tools/align_resize.py

import mmcv
import numpy as np
from mmcv.utils import deprecated_api_warning, is_tuple_of
from numpy import random

from mmseg.datasets.builder import PIPELINES
from IPython import embed

@PIPELINES.register_module()
class AlignResize(object):
    """Resize images & seg. Align
    """

    def __init__(self,
                 img_scale=None,
                 multiscale_mode='range',
                 ratio_range=None,
                 keep_ratio=True,
                 size_divisor=32):
        if img_scale is None:
            self.img_scale = None
        else:
            if isinstance(img_scale, list):
                self.img_scale = img_scale
            else:
                self.img_scale = [img_scale]
            assert mmcv.is_list_of(self.img_scale, tuple)

        if ratio_range is not None:
            # mode 1: given img_scale=None and a range of image ratio
            # mode 2: given a scale and a range of image ratio
            assert self.img_scale is None or len(self.img_scale) == 1
        else:
            # mode 3 and 4: given multiple scales or a range of scales
            assert multiscale_mode in ['value', 'range']

        self.multiscale_mode = multiscale_mode
        self.ratio_range = ratio_range
        self.keep_ratio = keep_ratio
        self.size_divisor = size_divisor

    @staticmethod
    def random_select(img_scales):
        """Randomly select an img_scale from given candidates.
        Args:
            img_scales (list[tuple]): Images scales for selection.
        Returns:
            (tuple, int): Returns a tuple ``(img_scale, scale_dix)``,
                where ``img_scale`` is the selected image scale and
                ``scale_idx`` is the selected index in the given candidates.
        """

        assert mmcv.is_list_of(img_scales, tuple)
        scale_idx = np.random.randint(len(img_scales))
        img_scale = img_scales[scale_idx]
        return img_scale, scale_idx

    @staticmethod
    def random_sample(img_scales):
        """Randomly sample an img_scale when ``multiscale_mode=='range'``.
        Args:
            img_scales (list[tuple]): Images scale range for sampling.
                There must be two tuples in img_scales, which specify the lower
                and uper bound of image scales.
        Returns:
            (tuple, None): Returns a tuple ``(img_scale, None)``, where
                ``img_scale`` is sampled scale and None is just a placeholder
                to be consistent with :func:`random_select`.
        """

        assert mmcv.is_list_of(img_scales, tuple) and len(img_scales) == 2
        img_scale_long = [max(s) for s in img_scales]
        img_scale_short = [min(s) for s in img_scales]
        long_edge = np.random.randint(
            min(img_scale_long),
            max(img_scale_long) + 1)
        short_edge = np.random.randint(
            min(img_scale_short),
            max(img_scale_short) + 1)
        img_scale = (long_edge, short_edge)
        return img_scale, None

    @staticmethod
    def random_sample_ratio(img_scale, ratio_range):
        """Randomly sample an img_scale when ``ratio_range`` is specified.
        A ratio will be randomly sampled from the range specified by
        ``ratio_range``. Then it would be multiplied with ``img_scale`` to
        generate sampled scale.
        Args:
            img_scale (tuple): Images scale base to multiply with ratio.
            ratio_range (tuple[float]): The minimum and maximum ratio to scale
                the ``img_scale``.
        Returns:
            (tuple, None): Returns a tuple ``(scale, None)``, where
                ``scale`` is sampled ratio multiplied with ``img_scale`` and
                None is just a placeholder to be consistent with
                :func:`random_select`.
        """

        assert isinstance(img_scale, tuple) and len(img_scale) == 2
        min_ratio, max_ratio = ratio_range
        assert min_ratio <= max_ratio
        ratio = np.random.random_sample() * (max_ratio - min_ratio) + min_ratio
        scale = int(img_scale[0] * ratio), int(img_scale[1] * ratio)
        return scale, None

    def _random_scale(self, results):
        """Randomly sample an img_scale according to ``ratio_range`` and
        ``multiscale_mode``.
        If ``ratio_range`` is specified, a ratio will be sampled and be
        multiplied with ``img_scale``.
        If multiple scales are specified by ``img_scale``, a scale will be
        sampled according to ``multiscale_mode``.
        Otherwise, single scale will be used.
        Args:
            results (dict): Result dict from :obj:`dataset`.
        Returns:
            dict: Two new keys 'scale` and 'scale_idx` are added into
                ``results``, which would be used by subsequent pipelines.
        """

        if self.ratio_range is not None:
            if self.img_scale is None:
                h, w = results['img'].shape[:2]
                scale, scale_idx = self.random_sample_ratio((w, h),
                                                            self.ratio_range)
            else:
                scale, scale_idx = self.random_sample_ratio(
                    self.img_scale[0], self.ratio_range)
        elif len(self.img_scale) == 1:
            scale, scale_idx = self.img_scale[0], 0
        elif self.multiscale_mode == 'range':
            scale, scale_idx = self.random_sample(self.img_scale)
        elif self.multiscale_mode == 'value':
            scale, scale_idx = self.random_select(self.img_scale)
        else:
            raise NotImplementedError

        results['scale'] = scale
        results['scale_idx'] = scale_idx

    def _align(self, img, size_divisor, interpolation=None):
        align_h = int(np.ceil(img.shape[0] / size_divisor)) * size_divisor
        align_w = int(np.ceil(img.shape[1] / size_divisor)) * size_divisor
        if interpolation == None:
            img = mmcv.imresize(img, (align_w, align_h))
        else:
            img = mmcv.imresize(img, (align_w, align_h), interpolation=interpolation)
        return img

    def _resize_img(self, results):
        """Resize images with ``results['scale']``."""
        if self.keep_ratio:
            img, scale_factor = mmcv.imrescale(
                results['img'], results['scale'], return_scale=True)
            #### align ####
            img = self._align(img, self.size_divisor)
            # the w_scale and h_scale has minor difference
            # a real fix should be done in the mmcv.imrescale in the future
            new_h, new_w = img.shape[:2]
            h, w = results['img'].shape[:2]
            w_scale = new_w / w
            h_scale = new_h / h
        else:
            img, w_scale, h_scale = mmcv.imresize(
                results['img'], results['scale'], return_scale=True)

            h, w = img.shape[:2]
            assert int(np.ceil(h / self.size_divisor)) * self.size_divisor == h and \
                   int(np.ceil(w / self.size_divisor)) * self.size_divisor == w, \
                   "img size not align. h:{} w:{}".format(h,w)
        scale_factor = np.array([w_scale, h_scale, w_scale, h_scale],
                                dtype=np.float32)
        results['img'] = img
        results['img_shape'] = img.shape
        results['pad_shape'] = img.shape  # in case that there is no padding
        results['scale_factor'] = scale_factor
        results['keep_ratio'] = self.keep_ratio

    def _resize_seg(self, results):
        """Resize semantic segmentation map with ``results['scale']``."""
        for key in results.get('seg_fields', []):
            if self.keep_ratio:
                gt_seg = mmcv.imrescale(
                    results[key], results['scale'], interpolation='nearest')
                gt_seg = self._align(gt_seg, self.size_divisor, interpolation='nearest')
            else:
                gt_seg = mmcv.imresize(
                    results[key], results['scale'], interpolation='nearest')
                h, w = gt_seg.shape[:2]
                assert int(np.ceil(h / self.size_divisor)) * self.size_divisor == h and \
                       int(np.ceil(w / self.size_divisor)) * self.size_divisor == w, \
                    "gt_seg size not align. h:{} w:{}".format(h, w)
            results[key] = gt_seg

    def __call__(self, results):
        """Call function to resize images, bounding boxes, masks, semantic
        segmentation map.
        Args:
            results (dict): Result dict from loading pipeline.
        Returns:
            dict: Resized results, 'img_shape', 'pad_shape', 'scale_factor',
                'keep_ratio' keys are added into result dict.
        """

        if 'scale' not in results:
            self._random_scale(results)
        self._resize_img(results)
        self._resize_seg(results)
        return results

    def __repr__(self):
        repr_str = self.__class__.__name__
        repr_str += (f'(img_scale={self.img_scale}, '
                     f'multiscale_mode={self.multiscale_mode}, '
                     f'ratio_range={self.ratio_range}, '
                     f'keep_ratio={self.keep_ratio})')
        return repr_str