TensorFlow 基础

import tensorflow as tf

# 创建模型
model = tf.keras.Sequential([
   tf.keras.layers.Dense(128, activation='relu'),
   tf.keras.layers.Dropout(0.2),
   tf.keras.layers.Dense(10, activation='softmax')
])

# 编译模型
model.compile(optimizer='adam',
             loss='sparse_categorical_crossentropy',
             metrics=['accuracy'])

训练模型

# 训练
model.fit(X_train, y_train, epochs=10, validation_split=0.2)

# 评估
test_loss, test_acc = model.evaluate(X_test, y_test)

转载请注明：周志洋的博客 » Python机器学习-深度学习入门