![[PukiWiki]](image/pukiwiki.png "[PukiWiki]")
「.NET 開発基盤部会 Wiki」は、「Open棟梁Project」,「OSSコンソーシアム .NET開発基盤部会」によって運営されています。 散布図
from keras.datasets import mnist (x_train_org, y_train_org), (x_test_org, y_test_org) = mnist.load_data() print(x_train_org.shape, x_test_org.shape) print(y_train_org.shape, y_test_org.shape)
show_image_info(x_train_org, y_train_org, [0,1,2,3,4,5,6,7,8,9], 10)
x_train_std = x_train_org.astype('f')
x_test_std = x_test_org.astype('f')x_train_std /= 255 x_test_std /= 255
y_train = np_utils.to_categorical(y_train_org, num_classes=10).astype('i')
y_test = np_utils.to_categorical(y_test_org, num_classes=10).astype('i')
・デコーディング
print((y_train.argmax(axis=1) == y_train_org).all()) print((y_test.argmax(axis=1) == y_test_org).all())
# モデルのインスタンスを作成
model = Sequential()
# addメソッドで層を追加していく。
# Flatten：入力の変換層、入力サイズを指定
model.add(Flatten(input_shape=(28, 28)))
# 入力層
# Dense：全結合（線形結合）層、出力サイズを指定
model.add(Dense(900))
# Activation: 活性化関数を定義（ReLU
model.add(Activation('relu'))
# 多層化：繰り返し
model.add(Dense(1000))
model.add(Activation('relu'))
model.add(Dense(500))
model.add(Activation('relu'))
# 出力層：
# Dense：全結合（線形結合）層、出力サイズを指定
model.add(Dense(10))
# Activation: 活性化関数を定義（softmax
model.add(Activation('softmax'))
# 誤差関数、最適化手法、評価基準を指定してコンパイル
# ・損失関数 ：categorical_crossentropy（分類の定番、回帰ならRMSE）
# ・最適化手法：SGD（基本的な確率的勾配降下法）
# ・評価方法 ：Accuracy（精度）に指定
model.compile(loss='categorical_crossentropy',
optimizer=SGD(),
metrics=['accuracy'])batch_size = 100
n_epoch = 20
# Keras Model の fit() は History オブジェクトを返す
hist = model.fit(x_train_std, y_train,
validation_data=(x_test_std, y_test),
batch_size=batch_size,
epochs=n_epoch,
verbose=1
)
※ batch_size、epochsについてはコチラindex = 10
show_image_info(x_test_org, y_test_org, [0,1,2,3,4,5,6,7,8,9], index)
predict = model.predict(x_test_std[index].reshape(1, 28, 28)).argmax()
answer = y_test_org[index]
print('predict: ', predict)
print('answer : ', answer)
if predict == answer:
print('正解')
else:
print('不正解')model.evaluate(x_test_std, y_test) #（損失値、精度）を返す
hist.history
# 損失値(Loss)の遷移のプロット
def plot_history_loss(hist):
plt.plot(hist.history['loss'],label="loss for training")
plt.plot(hist.history['val_loss'],label="loss for validation")
plt.title('model loss')
plt.xlabel('epoch')
plt.ylabel('loss')
plt.legend(loc='best')
plt.show()
# 精度(Accuracy)の遷移のプロット
def plot_history_acc(hist):
plt.plot(hist.history['accuracy'],label="accuracy for training")
plt.plot(hist.history['val_accuracy'],label="accuracy for validation")
plt.title('model accuracy')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.legend(loc='best')
plt.ylim([0, 1])
plt.show()
・グラフ表示
plot_history_loss(hist) plot_history_acc(hist)
result = model.predict(x_test_std).argmax(axis=1) confmat = cm(y_test_org, result) # y_testはOne-Hot表現前 confmat
print_metrics(y_test_org, result) # y_testはOne-Hot表現前
index = (y_test_org != result)
for i, val in enumerate(index):
if val == True:
print('predict: ', result[i])
print('answer : ', y_test_org[i])
show_image_info(x_test_org, y_test_org, [0,1,2,3,4,5,6,7,8,9], i)import os
from urllib import request
os.mkdir('./datasets')
url = 'https://.../train.pickle'
request.urlretrieve(url, './datasets/train.pickle')
url = 'https://.../test.pickle'
request.urlretrieve(url, './datasets/test.pickle')
url = 'https://.../label.pickle'
request.urlretrieve(url, './datasets/label.pickle')from keras.datasets import cifar10 (x_train,y_train),(x_test,y_test)=cifar10.load_data()
def unpickle(file):
import pickle
with open(file, 'rb') as f:
return pickle.load(f, encoding='bytes')train = unpickle('./datasets/train.pickle')
