图像预处理相关代码学习

1.数据增强

def augment(*args, hflip=True, rot=True):
    hflip = hflip and random.random() < 0.5
    vflip = rot and random.random() < 0.5
    rot90 = rot and random.random() < 0.5
#三种操作执行概率均为50%

    def _augment(img):
        if hflip: img = img[:, ::-1, :]
        if vflip: img = img[::-1, :, :]
        if rot90: img = img.transpose(1, 0, 2)
        
        return img

    return [_augment(a) for a in args]

random模块详解
and
关于[::-1]的讲解
参考一
参考二
参考三
transpose 详解
*args、**args

2.数据类型转换

def np2Tensor(*args, rgb_range=255):
    def _np2Tensor(img):
        np_transpose = np.ascontiguousarray(img.transpose((2, 0, 1)))
        tensor = torch.from_numpy(np_transpose).float()
        tensor.mul_(rgb_range / 255) 

        return tensor

np.ascontiguousarray()
torch.from_numpy(x)

    def mul_(self, value): # real signature unknown; restored from __doc__
        """
        mul_(value)
        
        In-place version of :meth:`~Tensor.mul`
        """
        pass

3.通道设置

def set_channel(*args, n_channels=3):
    def _set_channel(img):
        if img.ndim == 2:
            img = np.expand_dims(img, axis=2)

        c = img.shape[2]#通道数
        if n_channels == 1 and c == 3:
            img = np.expand_dims(sc.rgb2ycbcr(img)[:, :, 0], 2)
        elif n_channels == 3 and c == 1:
            img = np.concatenate([img] * n_channels, 2)

        return img

    return [_set_channel(a) for a in args]

sc.rgb2ycbcr(img)[:, :, 0]表示y通道
np.concatenate( )& np.append( )
np.expand_dims()
np中维度的理解和np.expand_dims
numpy的维度和括号[]联系，以及np.expand_dims解释

4.图像块的获取

def get_patch(*args, patch_size=96, scale=2, multi=False, input_large=False):
    ih, iw = args[0].shape[:2]

    if not input_large:
        p = scale if multi else 1
        tp = p * patch_size
        ip = tp // scale
    else:
        tp = patch_size
        ip = patch_size

    ix = random.randrange(0, iw - ip + 1)
    iy = random.randrange(0, ih - ip + 1)

    if not input_large:
        tx, ty = scale * ix, scale * iy
    else:
        tx, ty = ix, iy

    ret = [
        args[0][iy:iy + ip, ix:ix + ip, :],
        *[a[ty:ty + tp, tx:tx + tp, :] for a in args[1:]] #?
    ]

    return ret

shape[:2]相关问题
random.randrange
获取图像快
crop方法