【インストール版】Raspberry Piで DeepDreamを動かしてキモイ絵をモリモリ量産 Caffe Deep Learning

【ビルド版】Raspberry Piで DeepDreamを動かしてキモイ絵をモリモリ量産 Caffe Deep Learning Framework

pi@raspberrypi:~/pytorch $ uname -a
Linux raspberrypi 4.14.50-v7+ #1122 SMP Tue Jun 19 12:26:26 BST 2018 armv7l GNU/Linux

# お決まりの sudo apt-get updateで最新状態に更新する
sudo apt-get update

# apt-cache search caffeで caffeの名前のパッケージを検索する
apt-cache search caffe

# apt-get installで caffeの CPU版をインストールする
sudo apt-get -y install caffe-cpu

pi@raspberrypi:~ $ apt-cache search caffe
caffe-cpu - Fast, open framework for Deep Learning (Meta)
caffe-doc - Caffe's doxygen docs and examples
caffe-tools-cpu - Tools for fast, open framework for Deep Learning (CPU_ONLY)
caffeine - prevent the desktop becoming idle in full-screen mode
git-cola - highly caffeinated git GUI
gnome-shell-extension-caffeine - GNOME Shell extension to keep your computer awake
libcaffe-cpu-dev - development files for Caffe (CPU_ONLY)
libcaffe-cpu1 - library of Caffe, deep learning framework (CPU_ONLY)
python3-caffe-cpu - Python3 interface of Caffe (CPU_ONLY)
ttf-aenigma - 465 free TrueType fonts by Brian Kent

pi@raspberrypi:~ $ sudo apt-get -y install caffe-cpu
Reading package lists... Done
Building dependency tree
Reading state information... Done
The following additional packages will be installed:
  caffe-tools-cpu cython3 fonts-lyx ipython3 libaec0 libblosc1
  libboost-python1.62.0 libcaffe-cpu1 libgflags2v5 libgoogle-glog0v5
  libhdf5-100 libjs-jquery-ui libleveldb1v5 liblmdb0 libprotobuf10 libsz2
  libzstd1 python-matplotlib-data python-pexpect python-ptyprocess
  python-tables-data python3-bs4 python3-caffe-cpu python3-cycler
  python3-dateutil python3-decorator python3-gflags python3-h5py
  python3-html5lib python3-ipython python3-ipython-genutils python3-leveldb
  python3-lxml python3-matplotlib python3-networkx python3-nose
  python3-numexpr python3-pandas python3-pandas-lib python3-pexpect
  python3-pickleshare python3-prompt-toolkit python3-protobuf
  python3-ptyprocess python3-pygments python3-pyparsing python3-scipy
  python3-simplegeneric python3-skimage python3-skimage-lib python3-tables
  python3-tables-lib python3-traitlets python3-tz python3-wcwidth
  python3-webencodings python3-yaml ttf-bitstream-vera

# command line interface working
caffe

# python3 interface working
python3 -c 'import caffe; print(caffe.__path__)'

pi@raspberrypi:~ $ caffe --version
caffe version 1.0.0-rc4

pi@raspberrypi:~ $ python3 -c 'import caffe; print(caffe.__path__)'
['/usr/lib/python3/dist-packages/caffe']

pi@raspberrypi:~ $ caffe
caffe: command line brew
usage: caffe <command> <args>

commands:
  train           train or finetune a model
  test            score a model
  device_query    show GPU diagnostic information
  time            benchmark model execution time

  Flags from /build/caffe-V1QGus/caffe-1.0.0~rc4/tools/caffe.cpp:
    -gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
      '-gpu all' to run on all available GPUs. The effective training batch
      size is multiplied by the number of devices.) type: string default: ""
    -iterations (The number of iterations to run.) type: int32 default: 50
    -level (Optional; network level.) type: int32 default: 0
    -model (The model definition protocol buffer text file.) type: string
      default: ""
    -phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
      type: string default: ""
    -sighup_effect (Optional; action to take when a SIGHUP signal is received:
      snapshot, stop or none.) type: string default: "snapshot"
    -sigint_effect (Optional; action to take when a SIGINT signal is received:
      snapshot, stop or none.) type: string default: "stop"
    -snapshot (Optional; the snapshot solver state to resume training.)
      type: string default: ""
    -solver (The solver definition protocol buffer text file.) type: string
      default: ""
    -stage (Optional; network stages (not to be confused with phase), separated
      by ','.) type: string default: ""
    -weights (Optional; the pretrained weights to initialize finetuning,
      separated by ','. Cannot be set simultaneously with snapshot.)
      type: string default: ""

cd
git clone https://github.com/kesara/deepdreamer
cd deepdreamer

# 学習データ bvlc_googlenet.caffemodelをダウンロードする
wget http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel

# deploy.prototxtをダウンロードする
# https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet
wget https://raw.githubusercontent.com/BVLC/caffe/master/models/bvlc_googlenet/deploy.prototxt

