最近、性能良いとうわさのYolov3が出てきたので、ちょっと試したいと思って試してみた。
ちょっと。。。以下のサイトにたくさん事例があり、ほとんど同じようなことが書いてあるので、簡単なんだろうと思っていた。
【参考】
darknetでYOLOv3を動かしてみた。
YOLOv2(Keras / TensorFlow)でディープラーニングによる画像の物体検出を行う
【Darknet】リアルタイムオブジェクト認識 YOLOをTensorflowで試す
###環境作成するよ。。。
darknetでYOLOv3を動かしてみた。の記事のとおり、話を進める。
Ubuntuのようなので、以下を参考にWindows10（1060-3GB）にUbuntuを入れる。
Ubuntu がマイクロソフト ストアにやってきた
これはなんとなく再起動して動いた。
そして、「深層学習フレームワークdarknetをインストールする。」
git clone https://github.com/pjreddie/darknet.git
cd darknet
たぶん、ここはハマらずdarknetという一連のディレクトリができると思う。。。
※ウワンはここでもハマった様子①のとおり、ハマりましたが。。。
そして、
「Makefileを修正し、GPUとOpenCVをOnにし、makeする。」
これは、viでMakefileを以下のように編集して、その後makeするという意味です。
※当たり前だけど、。。。少し、ハマりました
vi Makefile
viが無い。。。ということで、ここは単に編集すればいいので、jupyter notebookからMakefileを呼び出して以下の部分を編集しました。
変更前(Makefile)
GPU=0
CUDNN=0
OPENCV=0
OPENMP=0
DEBUG=0
変更後(Makefile)
GPU=1
CUDNN=0
OPENCV=1
OPENMP=0
DEBUG=0
そして、問題はmake。。。
※ここはハマった様子②のようにすごくハマりました
make
無いです。。。
$ sudo apt install make
で入りましたが、gccが必要です。
$ sudo apt-get install gcc
そして、「YOLOv3の学習済みファイルをダウンロードする」
wget https://pjreddie.com/media/files/yolov3.weights
※ここでも実はハマってました。yolo.weightsというファイルもあって、こっちをダウンロードして以下実施するとweightsの読み込みエラーが出てthe endです
ということで、いよいよ「YOLOv3をテストする」
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
※以下のyolov3のネットワーク構造と実行結果の通り、動きました
dog: 99%
truck: 92%
bicycle: 99%
そして、以下yolov2の結果です。
yolov2.weightsをダウンロードして、
$ wget https://pjreddie.com/media/files/yolov2.weights
実行します。
$ ./darknet detect cfg/yolov2.cfg yolov2.weights data/dog.jpg
両者で精度はかなり異なりますね。。。
dog: 81%
truck: 74%
bicycle: 83%
めでたしめでたし。。。ですが、。。。
これは、C版です。。。ということで、python版動くかな？？
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet/python$ python3 darknet.py cfg/yolov3.cfg yolov3.weights data/dog.jpg
Traceback (most recent call last):
File "darknet.py", line 48, in <module>
lib = CDLL("libdarknet.so", RTLD_GLOBAL)
File "/usr/lib/python3.5/ctypes/__init__.py", line 347, in __init__
self._handle = _dlopen(self._name, mode)
OSError: libdarknet.so: cannot open shared object file: No such file or directory
"libdarknet.so"のファイルが見つかりません。。。
ここでも実はかなりハマりましたが、端折ります。。。
ということで、。。。以下の記事に乗り換えました。
【Darknet】リアルタイムオブジェクト認識 YOLOをTensorflowで試す
これ。。。簡単に動くといいなぁ～
今日はここまでにいたしとうござります^^;
###まとめ
・今回は、噂のYolov3を動かしてみた
・環境構築にすごくハマった
・結果はYolov3はYolov2に比較するとネットワーク構造もディープになって、検出精度も格段に上がっていた
・Python版は動かなかった
以下種々ハマったところなど、参考です。
####ハマった様子①darknetの環境作るまで
前半、YOLOv2(Keras / TensorFlow)でディープラーニングによる画像の物体検出を行うで環境構築を始めたので、その状況が入っています。。。
Microsoft Windows [Version 10.0.16299.371]
(c) 2017 Microsoft Corporation. All rights reserved.
C:\Users\user>sudo apt install git
'sudo' is not recognized as an internal or external command,
operable program or batch file.
C:\Users\user>bash
Windows Subsystem for Linux には、インストールされたディストリビューションがありません。
ディストリビューションをインストールするには、次の Windows ストアを訪問してください:
https://aka.ms/wslstore
続行するには何かキーを押してください...
