gmayday1997 / darknet.CG

Other
31 stars 12 forks source link

Darknet

Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.

This repository is borrowed heavily from https://github.com/pjreddie/darknet and https://github.com/AlexeyAB/darknet

new features

img1

How to use

basicunit darknetcfg

Results

yolov3 volume(MB) FLOPS Map(coco_val5k @0.5) finetuning iters parameters
before pruned 246 65 54.65 500k 1x
pruned @prune_rate=0.3 122 36.3 49.7 80k 0.5x
pruned @prune_rate=0.5 60.5 16 49.2 160k 0.25x
pruned @prune_rate=0.7 31 8.2 46 200k 0.125x
tiny-yolov3(official) 36 5.5 17.3
tiny-yolov3_3l 38 9.1 32
yolov3 volume(MB) FLOPS FPS(352x 288) FPS(960 x 540) FPS(1960 x 1080)
before pruned 246 65 60 57 53
pruned @prune_rate=0.3 122 36.3 82 78 76
pruned @prune_rate=0.5 60.5 16 107 105 97
pruned @prune_rate=0.7 31 8.2 130 123 120
yolov3 volume(MB) FLOPS Inference Time
before pruned 246 65 436ms
pruned @prune_rate=0.3 122 36.3 230ms
pruned @prune_rate=0.5 60.5 16 125ms
pruned @prune_rate=0.7 31 8.2 70ms