test = unpickle('./datasets/test.pickle')
label = unpickle('./datasets/label.pickle')x_train_org = train['data'] y_train_org = train['label'] x_test_org = test['data'] y_test_org = test['label'] print(x_train_org.shape) print(y_train_org.shape) print(x_test_org.shape) print(y_test_org.shape)
# サンプル数, height, width, channelへ変更 x_train = x_train_org.transpose([0, 2, 3, 1]) x_test = x_test_org.transpose([0, 2, 3, 1])
x_train_std = x_train.astype('f')
x_test_std = x_test.astype('f')x_train_std /= 255 x_test_std /= 255
y_train = np_utils.to_categorical(y_train_org, num_classes=5).astype('i')
y_test = np_utils.to_categorical(y_test_org, num_classes=5).astype('i')
・デコーディング
print((y_train.argmax(axis=1) == y_train_org).all()) print((y_test.argmax(axis=1) == y_test_org).all())
show_image_info(x_train, y_train_org, label, 1300)
model = Sequential()
# 畳み込み層とプーリング層１
model.add(Conv2D(input_shape=(32, 32, 3), filters=64, kernel_size=(4, 4), strides=(1, 1), padding='same')) # 畳み込み層
# バッチ正規化の追加位置
model.add(MaxPool2D(pool_size=(2, 2))) # プーリング増
model.add(Activation('relu'))
# 畳み込み層とプーリング層２
model.add(Conv2D(filters=128, kernel_size=(4, 4), strides=(1, 1), padding='same')) # 畳み込み層
# バッチ正規化の追加位置
model.add(MaxPool2D(pool_size=(2, 2))) # プーリング増
model.add(Activation('relu'))
# 畳み込み層とプーリング層３
model.add(Conv2D(filters=128, kernel_size=(4, 4), strides=(1, 1), padding='same')) # 畳み込み層
# バッチ正規化の追加位置
model.add(MaxPool2D(pool_size=(2, 2))) # プーリング増
model.add(Activation('relu'))
model.add(Flatten())
# 全結合層１
model.add(Dense(512))
model.add(Activation('relu'))
# Dropoutの追加位置
# 全結合層２
model.add(Dense(5))
model.add(Activation('softmax'))
# コンパイル
model.compile(loss='categorical_crossentropy',
optimizer=SGD(0.01), # 学習率：0.01
metrics=['accuracy'])batch_size = 500
n_epoch = 30
hist = model.fit(x_train_std , y_train,
validation_data=(x_test_std, y_test),
batch_size=batch_size,
epochs=n_epoch,
verbose=1)index = 10
show_image_info(x_train, y_train_org, label, index)
predict = model.predict(x_test_std[index].reshape(1, 32, 32, 3)).argmax()
answer = y_test_org[index]
print('predict: ', predict)
print('answer : ', answer)
if predict == answer:
print('正解')
else:
print('不正解')index = (y_test_org != result)
for i, val in enumerate(index):
if val == True:
print('predict: ', result[i])
print('answer : ', y_test_org[i])
show_image_info(x_test, y_test_org, label, i)def show_image_info(x, y, label, index):
print(label[y[index]])
plt.imshow(x[index].astype(np.uint8))
plt.show()model.add(BatchNormalization())
OpenCVを使用する。
url = 'https://upload.wikimedia.org/wikipedia/en/7/7d/Lenna_%28test_image%29.png' request.urlretrieve(url, 'lenna.png')
img = cv2.imread('lenna.png')
print(type(img))
print(img.shape)
plt.imshow(img) # OpenCVはBGR解釈なので青みがかる。img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # RGB解釈に変更。
plt.imshow(img) # 元のRGB解釈の色合いで表示される。
cv2.imwrite('new_lenna.jpg', img) # RGB解釈で保存def diff_image_info(img1, img2):
print(img1.shape)
print(img2.shape)
plt.subplot(1, 2, 1)
plt.imshow(img1)
plt.subplot(1, 2, 2)
plt.imshow(img2)img2 = cv2.resize(img, (224, 224)) diff_image_info(img, img2)
img2 = img[100:400,100:400,:] diff_image_info(img, img2)
h, w, c = img.shape img2 = img[:, int(w * (1/5)): int(w *(4/5)), :] diff_image_info(img, img2)
grayed = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) diff_image_info(img, grayed)
th, binary = cv2.threshold(grayed, 125, 255, cv2.THRESH_BINARY) diff_image_info(grayed, binary)
blurred = cv2.GaussianBlur(binary, (11, 11), 0) diff_image_info(binary, blurred)
