chainerのインストール&動作確認 | Visualize the Invisible

Visualize the Invisible

データとAIを使って、混沌とした世界を「見える化」したい。

Caffeは環境を作るのが大変そうなので、以下のURLをもとに
PFNのPFであるchainerをインストールして動作確認。


sh-3.2# pip install chainer
Collecting chainer
  Downloading chainer-1.8.2.tar.gz (934kB)
    100% |████████████████████████████████| 942kB 585kB/s 
Collecting filelock (from chainer)
  Downloading filelock-2.0.6.tar.gz
Requirement already satisfied (use --upgrade to upgrade): nose in /System/anaconda/lib/python3.5/site-packages (from chainer)
Requirement already satisfied (use --upgrade to upgrade): numpy>=1.9.0 in /System/anaconda/lib/python3.5/site-packages (from chainer)
Collecting protobuf (from chainer)
  Downloading protobuf-2.6.1.tar.gz (188kB)
    100% |████████████████████████████████| 194kB 1.1MB/s 
Requirement already satisfied (use --upgrade to upgrade): six>=1.9.0 in /System/anaconda/lib/python3.5/site-packages (from chainer)
Requirement already satisfied (use --upgrade to upgrade): setuptools in /System/anaconda/lib/python3.5/site-packages/setuptools-20.7.0-py3.5.egg (from protobuf->chainer)
Building wheels for collected packages: chainer, filelock, protobuf
  Running setup.py bdist_wheel for chainer ... done
  Stored in directory: /var/root/Library/Caches/pip/wheels/5c/d2/82/731748abf2caeed06ca25801854875ad5f2b7f125746223cf8
  Running setup.py bdist_wheel for filelock ... done
  Stored in directory: /var/root/Library/Caches/pip/wheels/97/9b/c0/47c42b4f38b378a65671364fb62ae7822b68b13f8048221d07
  Running setup.py bdist_wheel for protobuf ... done
  Stored in directory: /var/root/Library/Caches/pip/wheels/c9/97/49/1bf6b7b58d0adec650bcb625b6656877437d1f7d18c32e88ee
Successfully built chainer filelock protobuf
Installing collected packages: filelock, protobuf, chainer
Successfully installed chainer-1.8.2 filelock-2.0.6 protobuf-2.6.1
sh-3.2# 

sh-3.2# python download.py 
sh-3.2# 
sh-3.2# ls
download.py trees
trainDevTestTrees_PTB.zip
sh-3.2# touch train_sentiment.py
sh-3.2# subl train_sentiment.py 
sh-3.2# python train_sentiment.py
Epoch: 0
loss: 224035.69
13.66 iters/sec, 625.46 sec

Epoch: 1


1層終えるのに20分くらいかかる・・