使用卷积神经网络训练手写数字识别

前面步骤和传送门

一样，这里记录下重点

import tensorflow as tf
from tensorflow import keras
import numpy as np

(X_train_full, y_train_full), (X_test, y_test) = keras.datasets.mnist.load_data()
X_train_full = X_train_full / 255.
X_test = X_test / 255.
X_train, X_valid = X_train_full[:-5000], X_train_full[-5000:]
y_train, y_valid = y_train_full[:-5000], y_train_full[-5000:]


X_train = X_train[..., np.newaxis]
X_valid = X_valid[..., np.newaxis]
X_test = X_test[..., np.newaxis]

np.newaxis这个处理参考
传送门

卷积网络部分，使用经典结构

keras.backend.clear_session()
tf.random.set_seed(42)
np.random.seed(42)

model = keras.models.Sequential([
    keras.layers.Conv2D(32, kernel_size=3, padding="same", activation="relu"),
    keras.layers.Conv2D(64, kernel_size=3, padding="same", activation="relu"),
    keras.layers.MaxPool2D(),
    keras.layers.Flatten(),
    keras.layers.Dropout(0.25),
    keras.layers.Dense(128, activation="relu"),
    keras.layers.Dropout(0.5),
    keras.layers.Dense(10, activation="softmax")
])
model.compile(loss="sparse_categorical_crossentropy", optimizer="nadam",
              metrics=["accuracy"])

model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))
model.evaluate(X_test, y_test)

99.2%准确率