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8)) clahed = clahe.apply(grayed) diff_image_info(grayed, clahed)
img2 = x.astype('f')
img2 /= 255 # 0～1正規化
img2 -= np.mean(img2) # スケーリング
diff_image_info(img, img2)
※ img単位ではなくxに対して適用できる。img2 = img.astype('f')
img2 -= img.min()# 最小値を引く
img2 /= img.max()# 最大値で割る
diff_image_info(img, img2)
※ img単位ではなくxに対して適用できる。flipped = cv2.flip(img, 1) diff_image_info(img, flipped)
def opencv_rotate(img, angle=30):
size = (img.shape[0], img.shape[1])
center = (int(size[0]/2), int(size[1]/2))
rotation_matrix = cv2.getRotationMatrix2D(center, angle, 1.0)
return cv2.warpAffine(img, rotation_matrix, size)
・回転実行
rotated = opencv_rotate(img, 30) diff_image_info(img, rotated)
def opencv_move(img, h=100, v=50):
rows, cols, channnels = img.shape
M = np.float32([[1,0,h],[0,1,v]])
return cv2.warpAffine(img, M, (cols, rows))
・並進実行
moved = opencv_move(img, 200, 100) diff_image_info(img, moved)
def opencv_zoomin(img, h=2.0, v=2.0):
zoomed = cv2.resize(img, None, fx=h, fy=v)
height_1, width_1, channel_1 = img.shape
height_2, width_2, channel_2 = zoomed.shape
x = int((width_2 - width_1) / 2)
y = int((height_2 - height_1) / 2)
return zoomed[y:y+height_1, x:x+width_1]
・拡大実行
zoomed = opencv_zoomin(img, 2, 3) diff_image_info(img, zoomed)
def opencv_gamma(img, gamma=0.5):
look_up_table = np.zeros((256, 1), dtype='uint8')
for i in range(256):
look_up_table[i][0] = 255 * pow(float(i) / 255, 1.0 / gamma)
return cv2.LUT(img, look_up_table)
・ガンマ変換
img_gamma = opencv_gamma(img, 0.3) diff_image_info(img, img_gamma)
def opencv_gaussian(img, loc=0.0, scale=5.0):
row, col, ch = img.shape
noise = np.random.normal(loc,scale,(row,col,ch))
noise = noise.reshape(row,col,ch)
noised = img + noise
noised /= 255
return noised
・ガンマ変換
img_gaussian = opencv_gaussian(img, 50, 100) diff_image_info(img, img_gaussian)
def get_changed(img):
# グレースケール化
...
# ヒストグラム平坦化
...
# 平滑化
...
# カラーでなくなっている場合、
# 次元が減っているので、追加する。
return blurred[:,:,np.newaxis]def get_augmented(img):
# 左右反転
if np.random.rand() > 0.5:
img = cv2.flip(img, 1)
# 左右度回転
if np.random.rand() > 0.5:
size = (img.shape[0], img.shape[1])
center = (int(size[0]/2), int(size[1]/2))
angle = np.random.randint(-45, 45) # -45 ～ +45 の範囲で
rotation_matrix = cv2.getRotationMatrix2D(center, angle, 1.0)
img = cv2.warpAffine(img, rotation_matrix, size)
return img
plt.imshow(get_augmented(x_train[1300]).astype(np.uint8))base_model = VGG16(weights='imagenet', include_top=False, input_tensor=Input(shape=(32, 32, 3))) # inputs.output_shape => (None, 1, 1, 512)
n_class = 5
top_model = Sequential()
top_model.add(Flatten(input_shape=inputs.output_shape[1:]))
top_model.add(Dense(256))
top_model.add(Activation('relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(n_class))
top_model.add(Activation('softmax'))model = Model(inputs=base_model.input, outputs=top_model(base_model.output))
for layer in model.layers[:15]:
layer.trainable = False
model.compile(loss='categorical_crossentropy',
optimizer=SGD(lr=0.0001),
metrics=['accuracy'])model.summary()
def preprocess_vgg16(img):
# リサイズ
img= cv2.resize(img, (32, 32))
# RGBからそれぞれvgg指定の値を引く
# (mean-subtractionに相当)
img[:, :, 0] -= 103.939
img[:, :, 1] -= 116.779
img[:, :, 2] -= 123.68
return imgx_train_list = []
for img in x_train:
x_train_list.append(preprocess_vgg16(get_augmented(get_changed(img))))
x_train_aug = np.array(x_train_list)
x_test_list = []
for img in x_test:
x_test_list.append(preprocess_vgg16(get_augmented(get_changed(img))))
x_test_aug = np.array(x_test_list)batch_size = 100 n_epoch = 1 # 試用なので回数を減らす
