from tensorflow.keras.datasets import cifar10 from tensorflow.keras.utils import to_categorical import numpy as np def prepare_cifar10(): (x_train, y_train), (x_test, y_test) = cifar10.load_data() x_train = x_train.astype(np.float) x_test = x_test.astype(np.float) x_train = x_train / 255. x_test = x_test / 255. x_train = x_train.reshape((-1, 32, 32, 3)) x_test = x_test.reshape((-1, 32, 32, 3)) y_train = to_categorical(y_train) y_test = to_categorical(y_test) return x_train, x_test, y_train, y_test x_train, x_test, y_train, y_test = prepare_cifar10()

model = Sequential([ Input(shape=(32, 32, 3)), Conv2D(filters=6, kernel_size=5, # Nombre de pixel perdu + 1 strides=1, padding='valid', # La taille de l'image diminue (dans le problème d'origine 32x32) activation='relu'), MaxPool2D(pool_size=2), Conv2D(filters=16, kernel_size=5, strides=1, activation='relu', padding='valid'), MaxPool2D(pool_size=2), Flatten(), Dense(units=120, activation='relu'), Dense(units=84, activation='relu'), Dense(units=10, activation='softmax'), ]) model.compile(loss="categorical_crossentropy", optimizer="adam", metrics="accuracy") model.summary()

from sklearn.preprocessing import MinMaxScaler from tensorflow.keras.datasets import boston_housing def prepare_boston(): (x_train, y_train), (x_test, y_test) = boston_housing.load_data() scaler_x = MinMaxScaler() scaler_x.fit(x_train) x_train = scaler_x.transform(x_train) x_test = scaler_x.transform(x_test) scaler_y = MinMaxScaler() scaler_y.fit(y_train.reshape((-1, 1))) y_train = scaler_y.transform(y_train.reshape((-1, 1))) y_test = scaler_y.transform(y_test.reshape((-1, 1))) return x_train, x_test, y_train, y_test x_train, x_test, y_train, y_test = prepare_boston()