使用Sequential,Function API 构建简单CNN

Sequential

Sequential支持straightforward式的叠加中间层，他通过简单将每一层放置在当前最顶层来对中间层进行叠加，具体的内容可以参照官方文档

# GRADED FUNCTION: happyModel

def happyModel():
    """
    Implements the forward propagation for the binary classification model:
    ZEROPAD2D -> CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> FLATTEN -> DENSE
    
    Note that for simplicity and grading purposes, you'll hard-code all the values
    such as the stride and kernel (filter) sizes. 
    Normally, functions should take these values as function parameters.
    
    Arguments:
    None

    Returns:
    model -- TF Keras model (object containing the information for the entire training process) 
    """
    model = tf.keras.Sequential([
            ## ZeroPadding2D with padding 3, input shape of 64 x 64 x 3
            tfl.ZeroPadding2D(padding=3,input_shape=(64,64,3)),
            ## Conv2D with 32 7x7 filters and stride of 1
            tfl.Conv2D(filters=32,kernel_size=(7,7)),
            ## BatchNormalization for axis 3
            tfl.BatchNormalization(axis=3),
            ## ReLU
            tfl.ReLU(),
            ## Max Pooling 2D with default parameters
            tfl.MaxPool2D(),
            ## Flatten layer
            tfl.Flatten(),
            ## Dense layer with 1 unit for output & 'sigmoid' activation
            tfl.Dense(units=1,activation='sigmoid')
            # YOUR CODE STARTS HERE
            
            
            # YOUR CODE ENDS HERE
        ])
        # 简单按照顺序叠加
    return model

happy_model.fit(X_train, Y_train, epochs=10, batch_size=16)
happy_model.evaluate(X_test, Y_test)

Function API的简单使用

Function API可以更为灵活的神经网络结构，它需要一个或多个输入和输出。
关于它的使用，可以看作是构建一个计算图，在这其中，我们依然可以使用提供的各种layer模型。

# GRADED FUNCTION: convolutional_model

def convolutional_model(input_shape):
    """
    Implements the forward propagation for the model:
    CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> DENSE
    
    Note that for simplicity and grading purposes, you'll hard-code some values
    such as the stride and kernel (filter) sizes. 
    Normally, functions should take these values as function parameters.
    
    Arguments:
    input_img -- input dataset, of shape (input_shape)

    Returns:
    model -- TF Keras model (object containing the information for the entire training process) 
    """

    input_img = tf.keras.Input(shape=input_shape)
    ## CONV2D: 8 filters 4x4, stride of 1, padding 'SAME'
    # Z1 = None
    Z1 = tfl.Conv2D(filters=8,kernel_size=(4,4),padding='same',strides=(1,1))(input_img)
    ## RELU
    # A1 = None
    A1 = tfl.ReLU()(Z1)
    ## MAXPOOL: window 8x8, stride 8, padding 'SAME'
    # P1 = None
    P1 = tfl.MaxPool2D(pool_size=(8,8),strides=(8,8),padding='same')(A1)
    ## CONV2D: 16 filters 2x2, stride 1, padding 'SAME'
    # Z2 = None
    Z2 = tfl.Conv2D(filters=16,kernel_size=(2,2),strides=(1,1),padding='same')(P1)
    ## RELU
    # A2 = None
    A2 = tfl.ReLU()(Z2)
    ## MAXPOOL: window 4x4, stride 4, padding 'SAME'
    # P2 = None
    P2 = tfl.MaxPool2D(pool_size=(4,4),strides=(4,4),padding='same')(A2)
    ## FLATTEN
    # F = None
    F = tfl.Flatten()(P2)
    ## Dense layer
    ## 6 neurons in output layer. Hint: one of the arguments should be "activation='softmax'" 
    # outputs = None
    outputs = tfl.Dense(units=6,activation='softmax')(F)
    # YOUR CODE STARTS HERE
    
    
    # YOUR CODE ENDS HERE
    model = tf.keras.Model(inputs=input_img, outputs=outputs)
    return model

在最后，我们使用tf.keras.Modle将之实例化。

绘制loss曲线

# The history.history["loss"] entry is a dictionary with as many values as epochs that the
# model was trained on. 
df_loss_acc = pd.DataFrame(history.history)
df_loss= df_loss_acc[['loss','val_loss']]
df_loss.rename(columns={'loss':'train','val_loss':'validation'},inplace=True)
df_acc= df_loss_acc[['accuracy','val_accuracy']]
df_acc.rename(columns={'accuracy':'train','val_accuracy':'validation'},inplace=True)
df_loss.plot(title='Model loss',figsize=(12,8)).set(xlabel='Epoch',ylabel='Loss')
df_acc.plot(title='Model Accuracy',figsize=(12,8)).set(xlabel='Epoch',ylabel='Accuracy')