评估与预测
评估和预测函数：tf.keras.Model.evaluate和tf.keras.Model.predict方法。
代码：

模型评估

test_x = np.random.random((1000, 36))
test_y = np.random.random((1000, 10))
model.evaluate(test_x, test_y, batch_size=32)

输出：
1000/1000 [==============================] - 0s 45us/sample - loss: 12.2881 - categorical_accuracy: 0.0770
[12.288104843139648, 0.077]

代码：

模型预测

pre_x = np.random.random((10, 36))
result = model.predict(test_x,)
print(result)

输出：
[[0.04431767 0.24562006 0.05260926 ... 0.1016549 0.13826898 0.15511878]
[0.06296062 0.12550288 0.07593573 ... 0.06219672 0.21190381 0.12361749]
[0.07203944 0.19570401 0.11178136 ... 0.05625525 0.20609994 0.13041474]
...
[0.09224506 0.09908539 0.13944311 ... 0.08630784 0.15009451 0.17172746]
[0.08499582 0.17338121 0.0804626 ... 0.04409525 0.27150458 0.07133815]
[0.05191234 0.11740112 0.08346355 ... 0.0842929 0.20141983 0.19982798]]