【深度學習】基於Keras的手寫體識別
阿新 • • 發佈:2019-01-04
from keras import models
from keras import layers
from keras.datasets import mnist
# 搭建網路
network = models.Sequential()
network.add(layers.Dense(512, activation='relu', input_shape=(28*28,)))
network.add(layers.Dense(10,activation='softmax')) # 返回由10個概率值組成的陣列
# 編譯網路
network.compile(optimizer='rmsprop' , loss='categorical_crossentropy', metrics=['accuracy'])
# 載入資料
(train_images, train_labels),(test_images, test_labels) = mnist.load_data()
# 對資料進行預處理
train_images = train_images.reshape(60000, 28*28)
train_images.astype('float32') / 255
test_images = test_images.reshape(10000, 28*28)
test_images = test_images. astype('float32') / 255
# 準備標籤 -- One-Hot編碼
from keras.utils import to_categorical
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
print(train_labels[0]) # array([0., 0., 0., 0., 0., 1., 0., 0., 0., 0.], dtype=float32)
# 開始訓練網路:擬合數據
network.fit(train_images, train_labels, epochs=10, batch_size=128)
'''
Epoch 1/10
60000/60000 [==============================] - 2s 39us/step - loss: 5.3171 - acc: 0.6697
Epoch 2/10
60000/60000 [==============================] - 2s 39us/step - loss: 5.2466 - acc: 0.6743
Epoch 3/10
60000/60000 [==============================] - 2s 39us/step - loss: 5.2882 - acc: 0.6716
Epoch 4/10
60000/60000 [==============================] - 2s 38us/step - loss: 5.2737 - acc: 0.6726
Epoch 5/10
60000/60000 [==============================] - 2s 38us/step - loss: 5.2659 - acc: 0.6730
Epoch 6/10
60000/60000 [==============================] - 2s 38us/step - loss: 5.2511 - acc: 0.6740
Epoch 7/10
60000/60000 [==============================] - 2s 38us/step - loss: 5.2200 - acc: 0.6758
Epoch 8/10
60000/60000 [==============================] - 2s 38us/step - loss: 5.2329 - acc: 0.6751
Epoch 9/10
60000/60000 [==============================] - 2s 37us/step - loss: 5.2335 - acc: 0.6750
Epoch 10/10
60000/60000 [==============================] - 2s 37us/step - loss: 5.2414 - acc: 0.6746
'''
案例中訓練5輪即可達到98.9%的精度,我實際用起來效果並不是很好,還沒看哪裡有不同。
訓練完後,直接用於預測:
test_loss, test_acc = network.evaluate(test_images, test_labels)
print('test_acc: ', test_acc)
'''
10000/10000 [==============================] - 1s 52us/step
test_acc: 0.6772
'''
重點還是在於回顧Keras的使用,算是一個簡單的模板,後續再豐富使用場景。
END.