BitNetMCU：在CH32V003 RISC-V MCU上，实现MNIST手写数字识别

txc

设计简介

BitNetMCU 是一个专注于低位量化神经网络训练和推理的项目，专门设计用于在 CH32V003 等低端微控制器上高效运行。量化感知训练 (QAT) 和模型结构和推理代码的微调允许在 16x16 MNIST 数据集上实现超过 99% 的测试准确率，而无需使用乘法指令，并且仅需 2kb RAM 和 16kb Flash。

训练管道基于 PyTorch，可以在任何地方运行。推理引擎以 Ansi-C 实现，可以轻松移植到任何微控制器。

BitNetMCU is a project focused on the training and inference of low-bit quantized neural networks, specifically designed to run efficiently on low-end microcontrollers like the CH32V003. Quantization aware training (QAT) and fine-tuning of model structure and inference code allowed surpassing 99% Test accuracy on a 16x16 MNIST dataset without using multiplication instructions and in only 2kb of RAM and 16kb of Flash.

The training pipeline is based on PyTorch and should run anywhere. The inference engine is implemented in Ansi-C and can be easily ported to any Microcontroller.

通过百度网盘分享的文件：b1ca9ed6d48d0674f8802e1936a5ab7f869...

链接：https://pan.baidu.com/s/1ToMLTC6skD1UttK8fw4H_A?pwd=59wm

提取码：59wm