C:\Users\user>pip install numpy h5py pillow
Requirement already satisfied: numpy in c:\users\user\anaconda3\lib\site-packages
Requirement already satisfied: h5py in c:\users\user\anaconda3\lib\site-packages
Requirement already satisfied: pillow in c:\users\user\anaconda3\lib\site-packages
Requirement already satisfied: six in c:\users\user\anaconda3\lib\site-packages (from h5py)
You are using pip version 9.0.3, however version 10.0.1 is available.
You should consider upgrading via the 'python -m pip install --upgrade pip' command.
C:\Users\user>bash
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ pip install numpy h5py pillow
The program 'pip' is currently not installed. You can install it by typing:
sudo apt install python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ sudo apt install python-pip
[sudo] password for MuAuan:
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Unable to locate package python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ pip install numpy he5py pillow
The program 'pip' is currently not installed. You can install it by typing:
sudo apt install python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ sudo apt install python-pip
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Unable to locate package python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ pip install keras
The program 'pip' is currently not installed. You can install it by typing:
sudo apt install python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ sudo apt install python-pip
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Unable to locate package python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ wget http://pjreddie.com./media/files/yolo.weights
--2018-04-27 22:36:35-- http://pjreddie.com./media/files/yolo.weights
Resolving pjreddie.com. (pjreddie.com.)... 128.208.3.39
Connecting to pjreddie.com. (pjreddie.com.)|128.208.3.39|:80... connected.
HTTP request sent, awaiting response... 301 Moved Permanently
Location: https://pjreddie.com/media/files/yolo.weights [following]
--2018-04-27 22:36:40-- https://pjreddie.com/media/files/yolo.weights
Resolving pjreddie.com (pjreddie.com)... 128.208.3.39
Connecting to pjreddie.com (pjreddie.com)|128.208.3.39|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 203934260 (194M) [application/octet-stream]
Saving to: ‘yolo.weights’
yolo.weights 100%[=================================================>] 194.49M 5.22MB/s in 43s
2018-04-27 22:37:24 (4.53 MB/s) - ‘yolo.weights’ saved [203934260/203934260]
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ wget https://raw.githubusercontent.com/pjreddie/darknet/master/:cfg/yolo.cfg
--2018-04-27 22:38:20-- https://raw.githubusercontent.com/pjreddie/darknet/master/:cfg/yolo.cfg
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.72.133
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.72.133|:443... connected.
HTTP request sent, awaiting response... 404 Not Found
2018-04-27 22:38:26 ERROR 404: Not Found.
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ wget https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolo.cfg
--2018-04-27 22:38:41-- https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolo.cfg
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.72.133
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.72.133|:443... connected.
HTTP request sent, awaiting response... 404 Not Found
2018-04-27 22:38:52 ERROR 404: Not Found.
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ wget https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolo.cfg
--2018-04-27 22:40:38-- https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolo.cfg
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.72.133
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.72.133|:443... connected.
HTTP request sent, awaiting response... 404 Not Found
2018-04-27 22:40:43 ERROR 404: Not Found.
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ ./yad2k.py yolo.cfg yolo.weights model_data/yolo.h5
-bash: ./yad2k.py: No such file or directory
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ logout
C:\Users\user>cd ./yad2k
C:\Users\user\yad2k>python keras_yolo.py
Using TensorFlow backend.
Traceback (most recent call last):
File "keras_yolo.py", line 11, in <module>
from ..utils import compose
SystemError: Parent module '' not loaded, cannot perform relative import
C:\Users\user\yad2k>python test_yolo.py
Using TensorFlow backend.
Traceback (most recent call last):
File "test_yolo.py", line 14, in <module>
from yad2k.models.keras_yolo import yolo_eval, yolo_head
File "C:\Users\user\yad2k\yad2k.py", line 25, in <module>
from yad2k.models.keras_yolo import (space_to_depth_x2,
ImportError: No module named 'yad2k.models'; 'yad2k' is not a package
C:\Users\user\yad2k>pip install yad2k.models
Collecting yad2k.models
Could not find a version that satisfies the requirement yad2k.models (from versions: )
/pip-10.0.1-py2.py3-none-any.whl (1.3MB)
100% |################################| 1.3MB 1.1MB/s
Installing collected packages: pip
Found existing installation: pip 9.0.3
Uninstalling pip-9.0.3:
Successfully uninstalled pip-9.0.3
Successfully installed pip-10.0.1
C:\Users\user\yad2k>pip install yad2k.models
Collecting yad2k.models
Could not find a version that satisfies the requirement yad2k.models (from versions: )
No matching distribution found for yad2k.models
C:\Users\user\yad2k>cd ../
C:\Users\user>git clone https://github.com/pjreddie/darknet
'git' is not recognized as an internal or external command,
operable program or batch file.
