Transfer Learning with MobileNetV2（吴恩达课程）

Transfer Learning with MobileNetV2（吴恩达课程）

# UNQ_C1
# GRADED FUNCTION: data_augmenter
def data_augmenter():
    '''
    Create a Sequential model composed of 2 layers
    Returns:
        tf.keras.Sequential
    '''
    ### START CODE HERE
    data_augmentation = tf.keras.Sequential()
    data_augmentation.add(RandomFlip('horizontal'))
    data_augmentation.add(RandomRotation(0.2))
    ### END CODE HERE
    
    return data_augmentation

# UNQ_C2
# GRADED FUNCTION
def alpaca_model(image_shape=IMG_SIZE, data_augmentation=data_augmenter()):
    ''' Define a tf.keras model for binary classification out of the MobileNetV2 model
    Arguments:
        image_shape -- Image width and height
        data_augmentation -- data augmentation function
    Returns:
    Returns:
        tf.keras.model
    '''
    
    
    input_shape = image_shape + (3,)
    
    ### START CODE HERE
    base_model = tf.keras.applications.MobileNetV2(input_shape=input_shape,
                                                   include_top=False, # <== Important!!!!
                                                   weights='imagenet') # From imageNet
    # Freeze the base model by making it non trainable
    base_model.trainable = False

    # create the input layer (Same as the imageNetv2 input size)
    inputs = tf.keras.Input(shape=input_shape)
    
    # apply data augmentation to the inputs
    x = data_augmentation(inputs)
    
    # data preprocessing using the same weights the model was trained on
    x = tf.keras.applications.mobilenet_v2.preprocess_input(x)
    
    # set training to False to avoid keeping track of statistics in the batch norm layer
    x = base_model(x, training=False) 
    
    # Add the new Binary classification layers
    # use global avg pooling to summarize the info in each channel
    x = tfl.GlobalAveragePooling2D()(x) 
    #include dropout with probability of 0.2 to avoid overfitting
    x = tfl.Dropout(rate=0.2)(x)
        
    # create a prediction layer with one neuron (as a classifier only needs one)
    prediction_layer = tfl.Dense(1)
    
    ### END CODE HERE
    outputs = prediction_layer(x) 
    model = tf.keras.Model(inputs, outputs)
    
    return model

# UNQ_C3
base_model = model2.layers[4]
base_model.trainable = True
# Let's take a look to see how many layers are in the base model
print("Number of layers in the base model: ", len(base_model.layers))

# Fine-tune from this layer onwards
fine_tune_at = 120

### START CODE HERE

# Freeze all the layers before the `fine_tune_at` layer
for layer in base_model.layers[:fine_tune_at]:
    layer.trainable = True
    
# Define a BinaryCrossentropy loss function. Use from_logits=True
loss_function=tf.python.keras.losses.BinaryCrossentropy(from_logits=True)
# Define an Adam optimizer with a learning rate of 0.1 * base_learning_rate
optimizer = tf.keras.optimizers.Adam(lr=base_learning_rate*0.1)
# Use accuracy as evaluation metric
metrics=['accuracy']
### END CODE HERE

model2.compile(loss=loss_function,
              optimizer = optimizer,
              metrics=metrics)