deeplabv3+源码之慢慢解析29 第五章utils文件夹(4)ext_transforms.py--ExtResize类，ExtColorJitter类，Lambda类和Compose类

系列文章目录（共五章33节已完结）

第一章deeplabv3+源码之慢慢解析 根目录(1)main.py–get_argparser函数
第一章deeplabv3+源码之慢慢解析 根目录(2)main.py–get_dataset函数
第一章deeplabv3+源码之慢慢解析 根目录(3)main.py–validate函数
第一章deeplabv3+源码之慢慢解析 根目录(4)main.py–main函数
第一章deeplabv3+源码之慢慢解析 根目录(5)predict.py–get_argparser函数和main函数

第二章deeplabv3+源码之慢慢解析 datasets文件夹(1)voc.py–voc_cmap函数和download_extract函数
第二章deeplabv3+源码之慢慢解析 datasets文件夹(2)voc.py–VOCSegmentation类
第二章deeplabv3+源码之慢慢解析 datasets文件夹(3)cityscapes.py–Cityscapes类
第二章deeplabv3+源码之慢慢解析 datasets文件夹(4)utils.py–6个小函数

第三章deeplabv3+源码之慢慢解析 metrics文件夹stream_metrics.py–StreamSegMetrics类和AverageMeter类

第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(a1)hrnetv2.py–4个函数和可执行代码
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(a2)hrnetv2.py–Bottleneck类和BasicBlock类
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(a3)hrnetv2.py–StageModule类
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(a4)hrnetv2.py–HRNet类
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(b1)mobilenetv2.py–2个类和2个函数
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(b2)mobilenetv2.py–MobileNetV2类和mobilenet_v2函数
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(c1)resnet.py–2个基础函数，BasicBlock类和Bottleneck类
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(c2)resnet.py–ResNet类和10个不同结构的调用函数
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(d1)xception.py–SeparableConv2d类和Block类
第四章deeplabv3+源码之慢慢解析 network文件夹(1)backbone文件夹(d2)xception.py–Xception类和xception函数
第四章deeplabv3+源码之慢慢解析 network文件夹(2)_deeplab.py–ASPP相关的4个类和1个函数
第四章deeplabv3+源码之慢慢解析 network文件夹(3)_deeplab.py–DeepLabV3类，DeepLabHeadV3Plus类和DeepLabHead类
第四章deeplabv3+源码之慢慢解析 network文件夹(4)modeling.py–5个私有函数（4个骨干网，1个模型载入）
第四章deeplabv3+源码之慢慢解析 network文件夹(5)modeling.py–12个调用函数
第四章deeplabv3+源码之慢慢解析 network文件夹(6)utils.py–_SimpleSegmentationModel类和IntermediateLayerGetter类

第五章deeplabv3+源码之慢慢解析 utils文件夹(1)ext_transforms.py.py–2个翻转类和ExtCompose类
第五章deeplabv3+源码之慢慢解析 utils文件夹(2)ext_transforms.py.py–2个裁剪类和2个缩放类
第五章deeplabv3+源码之慢慢解析 utils文件夹(3)ext_transforms.py.py–旋转类，填充类，张量转化类和标准化类
第五章deeplabv3+源码之慢慢解析 utils文件夹(4)ext_transforms.py.py–ExtResize类，ExtColorJitter类，Lambda类和Compose类
第五章deeplabv3+源码之慢慢解析 utils文件夹(5)loss.py–FocalLoss类
第五章deeplabv3+源码之慢慢解析 utils文件夹(6)scheduler.py–PolyLR类
第五章deeplabv3+源码之慢慢解析 utils文件夹(7)utils.py–去标准化，momentum设定，标准化层锁定和路径创建
第五章deeplabv3+源码之慢慢解析 utils文件夹(8)visualizer.py–Visualizer类（完结）

---

说明

提示：本节介绍ext_transforms.py中的ExtResize类，ExtColorJitter类，Lambda类和Compose类。

尺寸调整 ExtResize类

class ExtResize(object):  #重调尺寸。如果size=(h,w)则直接使用。如果size=a,则图像短边=a,长边按原来的宽高比进行调整。
    """Resize the input PIL Image to the given size.
    Args:
        size (sequence or int): Desired output size. If size is a sequence like
            (h, w), output size will be matched to this. If size is an int,
            smaller edge of the image will be matched to this number.
            i.e, if height > width, then image will be rescaled to
            (size * height / width, size)
        interpolation (int, optional): Desired interpolation. Default is
            ``PIL.Image.BILINEAR``
    """

    def __init__(self, size, interpolation=Image.BILINEAR):
        assert isinstance(size, int) or (isinstance(size, collections.Iterable) and len(size) == 2)
        self.size = size
        self.interpolation = interpolation

    def __call__(self, img, lbl):
        """
        Args:
            img (PIL Image): Image to be scaled.
        Returns:
            PIL Image: Rescaled image.
        """
        return F.resize(img, self.size, self.interpolation), F.resize(lbl, self.size, Image.NEAREST) #直接调用F.resize函数。

    def __repr__(self):
        interpolate_str = _pil_interpolation_to_str[self.interpolation]
        return self.__class__.__name__ + '(size={0}, interpolation={1})'.format(self.size, interpolate_str) 