C:\Users\user>git clone https://github.com/pjreddie/darknet
'git' is not recognized as an internal or external command,
operable program or batch file.
C:\Users\user>bash
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ git clone https://github.com/pjreddie/darknet
Cloning into 'darknet'...
remote: Counting objects: 5756, done.
remote: Total 5756 (delta 0), reused 0 (delta 0), pack-reused 5756
Receiving objects: 100% (5756/5756), 6.00 MiB | 2.62 MiB/s, done.
Resolving deltas: 100% (3854/3854), done.
Checking connectivity... done.
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user$ cd ./darknet
####ハマった様子②make編
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ make
The program 'make' can be found in the following packages:
* make
* make-guile
Try: sudo apt install <selected package>
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt install make
[sudo] password for MuAuan:
Reading package lists... Done
Building dependency tree
Reading state information... Done
The following package was automatically installed and is no longer required:
libfreetype6
Use 'sudo apt autoremove' to remove it.
Suggested packages:
make-doc
The following NEW packages will be installed:
make
0 upgraded, 1 newly installed, 0 to remove and 0 not upgraded.
Need to get 151 kB of archives.
After this operation, 365 kB of additional disk space will be used.
Get:1 http://archive.ubuntu.com/ubuntu xenial/main amd64 make amd64 4.1-6 [151 kB]
Fetched 151 kB in 9s (15.8 kB/s)
Selecting previously unselected package make.
(Reading database ... 25532 files and directories currently installed.)
Preparing to unpack .../archives/make_4.1-6_amd64.deb ...
Unpacking make (4.1-6) ...
Processing triggers for man-db (2.7.5-1) ...
Setting up make (4.1-6) ...
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ make
mkdir -p obj
mkdir -p results
gcc -Iinclude/ -Isrc/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -Ofast -c ./src/gemm.c -o obj/gemm.o
make: gcc: Command not found
Makefile:85: recipe for target 'obj/gemm.o' failed
make: *** [obj/gemm.o] Error 127
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$
なんとなく、makeがインストールできたみたいなので。。。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ make Makefile
make: Nothing to be done for 'Makefile'.
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ make
gcc -Iinclude/ -Isrc/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -Ofast -c ./src/gemm.c -o obj/gemm.o
make: gcc: Command not found
Makefile:85: recipe for target 'obj/gemm.o' failed
make: *** [obj/gemm.o] Error 127
gccが無いと怒られました。。。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ pip install gcc
The program 'pip' is currently not installed. You can install it by typing:
sudo apt install python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt install python-pip
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Unable to locate package python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt install python-pip
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Unable to locate package python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt install gcc
あれ、gccが入りません。。。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt install gcc
Reading package lists... Done
Building dependency tree
Reading state information... Done
The following package was automatically installed and is no longer required:
libfreetype6
Use 'sudo apt autoremove' to remove it.
The following additional packages will be installed:
binutils cpp cpp-5 gcc-5 libasan2 libatomic1 libc-dev-bin libc6-dev libcc1-0 libcilkrts5 libgcc-5-dev libgomp1
libisl15 libitm1 liblsan0 libmpc3 libmpx0 libquadmath0 libtsan0 libubsan0 linux-libc-dev manpages-dev
Suggested packages:
。。。
入ったかな？？
でも、
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ make
gcc -Iinclude/ -Isrc/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -Ofast -c ./src/gemm.c -o obj/gemm.o
make: gcc: Command not found
Makefile:85: recipe for target 'obj/gemm.o' failed
make: *** [obj/gemm.o] Error 127
変わってないじゃない。。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ pip install gcc
The program 'pip' is currently not installed. You can install it by typing:
sudo apt install python-pip
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ python
The program 'python' can be found in the following packages:
* python-minimal
* python3
Try: sudo apt install <selected package>
つまり、bash側にはpythonも入ってなかった？？
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt install python
Reading package lists... Done
Building dependency tree
Reading state information... Done
。。。
minimal python2.7 python2.7-minimal
0 upgraded, 7 newly installed, 0 to remove and 0 not upgraded.
Need to get 3,915 kB of archives.
After this operation, 16.6 MB of additional disk space will be used.
Do you want to continue? [Y/n] y
python2.7が入りましたが、。。
E: Unable to fetch some archives, maybe run apt-get update or try with --fix-missing?
