Data Preparation

train="SPORT_1/train"
test="SPORT_1/test"

filepaths_train = list(glob.glob(train+'/**/*.jpg'))
filepaths_test = list(glob.glob(test+'/**/*.jpg'))

def proc_img(filepath):
    """ Create a DataFrame with the filepath and the labels of the pictures
    """

    labels = list(map(lambda x: os.path.split(os.path.split(x)[0])[1], filepath))

    filepath = pd.Series(filepath, name='Filepath').astype(str)
    labels = pd.Series(labels, name='Label')

    # Concatenate filepaths and labels
    df = pd.concat([filepath, labels], axis=1)

train_df = proc_img(filepaths_train)
test_df = proc_img(filepaths_test)

print(f'Number of training pictures: {train_df.shape[0]}')
print(f'Number of test pictures: {test_df.shape[0]}')

    # Shuffle the DataFrame and reset index
    df = df.sample(frac=1).reset_index(drop = True)
    
    return df