Class GroupRandomSizedCrop

src/data_loader/transform.py:209–253

Random crop the given PIL.Image to a random size of (0.08 to 1.0) of the original size and and a random aspect ratio of 3/4 to 4/3 of the original aspect ratio This is popularly used to train the Inception networks size: size of the smaller edge interpolation: Default: PIL.Image.BILI

class GroupRandomSizedCrop(object):
    """Random crop the given PIL.Image to a random size of (0.08 to 1.0) of the original size
    and and a random aspect ratio of 3/4 to 4/3 of the original aspect ratio
    This is popularly used to train the Inception networks
    size: size of the smaller edge
    interpolation: Default: PIL.Image.BILINEAR
    """
    def __init__(self, size, interpolation=Image.BILINEAR):
        self.size = size
        self.interpolation = interpolation

    def __call__(self, img_group):
        for attempt in range(10):
            area = img_group[0].size[0] * img_group[0].size[1]
            target_area = random.uniform(0.08, 1.0) * area
            aspect_ratio = random.uniform(3. / 4, 4. / 3)

            w = int(round(math.sqrt(target_area * aspect_ratio)))
            h = int(round(math.sqrt(target_area / aspect_ratio)))

            if random.random() < 0.5:
                w, h = h, w

            if w <= img_group[0].size[0] and h <= img_group[0].size[1]:
                x1 = random.randint(0, img_group[0].size[0] - w)
                y1 = random.randint(0, img_group[0].size[1] - h)
                found = True
                break
        else:
            found = False
            x1 = 0
            y1 = 0

        if found:
            out_group = list()
            for img in img_group:
                img = img.crop((x1, y1, x1 + w, y1 + h))
                assert(img.size == (w, h))
                out_group.append(img.resize((self.size, self.size), self.interpolation))
            return out_group
        else:
            # Fallback
            scale = GroupScale(self.size, interpolation=self.interpolation)
            crop = GroupRandomCrop(self.size)
            return crop(scale(img_group))


class Stack(object):