util.py 文件源码

def load_data(test=False):
    fname = FTEST if test else FTRAIN
    df = pd.read_csv(fname)

    cols = df.columns[:-1]

    df['Image'] = df['Image'].apply(lambda im: np.fromstring(im, sep=' ') / 255.0)
    df = df.dropna()

    X = np.vstack(df['Image'])
    X = X.reshape(-1, IMAGE_SIZE, IMAGE_SIZE, 1)
    if not test:
        # y = (df[cols].values -48) / 48.0
        y = df[cols].values / 96.0
        X, y = shuffle(X, y)
        joblib.dump(cols, 'data/cols.pkl', compress=3)

    else:
        y = None
    return X, y