使用keras進(jìn)行mnist識別
構(gòu)建一個(gè)兩層全連接網(wǎng)絡(luò)
因?yàn)槿B接輸出層為十個(gè)輸出母廷，所以將標(biāo)簽y進(jìn)行one-hot encoding對應(yīng)輸出
代碼如下
from tensorflow.keras.datasets import mnist
from tensorflow.keras import utils
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import RMSprop
#download the mnist to the path
(X_train, y_train), (X_test, y_test) = mnist.load_data()
#data pre-processing normalization
X_train = X_train.reshape(X_train.shape[0], -1)/255
X_test = X_test.reshape(X_test.shape[0], -1)/255
# one hot
y_train = utils.to_categorical(y_train, num_classes=10)
y_test = utils.to_categorical(y_test, num_classes=10)
model = Sequential([
? ??????????Dense(units=32, input_shape=[784], activation="relu"),
? ??????????Dense(units=10, activation='softmax')
])
rmsprop = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)
model.compile( optimizer=rmsprop,loss="categorical_crossentropy", metrics = ["accuracy"],)
model.fit(X_train, y_train, nb_epoch=2, batch_size=32)
loss, accuracy = model.evaluate(X_test, y_test)
print("loss:",loss)
print("accuracy:",accuracy)
