- Windows上でのPython3.6のサポート
- spatio temporal deconvolutionのための
tf.layers.conv3d_transposeレイヤの追加- コメント:3次元MRI画像のようなデータをさばくためのレイヤだと理解
- 前のTFには2次元の畳込みしかなかった記憶がある
tf.Session.make_callable()の追加- オーバーヘッドが削減されるとのこと
- contrib向けにibverbsベースのリモートダイレクトメモリアクセス(RDMA)を追加
- RDMAやInfiniBandが関わるのでTFの分散システム的側面のための機能だと理解
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env/python | |
| # coding: utf-8 | |
| # **[CNN-01]** 必要なモジュールをインポートして、乱数のシードを設定します。 | |
| # In[1]: | |
| import time | |
| import tensorflow as tf | |
| import numpy as np |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| curl -O https://gist.githubusercontent.com/akimach/27e87cb7f97dc253921b9ea8b7b332b5/raw/fd112a66a3ca953dd7ad26098cccfe1d532ba0d7/binominal_confidience_interval.ipynb | |
| jupyter-nbconvert binominal_confidience_interval.ipynb --to markdown | |
| pandoc binominal_confidience_interval.ipynb -t docx -o binominal_confidience_interval.docx |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| $ curl -O https://gist.githubusercontent.com/akimach/27e87cb7f97dc253921b9ea8b7b332b5/raw/fd112a66a3ca953dd7ad26098cccfe1d532ba0d7/binominal_confidience_interval.ipynb | |
| $ jupyter-nbconvert binominal_confidience_interval.ipynb --to markdown | |
| $ pandoc binominal_confidience_interval.md -t docx -o binominal_confidience_interval.docx |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| pip3 install scikit-learn |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.utils import shuffle | |
| from sklearn import svm | |
| from sklearn.metrics import precision_score | |
| from sklearn.metrics import recall_score | |
| from sklearn.metrics import f1_score | |
| np.random.seed(1234) | |
| n_data = 200 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| np.random.seed(1234) | |
| from keras.models import Sequential | |
| from keras.layers import Dense, Activation | |
| from keras import optimizers | |
| from keras.wrappers.scikit_learn import KerasClassifier | |
| from sklearn.utils import shuffle | |
| from sklearn.model_selection import GridSearchCV |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| from keras.models import Sequential | |
| from keras.layers import Dense, Activation | |
| from keras import optimizers | |
| from keras.callbacks import EarlyStopping | |
| from sklearn.utils import shuffle | |
| from sklearn.model_selection import train_test_split | |
| # Setup dataset | |
| np.random.seed(1234) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| timesteps = 40 # 最大系列長 | |
| input_dim = 3 # 入力次元 | |
| df = pd.read_csv('example.csv') | |
| seq = df.as_matrix() | |
| seq_length = seq.shape[0] # 対象となるデータの系列長 | |
| seq_0padding = np.r_[seq, np.zeros((timesteps-seq_length, input_dim))] |