surveillance, autonomous driving, and intelligent security.
Source model
- Input shape: 1x3x640x640
- Number of parameters: 33.24M
- Model size: 133.20MB
- Output shape: 1x8400x85
The source model can be found here
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm