custom_transforms.py

# Copyright 2020 Huawei Technologies Co., Ltd
#
# Licensed under the Apache License, Version 2.0 (the License);
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# httpwww.apache.orglicensesLICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an AS IS BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Random process dataset."""
import random

import numpy as np
from PIL import Image, ImageOps, ImageFilter


class Normalize:
    """Normalize a tensor image with mean and standard deviation.
    Args:
        mean (tuple): means for each channel.
        std (tuple): standard deviations for each channel.
    """

    def __init__(self, mean=(0., 0., 0.), std=(1., 1., 1.)):
        self.mean = mean
        self.std = std

    def __call__(self, img, mask):
        img = np.array(img).astype(np.float32)
        mask = np.array(mask).astype(np.float32)
        img = ((img - self.mean) / self.std).astype(np.float32)

        return img, mask


class RandomHorizontalFlip:
    """Randomly decide whether to horizontal flip."""
    def __call__(self, img, mask):
        if random.random() < 0.5:
            img = img.transpose(Image.FLIP_LEFT_RIGHT)
            mask = mask.transpose(Image.FLIP_LEFT_RIGHT)

        return img, mask


class RandomRotate:
    """
    Randomly decide whether to rotate.

    Args:
        degree (float): The degree of rotate.
    """
    def __init__(self, degree):
        self.degree = degree

    def __call__(self, img, mask):
        rotate_degree = random.uniform(-1 * self.degree, self.degree)
        img = img.rotate(rotate_degree, Image.BILINEAR)
        mask = mask.rotate(rotate_degree, Image.NEAREST)

        return img, mask


class RandomGaussianBlur:
    """Randomly decide whether to filter image with gaussian blur."""
    def __call__(self, img, mask):
        if random.random() < 0.5:
            img = img.filter(ImageFilter.GaussianBlur(
                radius=random.random()))

        return img, mask


class RandomScaleCrop:
    """Randomly decide whether to scale and crop image."""
    def __init__(self, base_size, crop_size, fill=0):
        self.base_size = base_size
        self.crop_size = crop_size
        self.fill = fill

    def __call__(self, img, mask):
        # random scale (short edge)
        short_size = random.randint(int(self.base_size * 0.5), int(self.base_size * 2.0))
        w, h = img.size
        if h > w:
            ow = short_size
            oh = int(1.0 * h * ow / w)
        else:
            oh = short_size
            ow = int(1.0 * w * oh / h)
        img = img.resize((ow, oh), Image.BILINEAR)
        mask = mask.resize((ow, oh), Image.NEAREST)
        # pad crop
        if short_size < self.crop_size:
            padh = self.crop_size - oh if oh < self.crop_size else 0
            padw = self.crop_size - ow if ow < self.crop_size else 0
            img = ImageOps.expand(img, border=(0, 0, padw, padh), fill=0)
            mask = ImageOps.expand(mask, border=(0, 0, padw, padh), fill=self.fill)
        # random crop crop_size
        w, h = img.size
        x1 = random.randint(0, w - self.crop_size)
        y1 = random.randint(0, h - self.crop_size)
        img = img.crop((x1, y1, x1 + self.crop_size, y1 + self.crop_size))
        mask = mask.crop((x1, y1, x1 + self.crop_size, y1 + self.crop_size))

        return img, mask


class FixScaleCrop:
    """Scale and crop image with fixing size."""
    def __init__(self, crop_size):
        self.crop_size = crop_size

    def __call__(self, img, mask):
        w, h = img.size
        if w > h:
            oh = self.crop_size
            ow = int(1.0 * w * oh / h)
        else:
            ow = self.crop_size
            oh = int(1.0 * h * ow / w)
        img = img.resize((ow, oh), Image.BILINEAR)
        mask = mask.resize((ow, oh), Image.NEAREST)
        # center crop
        w, h = img.size
        x1 = int(round((w - self.crop_size) / 2.))
        y1 = int(round((h - self.crop_size) / 2.))
        img = img.crop((x1, y1, x1 + self.crop_size, y1 + self.crop_size))
        mask = mask.crop((x1, y1, x1 + self.crop_size, y1 + self.crop_size))

        return img, mask


class FixedResize:
    """Resize image with fixing size."""
    def __init__(self, size):
        self.size = (size, size)

    def __call__(self, img, mask):
        assert img.size == mask.size

        img = img.resize(self.size, Image.BILINEAR)
        mask = mask.resize(self.size, Image.NEAREST)
        return img, mask