【機械学習】Pythonでひらがな(日本語)の文字分類手順。〜 Keras使用 〜

├── a
│   └── a.jpg
└── i
    └── i.jpg

import keras
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.layers.core import Dense, Dropout, Activation, Flatten
import numpy as np
from sklearn.model_selection import train_test_split
from PIL import Image
import glob



folders = ['a','i']
print("147,151,149,152,154,153,154,137,149,153,158,158,157,157,154,152")
X = []
Y = []

image_size = 50
# 対象Aの画像
index = 0
for folder in folders:
    files = glob.glob('./test/' + str(folder) + '/*.JPG')
    print(files)
    for file in files:
        print(file)
        image = Image.open(file)
        image = image.convert("RGB")
        image = image.resize((image_size, image_size))
        data = np.asarray(image)
        X.append(data)
        Y.append(index)
    index = index + 1
X = np.array(X)
Y = np.array(Y)


X = X.astype('float32')
X = X / 255.0

# 正解ラベルの形式を変換
Y = np_utils.to_categorical(Y, 16)

# 学習用データとテストデータ
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.20)

# CNNを構築
model = Sequential()
 
model.add(Conv2D(32, (3, 3), padding='same',input_shape=X_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
 
model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
 
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(16))
model.add(Activation('softmax'))
 
# コンパイル
model.compile(loss='categorical_crossentropy',optimizer='SGD',metrics=['accuracy'])

history = model.fit(X_train, y_train, epochs=200)
print("完了")

model.save('/only_test/model.hdf5')
print("保存完了")