颜色微调 ExtColorJitter类

class ExtColorJitter(object): #随机改变图片的亮度，对比度和饱和度，还有色调。
    """Randomly change the brightness, contrast and saturation of an image. 
    Args:
        brightness (float or tuple of float (min, max)): How much to jitter brightness.
            brightness_factor is chosen uniformly from [max(0, 1 - brightness), 1 + brightness]
            or the given [min, max]. Should be non negative numbers.
        contrast (float or tuple of float (min, max)): How much to jitter contrast.
            contrast_factor is chosen uniformly from [max(0, 1 - contrast), 1 + contrast]
            or the given [min, max]. Should be non negative numbers.
        saturation (float or tuple of float (min, max)): How much to jitter saturation.
            saturation_factor is chosen uniformly from [max(0, 1 - saturation), 1 + saturation]
            or the given [min, max]. Should be non negative numbers.
        hue (float or tuple of float (min, max)): How much to jitter hue.
            hue_factor is chosen uniformly from [-hue, hue] or the given [min, max].
            Should have 0<= hue <= 0.5 or -0.5 <= min <= max <= 0.5.
    """
    def __init__(self, brightness=0, contrast=0, saturation=0, hue=0):
        self.brightness = self._check_input(brightness, 'brightness')  #亮度
        self.contrast = self._check_input(contrast, 'contrast')       #对比度
        self.saturation = self._check_input(saturation, 'saturation')  #饱和度
        self.hue = self._check_input(hue, 'hue', center=0, bound=(-0.5, 0.5),
                                     clip_first_on_zero=False)   #色调

    def _check_input(self, value, name, center=1, bound=(0, float('inf')), clip_first_on_zero=True):
        if isinstance(value, numbers.Number):
            if value < 0:
                raise ValueError("If {} is a single number, it must be non negative.".format(name))
            value = [center - value, center + value] #取值范围value在center附近
            if clip_first_on_zero:
                value[0] = max(value[0], 0)
        elif isinstance(value, (tuple, list)) and len(value) == 2: #如果是tuple或者list，且长度为2，即输入是个大小值范围。
            if not bound[0] <= value[0] <= value[1] <= bound[1]: #value的大小范围不能超过bound的大小范围。
                raise ValueError("{} values should be between {}".format(name, bound))
        else:
            raise TypeError("{} should be a single number or a list/tuple with lenght 2.".format(name))

        # if value is 0 or (1., 1.) for brightness/contrast/saturation
        # or (0., 0.) for hue, do nothing
        if value[0] == value[1] == center: #如果波动为0，则value=None
            value = None
        return value

    @staticmethod
    def get_params(brightness, contrast, saturation, hue):
        """Get a randomized transform to be applied on image.
        Arguments are same as that of __init__.
        Returns:
            Transform which randomly adjusts brightness, contrast and
            saturation in a random order.
        """
        transforms = []

        if brightness is not None:
            brightness_factor = random.uniform(brightness[0], brightness[1]) #在brightness[0]和brightness[1]之间随机选择brightness_factor。
            transforms.append(Lambda(lambda img: F.adjust_brightness(img, brightness_factor)))  #调用F.adjust_brightness调整亮度。

        if contrast is not None:    #同上，调整对比度
            contrast_factor = random.uniform(contrast[0], contrast[1])
            transforms.append(Lambda(lambda img: F.adjust_contrast(img, contrast_factor)))

        if saturation is not None: #同上，调整饱和度
            saturation_factor = random.uniform(saturation[0], saturation[1])
            transforms.append(Lambda(lambda img: F.adjust_saturation(img, saturation_factor)))

        if hue is not None:  #同上，调整色度
            hue_factor = random.uniform(hue[0], hue[1])
            transforms.append(Lambda(lambda img: F.adjust_hue(img, hue_factor)))

        random.shuffle(transforms)  #重调transforms的顺序。
        transform = Compose(transforms)  #即新的转化操作组合。

        return transform

    def __call__(self, img, lbl):
        """
        Args:
            img (PIL Image): Input image.
        Returns:
            PIL Image: Color jittered image.
        """
        transform = self.get_params(self.brightness, self.contrast,
                                    self.saturation, self.hue)  #得到转换操作。
        return transform(img), lbl     #对输入img进行转换操作，标签不变。

    def __repr__(self):
        format_string = self.__class__.__name__ + '('
        format_string += 'brightness={0}'.format(self.brightness)
        format_string += ', contrast={0}'.format(self.contrast)
        format_string += ', saturation={0}'.format(self.saturation)
        format_string += ', hue={0})'.format(self.hue)
        return format_string

自定义功能 Lambda类

class Lambda(object):  #自定义lambda转换功能，调用使用。供ExtColorJitter类调用。
    """Apply a user-defined lambda as a transform.
    Args:
        lambd (function): Lambda/function to be used for transform.
    """

    def __init__(self, lambd):
        assert callable(lambd), repr(type(lambd).__name__) + " object is not callable"
        self.lambd = lambd

    def __call__(self, img):
        return self.lambd(img)

    def __repr__(self):
        return self.__class__.__name__ + '()'

功能组合 Compose类

class Compose(object):  #多操作组合，与ExtCompose不同，只对输入的img进行操作。供ExtColorJitter类调用。
    """Composes several transforms together.
    Args:
        transforms (list of ``Transform`` objects): list of transforms to compose.
    Example:
        >>> transforms.Compose([
        >>>     transforms.CenterCrop(10),
        >>>     transforms.ToTensor(),
        >>> ])
    """

    def __init__(self, transforms):
        self.transforms = transforms

    def __call__(self, img):
        for t in self.transforms:
            img = t(img)
        return img

    def __repr__(self):
        format_string = self.__class__.__name__ + '('
        for t in self.transforms:
            format_string += '\n'
            format_string += '    {0}'.format(t)
        format_string += '\n)'
        return format_string

Tips

1. Lambda类和Compose类是为ExtColorJitter类服务的。至此，ext_transforms.py内容结束。
2. 下一个节介绍loss.py中的内容。