nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
286 Commits
5 Branches
354 MB
1 Download
 
 
 
 
 
 
Tree: 6ea09ebf2c
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '6ea09ebf2c'
${ noResults }
ncnn/benchmark
nihui a335ae840f
add mobilenet v2 result 		8 years ago
..
CMakeLists.txt benchmark routine :) 8 years ago
README.md add mobilenet v2 result 8 years ago
alexnet.param benchmark routine :) 8 years ago
benchncnn.cpp add mobilenet_v2 benchmark 8 years ago
googlenet.param benchmark routine :) 8 years ago
mobilenet.param benchmark routine :) 8 years ago
mobilenet_ssd.param benchmark routine :) 8 years ago
mobilenet_v2.param add mobilenet_v2 benchmark 8 years ago
resnet18.param benchmark routine :) 8 years ago
shufflenet.param benchmark routine :) 8 years ago
squeezenet.param benchmark routine :) 8 years ago
squeezenet_ssd.param benchmark routine :) 8 years ago
vgg16.param benchmark routine :) 8 years ago

README.md

benchncnn can be used to test neural network inference performance

Only the network definition files (ncnn param) are required.

The large model binary files (ncnn bin) are not loaded but generated randomly for speed test.

More model networks may be added later.

Usage

# copy all param files to the current directory
./benchncnn [loop count] [num threads] [powersave]

Typical output (executed in android adb shell)

HM2014812:/data/local/tmp # ./benchncnn 8 4 0
loop_count = 8
num_threads = 4
powersave = 0
      squeezenet  min =   98.27  max =  118.75  avg =  105.22
       mobilenet  min =  168.36  max =  178.58  avg =  174.52
    mobilenet_v2  min =  192.38  max =  210.21  avg =  201.79
      shufflenet  min =   66.07  max =   74.64  avg =   70.58
       googlenet  min =  327.53  max =  344.18  avg =  334.36
        resnet18  min =  465.24  max =  479.58  avg =  470.86
         alexnet  min =  380.57  max =  406.64  avg =  397.66
           vgg16  min = 2341.65  max = 2475.65  avg = 2402.14
  squeezenet-ssd  min =  187.64  max =  283.71  avg =  204.29
   mobilenet-ssd  min =  183.96  max =  214.15  avg =  193.30
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

C++ C Python Text Protocol Buffer other