Can I read Auto-Tuning DNN Quantization Framework on EtoBox?
Auto-Tuning DNN Quantization Framework by Viet Nguyen is a document available to read on EtoBox.
What is Auto-Tuning DNN Quantization Framework about?
The document presents an auto-tuning neural network quantization framework designed for collaborative inference between cloud and edge devices, addressing the challenges of data transmission overhead and privacy concerns in mobile AI applications. By analyzing DNN layer characteristics, the framework optimizes network partitioning and quantization, allowing for reduced storage on mobile devices with minimal accuracy loss. Experimental results demonstrate the framework
- Author
- Viet Nguyen
- Language
- EN