深度学习示例1-全零通道的 MNIST 数据训练模型

一、代码示例

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.datasets import mnist
import numpy as np

(train_images, train_labels), _ = mnist.load_data()
train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype("float32") / 255

train_images_with_zeros_channels = np.concatenate(
    [train_images, np.zeros((len(train_images), 784))], axis=1)

def get_model():
    model = keras.Sequential([
        layers.Dense(512, activation="relu"),
        layers.Dense(10, activation="softmax")
    ])
    model.compile(optimizer="rmsprop",
                  loss="sparse_categorical_crossentropy",
                  metrics=["accuracy"])
    return model

model = get_model()
history_zeros = model.fit(
    train_images_with_zeros_channels, train_labels,
    epochs=10,
    batch_size=128,
    validation_split=0.2)

运行结果：

Epoch 1/10
375/375 [==============================] - 5s 11ms/step - loss: 0.2893 - accuracy: 0.9178 - val_loss: 0.1775 - val_accuracy: 0.9465
Epoch 2/10
375/375 [========================