深度学习中图片处理经常用到的预处理代码：

……
    if mode == 'tf':
        x /= 127.5
        x -= 1.
        if x.ndim == 3:
            x = np.expand_dims(x, 0)
        return x
    
    if mode == 'custom':
        x /= 255
        if x.ndim == 3:
            x = np.expand_dims(x, 0)
        return x
    
    if mode == 'torch':
        x /= 255.
        mean = [0.485, 0.456, 0.406]
        std = [0.229, 0.224, 0.225]

在之前要加一句类型转换，否则会报错：TypeError: ufunc ‘true_divide’ output (typecode ‘d’) could not be coerced to provided output parameter (typecode ‘B’) according to the casting rule ‘‘same_kind’’

x = x.astype(np.float32)