Skip to content

Instantly share code, notes, and snippets.

View rakuishi's full-sized avatar
🏠
Working from home

OCHIISHI Koichiro rakuishi

🏠
Working from home
View GitHub Profile
@rakuishi
rakuishi / macos-catalina-init-setup.md
Created November 13, 2020 20:58
macOS Catalina 初期設定

システム環境設定

Dock

  • 画面上の位置を「右」に設定する
  • 「Dock を自動的に隠す」を入にする

キーボード

  • キーボード → 「キーのリピート」を最速に、「リピート入力認識までの時間」を最短にする
@rakuishi
rakuishi / index.css
Created December 28, 2019 04:17
群れは意識をもつ 個の自由と集団の秩序
html, body {
margin: 0;
padding: 0;
}
.ant-box {
position: relative;
width: 400px;
height: 400px;
border: 1px solid #ddd;
}

Install the Flutter

https://flutter.dev/docs/get-started/install/macos

$ cd ~/Projects
$ unzip ~/Downloads/flutter_macos_v1.9.1+hotfix.2-stable.zip
$ export PATH="$PATH:/Users/rakuishi/Projects/flutter/bin"
$ source ~/.bash_profile
$ flutter precache
@rakuishi
rakuishi / 20180225_multiple-linear-regression_1.ipynb
Last active February 3, 2022 02:14
【キカガク流】人工知能・機械学習 脱ブラックボックス講座 - 中級編 -
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@rakuishi
rakuishi / 20180220_simple-linear-regression.ipynb
Last active February 3, 2022 02:14
【キカガク流】人工知能・機械学習 脱ブラックボックス講座 - 初級編 -
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
# 0.1176554
def homework(train_X, train_Y, tokenizer_en, tokenizer_ja):
import numpy as np
from keras.models import Model
from keras.layers import Input, Embedding, Dense, LSTM
emb_dim = 256
hid_dim = 256
en_vocab_size = len(tokenizer_en.word_index) + 1
@rakuishi
rakuishi / international-airline-passengers.csv
Created February 10, 2018 01:08
再帰型ニューラルネットワーク
Month International airline passengers: monthly totals in thousands. Jan 49 ? Dec 60
1949-01 112
1949-02 118
1949-03 132
1949-04 129
1949-05 121
1949-06 135
1949-07 148
1949-08 148
1949-09 136
# -*- coding: utf-8 -*-
# https://rakuishi.com/archives/getting-started-with-keras/
from keras.datasets import mnist
from keras.utils import to_categorical
from keras.models import Sequential
from keras.layers import Dense, Activation
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train.shape, y_train.shape, x_test.shape, y_test.shape
def homework(train_X, train_y, test_X):
import keras
from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Input, Activation, Dropout
from keras.layers.normalization import BatchNormalization
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
gcn_whitening = ImageDataGenerator(samplewise_center=True, samplewise_std_normalization=True)
gcn_whitening.fit(train_X)