Low-precision integer arithmetic is a necessary ingredient for enabling Deep Learning inference on tiny and resource-constrained IoT edge devices. This brief presents CMix-NN, a flexible open-sourceCMix-NN is available at https://github.com/EEESlab/CMix-NN. mixed low-precision (independent tensors quantization of weight and activations at 8, 4, 2 bits) inference library for low bitwidth Quantized Networks. CMix-NN efficiently supports both Per-Layer and Per-Channel quantization strategies of weights and activations. Thanks to CMix-NN, we deploy on an STM32H7 microcontroller a set of Mobilenet family networks with the largest input resolutions ( $224\times 224$ ) and higher accuracies (up to 68% Top1) when compressed with a mixed low precision technique, achieving up to +8% accuracy improvement concerning any other published solution for MCU devices.

中文翻译：

---

CMix-NN：用于内存受限边缘设备的混合低精度 CNN 库

低精度整数算法是在微小且资源受限的物联网边缘设备上启用深度学习推理的必要因素。本简介介绍了 CMix-NN，这是一个灵活的开源 CMix-NN，可从 https://github.com/EEESlab/CMix-NN 获得。用于低位宽量化网络的混合低精度（权重和激活的独立张量量化 8、4、2 位）推理库。Cmix-NN 有效地支持权重和激活的每层和每通道量化策略。多亏了 CMix-NN，我们在 STM32H7 微控制器上部署了一组 Mobilenet 系列网络，当使用混合低精度技术压缩时，具有最大输入分辨率（$224\times 224$）和更高的精度（高达 68% Top1），