函数式API

## 示例一：

## 1. 导入依赖包

```python
from tensorflow import keras
from tensorflow.keras import layers
import matplotlib.pyplot as plt
```

## 2. 导入数据集并对其进行归一化

```python
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = x_train.reshape(60000, 784).astype('float32') / 255
x_test = x_test.reshape(10000, 784).astype('float32') / 255
```

## 3. 用函数式API进行模型搭建

```python
inputs = keras.Input(shape=(784,))
dense = layers.Dense(64, activation='relu')
x = dense(inputs)
x = layers.Dense(64, activation='relu')(x)
outputs = layers.Dense(10)(x)
```

```python
model = keras.Model(inputs=inputs, outputs=outputs)
model.summary()
keras.utils.plot_model(model, 'model_info.png', show_shapes=True)
```

## 4. 定义模型损失函数、优化器和评价指标

```python
model.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer=keras.optimizers.Adam(),
    metrics=['acc']
)
```

## 5. 对模型进行训练

```python
history = model.fit(x_train, y_train, batch_size=64, epochs=5, validation_split=0.2)
```

## 6. 用测试集测试模型准确率

```python
test_scores = model.evaluate(x_test, y_test, verbose=2)
print('Test loss:', test_scores[0])
print('Test accuracy:', test_scores[1])
```

## 7. 绘制模型的损失变化曲线和准确率变化曲线

```python
print(history.history.keys())
plt.plot(history.epoch, history.history.get('loss'), label='loss')
plt.plot(history.epoch, history.history.get('val_loss'), label='val_loss')
plt.legend()
plt.show()
```

```python
plt.plot(history.epoch, history.history.get('acc'), label='acc')
plt.plot(history.epoch, history.history.get('val_acc'), label='val_acc')
plt.legend()
plt.show()
```

## 示例二：

```python
from tensorflow import keras
from tensorflow.keras import layers
import matplotlib.pyplot as plt

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

x_train = x_train / 255.0
x_test = x_test / 255.0

inputs = keras.Input(shape=(28, 28))
x = keras.layers.Flatten()(inputs)
x = layers.Dense(64, activation='relu')(x)
x = layers.Dense(64, activation='relu')(x)
outputs = layers.Dense(10, activation='softmax')(x)

model = keras.Model(inputs=inputs, outputs=outputs)
model.summary()
keras.utils.plot_model(model, 'model_info.png', show_shapes=True)

model.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer=keras.optimizers.Adam(),
    metrics=['acc']
)

history = model.fit(x_train, y_train, batch_size=64, epochs=5, validation_split=0.2)

test_scores = model.evaluate(x_test, y_test, verbose=2)
print('Test loss:', test_scores[0])
print('Test accuracy:', test_scores[1])

print(history.history.keys())
plt.plot(history.epoch, history.history.get('loss'), label='loss')
plt.plot(history.epoch, history.history.get('val_loss'), label='val_loss')
plt.legend()
plt.show()

plt.plot(history.epoch, history.history.get('acc'), label='acc')
plt.plot(history.epoch, history.history.get('val_acc'), label='val_acc')
plt.legend()
plt.show()
```

## 示例三：

```python
input1 = keras.Input(shape=(28, 28))
input2 = keras.Input(shape=(28, 28))

x1 = keras.layers.Flatten()(input1)
x2 = keras.layers.Flatten()(input2)

x = keras.layers.concatenate([x1, x2])
x = keras.layers.Dense(32, activation='relu')(x)
output = keras.layers.Dense(1, activation='sigmoid')(x)
model = keras.Model(inputs=[input1, input2], outputs=output)
print(model.summary())
```