使用Verilog实现的CNN模块,可以方便的在FPGA项目中使用. Contribute to wxdbb0/CNN-FPGA development by creating an account on GitHub.
https://github.com/Haleski47/RTL-Implementation-of-Two-Layer-CNN https://github.com/Di5h3z/ECE-564-Convolutional-Neural-Network-Accelerator 具有详细设计的两层 CNN 详细的设计文档: https://github.com/Haleski47/RTL-Implementation-of-Two-Layer-CNN/blob/master/report/Apar%20Bansal%20ECE564%20Pro...
Contribute to Husain-Malwat/CNN_FPGA development by creating an account on GitHub.
Last commit date Latest commit diaoenmao Update README.md Mar 31, 2018 f3e53b1·Mar 31, 2018 History 105 Commits Quartus another txt May 9, 2015 16by16_index.xlsx sixteenby sixteen edge detection successful, modelsim simulation fini… ...
代码地址：https://github.com/jonathan93sh/CNNA2年前最后更新相关论文：BJERGE K, SCHOUGAARD J H,...
FPGA. Contribute to MasLiang/CNN-On-FPGA development by creating an account on GitHub.
Zynq/FPGA实现CNN手写数字(0-9)识别. Contribute to CLi321/zynq-fpga-cnn-digital-recognition development by creating an account on GitHub.
代码地址：https://github.com/jonathan93sh/CNNA2年前最后更新相关论文：BJERGE K, SCHOUGAARD J H,...
原创教程,转载请联系作者并注明出处: https://github.com/WalkerLau源码地址: https://github.com/WalkerLau/Accelerating-CNN-with-FPGA最近发现很多小伙伴都想用FPGA加速卷积神经网络运算,而恰好我刚做完的…
地址:https://github.com/nachiket/papaa-opencl 以下图片源自Yufei Ma的Slide。 可以看到cnn算法主要由conv ,pooling,norm等几个部分组成。工作时将image跟weight灌进去,最终得到预测结果。 接下来拿profiler(比如perf)去分析下软件算法,找找热点和性能瓶颈。在cnn里面主要耗时的就是conv二维卷积了。性能瓶颈也主要在...