GitHub - jack-willturner/characterising-neural-compression: Code for "Characterising Across Stack Optimisations for Deep Convolutional Neural Networks"

jack-willturner / characterising-neural-compression Public

Notifications You must be signed in to change notification settings
Fork 2
Star 1

Code for "Characterising Across Stack Optimisations for Deep Convolutional Neural Networks"

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
imagenet		imagenet
img		img
include		include
src		src
weights		weights
LICENCE		LICENCE
Makefile		Makefile
MobileNet_CPU_cifar.c		MobileNet_CPU_cifar.c
ResNet-18_CPU_cifar.c		ResNet-18_CPU_cifar.c
VGG-16_CPU_cifar.c		VGG-16_CPU_cifar.c
readme.txt		readme.txt

Repository files navigation


You need to include the weights file (e.g. vgg_plain.txt) file generated from scratchpad/codes/pytorch-cifar/


compile:	gcc -O3 VGG16_CPU_cifar.c -lm -fopenmp -o VGG16_CPU_cifar 

run (example):	./VGG-16_CPU_cifar weights/vgg.txt img/filelist_cf.txt result_cf_conv.txt 1	(only convolutional layers)
run (example):	./VGG-16_CPU_cifar weights/vgg.txt img/filelist_cf.txt result_cf.txt		(all layers)