utils.py 文件源码

def load_dataset():
    if(not os.path.exists("./dataset/training.csv")):
        print("dataset does not exist")
        raise Exception

    #load dataset
    labeled_image = pd.read_csv("./dataset/training.csv")

    #preprocessing dataframe
    image = np.array(labeled_image["Image"].values).reshape(-1,1)
    image = np.apply_along_axis(lambda img: (img[0].split()),1,image)
    image = image.astype(np.int32) #because train_img elements are string before preprocessing
    image = image.reshape(-1,96*96) # data 96 * 96 size image

    label = labeled_image.values[:,:-1]
    label = label.astype(np.float32)

    #nan value to mean value
    col_mean = np.nanmean(label, axis=0)
    indices = np.where(np.isnan(label))
    label[indices] = np.take(col_mean, indices[1])

    return image, label