AccANN

A compiler from AI model to RTL (Verilog) accelerator in FPGA hardware with auto design space exploration for AdderNet.

<div align=center><img src="./img/figure/figure1.png"></div> Fig 1. Visualization of features in AdderNets and CNNs. ^[1] <br> <div align=center><img src="./img/figure/figure2.png"></div> Fig 2. Visualization of features in different neural networks on MNIST dataset. ^[3]

🍮 Community

• Github <a href="https://github.com/Charmve/AccANN/discussions" target="_blank">discussions 💬</a> or <a href="https://github.com/Charmve/AccANN/issues" target="_blank">issues 💭</a>

• QQ Group: 697948168 (password：AccANN)

• Email: yidazhang#gmail.com

🔗 Related Works

[1] AdderNet: Do We Really Need Multiplications in Deep Learning? Hanting Chen, Yunhe Wang, Chunjing Xu, Boxin Shi, Chao Xu, Qi Tian, Chang Xu. CVPR, 2020. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[2] AdderSR: Towards Energy Efficient Image Super-Resolution. Dehua Song, Yunhe Wang, Hanting Chen, Chang Xu, Chunjing Xu, Dacheng Tao. Arxiv, 2020. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[3] ShiftAddNet: A Hardware-Inspired Deep Network. Haoran You, Xiaohan Chen, Yongan Zhang, Chaojian Li, Sicheng Li, Zihao Liu, Zhangyang Wang, Yingyan Lin. NeurIPS, 2020. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[4] Kernel Based Progressive Distillation for Adder Neural Networks. Yixing Xu, Chang Xu, Xinghao Chen, Wei Zhang, Chunjing XU, Yunhe Wang. NeurIPS, 2020. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[5] GhostNet: More Features from Cheap Operations [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[6] MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[7] VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing. Qian Zhang, Jianjun Li, Meng Yao. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[8] And the bit goes down: Revisiting the quantization of neural networks (ICLR 2020). Pierre Stock, Armand Joulin, Remi Gribonval. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[9] DNNBuilder: an Automated Tool for Building High-Performance DNN Hardware Accelerators for FPGAs [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]

[10] AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence. Yunhe Wang, Mingqiang Huang, Kai Han, et.al. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/> code]

[11] PipeCNN: An OpenCL-Based Open-Source FPGA Accelerator for Convolution Neural Networks. FPT 2017. Dong Wang, Ke Xu and Diankun Jiang. [📑paper | <img src="https://img.icons8.com/material-sharp/24/000000/github.png" alt="Github" width="22px"/>code]