Abstract: Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance at the ...

Abstract: The huge memory and computing costs of deep neural networks (DNNs) greatly hinder their deployment on resource-constrained devices with high efficiency. Quantization has emerged as an ...

SD.Next Quantization provides full cross-platform quantization to reduce memory usage and increase performance for any device. Triton enables the use of optimized kernels for much better performance.

This is a example to quantize onnx. The input is onnx of float. Quantization is done using onnxruntime. The output is onnx of int8. The default is to quantize using only 2 images, which is less ...