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ run apt-get update
No command 'run' found, did you mean:
いや、入らなかったようです。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt-get update python
E: The update command takes no arguments
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt-get update
Get:1 http://security.ubuntu.com/ubuntu xenial-security InRelease [107 kB]
Hit:2 http://archive.ubuntu.com/ubuntu xenial InRelease
Get:3 http://archive.ubuntu.com/ubuntu xenial-updates InRelease [109 kB]
Get:4 http://security.ubuntu.com/ubuntu xenial-security/main amd64 Packages [481 kB]
Get:5 http://archive.ubuntu.com/ubuntu xenial-backports InRelease [107 kB]
Get:6 http://archive.ubuntu.com/ubuntu xenial/universe amd64 Packages [7,532 kB]
。。。
なんとなく、ubuntuのアップデートできました。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ make
gcc -Iinclude/ -Isrc/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -Ofast -c ./src/gemm.c -o obj/gemm.o
make: gcc: Command not found
Makefile:85: recipe for target 'obj/gemm.o' failed
make: *** [obj/gemm.o] Error 127
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt-get install make
Reading package lists... Done
Building dependency tree
Reading state information... Done
make is already the newest version (4.1-6).
The following package was automatically installed and is no longer required:
libfreetype6
Use 'sudo apt autoremove' to remove it.
0 upgraded, 0 newly installed, 0 to remove and 134 not upgraded.
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt-get install python3
make入りません。。。いまどきpython3だよなぁ～
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt-get install python3
Reading package lists... Done
Building dependency tree
Reading state information... Done
python3 is already the newest version (3.5.1-3).
もうinstall済でした。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ make
gcc -Iinclude/ -Isrc/ -Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC -Ofast -c ./src/gemm.c -o obj/gemm.o
make: gcc: Command not found
Makefile:85: recipe for target 'obj/gemm.o' failed
make: *** [obj/gemm.o] Error 127
makeは動きません。。。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ sudo apt-get install gcc
Reading package lists... Done
Building dependency tree
Reading state information... Done
The following package was automatically installed and is no longer required:
libfreetype6
Use 'sudo apt autoremove' to remove it.
The following additional packages will be installed:
。。。
Setting up manpages-dev (4.04-2) ...
Processing triggers for libc-bin (2.23-0ubuntu9) ...
なんとなく、gccが入りました。。。なんで入ったのかな？？
$ pip install gcc
$ sudo apt install gcc
$ sudo apt install gcc
$ sudo apt-get install gcc
つまり、コマンドが$ sudo apt-get install gccでよかったんだろう
因みに、makeのインストールは以下のコマンドでやってました^^;
$ sudo apt install make
####yolov3のネットワーク構造と実行結果
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ ./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
layer filters size input output
0 conv 32 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 32 0.299 BFLOPs
1 conv 64 3 x 3 / 2 416 x 416 x 32 -> 208 x 208 x 64 1.595 BFLOPs
2 conv 32 1 x 1 / 1 208 x 208 x 64 -> 208 x 208 x 32 0.177 BFLOPs
3 conv 64 3 x 3 / 1 208 x 208 x 32 -> 208 x 208 x 64 1.595 BFLOPs
4 res 1 208 x 208 x 64 -> 208 x 208 x 64
5 conv 128 3 x 3 / 2 208 x 208 x 64 -> 104 x 104 x 128 1.595 BFLOPs
6 conv 64 1 x 1 / 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BFLOPs
7 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
8 res 5 104 x 104 x 128 -> 104 x 104 x 128
9 conv 64 1 x 1 / 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BFLOPs
10 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
11 res 8 104 x 104 x 128 -> 104 x 104 x 128
12 conv 256 3 x 3 / 2 104 x 104 x 128 -> 52 x 52 x 256 1.595 BFLOPs
13 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
14 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
15 res 12 52 x 52 x 256 -> 52 x 52 x 256
16 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
17 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
18 res 15 52 x 52 x 256 -> 52 x 52 x 256
19 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
20 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
21 res 18 52 x 52 x 256 -> 52 x 52 x 256
22 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
23 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
24 res 21 52 x 52 x 256 -> 52 x 52 x 256
25 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
26 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
27 res 24 52 x 52 x 256 -> 52 x 52 x 256
28 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
29 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
30 res 27 52 x 52 x 256 -> 52 x 52 x 256
31 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
32 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
33 res 30 52 x 52 x 256 -> 52 x 52 x 256
34 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
35 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
36 res 33 52 x 52 x 256 -> 52 x 52 x 256
37 conv 512 3 x 3 / 2 52 x 52 x 256 -> 26 x 26 x 512 1.595 BFLOPs
38 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
39 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
40 res 37 26 x 26 x 512 -> 26 x 26 x 512
41 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
42 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
43 res 40 26 x 26 x 512 -> 26 x 26 x 512
44 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
