Skip to content

missionfission/FPGA-CNN-Acceleration

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
FPGA
FPGA
 
 
prototxt models
prototxt models
 
 
v2
v2
 
 
vivado_include
vivado_include
 
 
README.md
README.md
 
 
cpu_top.cpp
cpu_top.cpp
 
 
cpu_top.hpp
cpu_top.hpp
 
 
fpga_top.cpp
fpga_top.cpp
 
 
fpga_top.hpp
fpga_top.hpp
 
 
gpool_cache.cpp
gpool_cache.cpp
 
 
gpool_cache.hpp
gpool_cache.hpp
 
 
image_cache.cpp
image_cache.cpp
 
 
image_cache.hpp
image_cache.hpp
 
 
indata.bin
indata.bin
 
 
input.bin
input.bin
 
 
list_cores.txt
list_cores.txt
 
 
maxpool.cpp
maxpool.cpp
 
 
maxpool.hpp
maxpool.hpp
 
 
memory_controller.cpp
memory_controller.cpp
 
 
memory_controller.hpp
memory_controller.hpp
 
 
netconfig.cpp
netconfig.cpp
 
 
netconfig.hpp
netconfig.hpp
 
 
network.cpp
network.cpp
 
 
network.hpp
network.hpp
 
 
output_cache.cpp
output_cache.cpp
 
 
output_cache.hpp
output_cache.hpp
 
 
processing_element.cpp
processing_element.cpp
 
 
processing_element.hpp
processing_element.hpp
 
 
solution2_fpga_top_csynth.html
solution2_fpga_top_csynth.html
 
 
unittests.cpp
unittests.cpp
 
 
unittests.hpp
unittests.hpp
 
 
weights.bin
weights.bin
 
 
weights_cache.cpp
weights_cache.cpp
 
 
weights_cache.hpp
weights_cache.hpp
 
 
weights_malaria.bin
weights_malaria.bin
 
 

Repository files navigation

High Level Synthesis for FPGA-Acceleration of CNNs using Vivado HLS

Layers Supported

1. Convolution kernel size : 3x3 and 1x1

2. Global Pool

3. Concat Layers

Activations : ReLu and Softmax

TODO

1. Maxpool Layer

2. Dense Layer

3. Deconvolution Layer

The convolution computation isdone by using MAC2d units.

About

No description, website, or topics provided.

Resources

Readme
Activity

Stars

6 stars

Watchers

1 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages