第六讲的主题是Neural Networks，这里总结第六讲以及第六次作业。

课程地址：https://cs50.harvard.edu/ai/

备注：图片均来自课程课件。

由于这一讲主要是神经网络的内容，课程内容的回顾在此从略，主要回顾project。

Project

Traffic

def load_data(data_dir):
    """
    Load image data from directory `data_dir`.

    Assume `data_dir` has one directory named after each category, numbered
    0 through NUM_CATEGORIES - 1. Inside each category directory will be some
    number of image files.

    Return tuple `(images, labels)`. `images` should be a list of all
    of the images in the data directory, where each image is formatted as a
    numpy ndarray with dimensions IMG_WIDTH x IMG_HEIGHT x 3. `labels` should
    be a list of integer labels, representing the categories for each of the
    corresponding `images`.
    """
    files = os.listdir(data_dir)
    images = []
    labels = []
    for file in files:
        path = os.path.join(data_dir, file)
        image_names = os.listdir(path)
        label = int(file)
        for image_name in image_names:
            image = cv2.imread(os.path.join(path, image_name)) / 255.0
            image = cv2.resize(image, (IMG_WIDTH, IMG_HEIGHT))
            images.append(image)
            labels.append(label)
    
    return images, labels


def get_model():
    """
    Returns a compiled convolutional neural network model. Assume that the
    `input_shape` of the first layer is `(IMG_WIDTH, IMG_HEIGHT, 3)`.
    The output layer should have `NUM_CATEGORIES` units, one for each category.
    """
    model = tf.keras.models.Sequential([
        tf.keras.layers.Conv2D(
            32, (3, 3), activation='relu', input_shape=(IMG_WIDTH, IMG_HEIGHT, 3)
            ),
        
        tf.keras.layers.MaxPooling2D(pool_size=(2, 2)),
        tf.keras.layers.Flatten(),
        
        tf.keras.layers.Dense(128, activation="relu"),
        tf.keras.layers.Dropout(0.5),
        
        tf.keras.layers.Dense(NUM_CATEGORIES, activation="softmax")
        ])
    
    model.compile(
        optimizer="adam",
        loss="categorical_crossentropy",
        metrics=["accuracy"]
        )
    
    return model