# deploy.prototxtの一番最後に force_backward: trueの行を追加する
# nano deploy.prototxt
# force_backward: true

# コマンドラインでサクッと force_backward: trueの行を追加する
echo "force_backward: true" >> deploy.prototxt

# tailコマンドで最後に追加された事を確認する
tail deploy.prototxt

pi@raspberrypi:~/deepdreamer $ python3 deepdreamer.py sample.jpg

# ディレクトリを GITの kesara/deepdreamerに変更する
cd
cd deepdreamer

# flowers.jpg画像をダウンロードする
wget https://github.com/google/deepdream/raw/master/flowers.jpg

# flowers.jpg画像を元に DeepDream（100世代）する
python3 deepdreamer.py flowers.jpg

# flowers.jpg画像を元に DeepDreamで GIFアニメを生成する
python3 deepdreamer.py --gif true flowers.jpg
# Error: only integer scalar arrays can be converted to a scalar index

# ImageMagick
sudo apt-get -y install imagemagick

pi@raspberrypi:~/deepdreamer $ python3 deepdreamer.py flowers.jpg
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0807 13:06:42.396404  2675 _caffe.cpp:135] DEPRECATION WARNING - deprecated use of Python interface
W0807 13:06:42.396530  2675 _caffe.cpp:136] Use this instead (with the named "weights" parameter):
W0807 13:06:42.396548  2675 _caffe.cpp:138] Net('deploy.prototxt', 1, weights='bvlc_googlenet.caffemodel')
I0807 13:06:42.405501  2675 net.cpp:53] Initializing net from parameters:
name: "GoogleNet"
force_backward: true
state {

...

  convolution_param {
    num_output: 32
    kernel_size: 1
    weight_filler {
      type: "xavier"
      std: 0.2
    }
    bias_filler {
      type: "c
I0807 13:06:42.438524  2675 layer_factory.hpp:77] Creating layer data
I0807 13:06:42.438645  2675 net.cpp:86] Creating Layer data
I0807 13:06:42.438694  2675 net.cpp:382] data -> data
I0807 13:06:42.438804  2675 net.cpp:124] Setting up data
I0807 13:06:42.438846  2675 net.cpp:131] Top shape: 10 3 224 224 (1505280)
I0807 13:06:42.438896  2675 net.cpp:139] Memory required for data: 6021120
I0807 13:06:42.438936  2675 layer_factory.hpp:77] Creating layer conv1/7x7_s2
I0807 13:06:42.439004  2675 net.cpp:86] Creating Layer conv1/7x7_s2
I0807 13:06:42.439043  2675 net.cpp:408] conv1/7x7_s2 <- data
I0807 13:06:42.439093  2675 net.cpp:382] conv1/7x7_s2 -> conv1/7x7_s2

...

I0807 13:07:56.687074  2682 net.cpp:746] Ignoring source layer loss3/loss3
Dreaming...
/usr/lib/python3/dist-packages/scipy/ndimage/interpolation.py:568: UserWarning: From scipy 0.13.0, the output shape of zoom() is calculated with round() instead of int() - for these inputs the size of the returned array has changed.
  "the returned array has changed.", UserWarning)

Raspberry Piでメモリを馬鹿食いするアプリ用に不要なサービスを停止してフリーメモリを増やす方法

pi@raspberrypi:~ $ free -h
              total        used        free      shared  buff/cache   available
Mem:           976M        250M        531M        6.5M        194M        670M
Swap:          2.0G          0B        2.0G

【ビルド版】Raspberry Piで DeepDreamを動かしてキモイ絵をモリモリ量産 Caffe Deep Learning Framework

NVIDIA Jetson Nano 開発者キットを買ってみた。メモリ容量 4GB LPDDR4 RAM

Raspberry Piでメモリを馬鹿食いするアプリ用に不要なサービスを停止してフリーメモリを増やす方法

【成功版】最新版の Darknetに digitalbrain79版の Darknet with NNPACKの NNPACK処理を適用する

【成功版】Raspberry Piで NNPACK対応版の Darknet Neural Network Frameworkをビルドする方法

【成功版】Raspberry Piで Darknet Neural Network Frameworkをビルドする方法

【成功版】Raspberry Piに TensorFlow Deep Learning Frameworkをインストールする方法

Raspberry Piで TensorFlow Deep Learning Frameworkを自己ビルドする方法

Raspberry Piで Caffe Deep Learning Frameworkで物体認識を行なってみるテスト

【ビルド版】Raspberry Piで DeepDreamを動かしてキモイ絵をモリモリ量産 Caffe Deep Learning Framework

Raspberry Piで Caffe2 Deep Learning Frameworkをソースコードからビルドする方法

Orange Pi PC 2の 64bitのチカラで DeepDreamしてキモイ絵を高速でモリモリ量産してみるテスト

Raspberry Piに Jupyter Notebookをインストールして拡張子 ipynb形式の IPythonを動かす

Raspberry Piで Deep Learningフレームワーク Chainerをインストールしてみる

Raspberry Piで DeepBeliefSDKをビルドして画像認識フレームワークを動かす方法

Raspberry Piで Microsoftの ELLをビルドする方法

Raspberry Piで MXNet port of SSD Single Shot MultiBoxを動かして画像の物体検出をする方法

Raspberry Piで Apache MXNet Incubatingをビルドする方法

Raspberry Piで OpenCVの Haar Cascade Object Detectionでリアルタイムにカメラ映像の顔検出を行なってみる

Raspberry Piで NNPACKをビルドする方法

Raspberry Pi 3の Linuxコンソール上で使用する各種コマンドまとめ