45 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
46 res 43 26 x 26 x 512 -> 26 x 26 x 512
47 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
48 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
49 res 46 26 x 26 x 512 -> 26 x 26 x 512
50 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
51 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
52 res 49 26 x 26 x 512 -> 26 x 26 x 512
53 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
54 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
55 res 52 26 x 26 x 512 -> 26 x 26 x 512
56 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
57 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
58 res 55 26 x 26 x 512 -> 26 x 26 x 512
59 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
60 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
61 res 58 26 x 26 x 512 -> 26 x 26 x 512
62 conv 1024 3 x 3 / 2 26 x 26 x 512 -> 13 x 13 x1024 1.595 BFLOPs
63 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
64 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
65 res 62 13 x 13 x1024 -> 13 x 13 x1024
66 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
67 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
68 res 65 13 x 13 x1024 -> 13 x 13 x1024
69 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
70 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
71 res 68 13 x 13 x1024 -> 13 x 13 x1024
72 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
73 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
74 res 71 13 x 13 x1024 -> 13 x 13 x1024
75 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
76 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
77 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
78 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
79 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
80 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
81 conv 255 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 255 0.088 BFLOPs
82 detection
83 route 79
84 conv 256 1 x 1 / 1 13 x 13 x 512 -> 13 x 13 x 256 0.044 BFLOPs
85 upsample 2x 13 x 13 x 256 -> 26 x 26 x 256
86 route 85 61
87 conv 256 1 x 1 / 1 26 x 26 x 768 -> 26 x 26 x 256 0.266 BFLOPs
88 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
89 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
90 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
91 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
92 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
93 conv 255 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 255 0.177 BFLOPs
94 detection
95 route 91
96 conv 128 1 x 1 / 1 26 x 26 x 256 -> 26 x 26 x 128 0.044 BFLOPs
97 upsample 2x 26 x 26 x 128 -> 52 x 52 x 128
98 route 97 36
99 conv 128 1 x 1 / 1 52 x 52 x 384 -> 52 x 52 x 128 0.266 BFLOPs
100 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
101 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
102 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
103 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
104 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
105 conv 255 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 255 0.353 BFLOPs
106 detection
Loading weights from yolov3.weights...Done!
data/dog.jpg: Predicted in 17.953083 seconds.
dog: 99%
truck: 92%
bicycle: 99%
Yolov2のネットワーク構造と実行結果です。
MuAuan@DESKTOP-S5LF5OV:/mnt/c/Users/user/darknet$ ./darknet detect cfg/yolov2.cfg yolov2.weights data/dog.jpg
layer filters size input output
0 conv 32 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 32 0.299 BFLOPs
1 max 2 x 2 / 2 416 x 416 x 32 -> 208 x 208 x 32
2 conv 64 3 x 3 / 1 208 x 208 x 32 -> 208 x 208 x 64 1.595 BFLOPs
3 max 2 x 2 / 2 208 x 208 x 64 -> 104 x 104 x 64
4 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
5 conv 64 1 x 1 / 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BFLOPs
6 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
7 max 2 x 2 / 2 104 x 104 x 128 -> 52 x 52 x 128
8 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
9 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
10 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
11 max 2 x 2 / 2 52 x 52 x 256 -> 26 x 26 x 256
12 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
13 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
14 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
15 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
16 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
17 max 2 x 2 / 2 26 x 26 x 512 -> 13 x 13 x 512
18 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
19 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
20 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
21 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
22 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
23 conv 1024 3 x 3 / 1 13 x 13 x1024 -> 13 x 13 x1024 3.190 BFLOPs
24 conv 1024 3 x 3 / 1 13 x 13 x1024 -> 13 x 13 x1024 3.190 BFLOPs
25 route 16
26 conv 64 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 64 0.044 BFLOPs
27 reorg / 2 26 x 26 x 64 -> 13 x 13 x 256
28 route 27 24
29 conv 1024 3 x 3 / 1 13 x 13 x1280 -> 13 x 13 x1024 3.987 BFLOPs
30 conv 425 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 425 0.147 BFLOPs
31 detection
mask_scale: Using default '1.000000'
Loading weights from yolov2.weights...Done!
data/dog.jpg: Predicted in 8.946540 seconds.
dog: 81%
truck: 74%
bicycle: 83%