Skip to content

Implementation of CNN on ZYNQ FPGA to classify handwritten numbers using MNIST database

Notifications You must be signed in to change notification settings

hitshuangwei/CNN-FPGA

 
 

Repository files navigation

CNN-FPGA

Implementation of CNN on ZYNQ FPGA to classify handwritten numbers using MNIST database

Network Conv2D->Tanh Activation->AvgPool->Conv2D->Tanh Activation->AvgPool->Conv2D->Tanh Activation->Fully Connected Layer->Relu->Fully Connected Layer->Softmax

Further information regarding architecture and number of LUTS can be found in the Hardware Documentation

About

Implementation of CNN on ZYNQ FPGA to classify handwritten numbers using MNIST database

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Verilog 95.9%
  • Python 2.7%
  • HTML 0.6%
  • C++ 0.4%
  • Batchfile 0.2%
  • Tcl 0.1%
  • Pascal 0.1%