import mmcv
import numpy as np
from numpy import random
from ..builder import PIPELINES
@PIPELINES.register_module()
class Resize(object):
"""Resize images & seg.
This transform resizes the input image to some scale. If the input dict
contains the key "scale", then the scale in the input dict is used,
otherwise the specified scale in the init method is used.
``img_scale`` can either be a tuple (single-scale) or a list of tuple
(multi-scale). There are 3 multiscale modes:
- ``ratio_range is not None``: randomly sample a ratio from the ratio range
and multiply it with the image scale.
- ``ratio_range is None and multiscale_mode == "range"``: randomly sample a
scale from the a range.
- ``ratio_range is None and multiscale_mode == "value"``: randomly sample a
scale from multiple scales.
Args:
img_scale (tuple or list[tuple]): Images scales for resizing.
multiscale_mode (str): Either "range" or "value".
ratio_range (tuple[float]): (min_ratio, max_ratio)
keep_ratio (bool): Whether to keep the aspect ratio when resizing the
image.
"""
def __init__(self,
img_scale=None,
multiscale_mode='range',
ratio_range=None,
keep_ratio=True):
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 a scale and a range of image ratio
assert len(self.img_scale) == 1
else:
# mode 2: 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
@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:
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 _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)
# 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)
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')
else:
gt_seg = mmcv.imresize(
results[key], results['scale'], interpolation='nearest')
results['gt_semantic_seg'] = 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
@PIPELINES.register_module()
class RandomFlip(object):
"""Flip the image & seg.
If the input dict contains the key "flip", then the flag will be used,
otherwise it will be randomly decided by a ratio specified in the init
method.
Args:
flip_ratio (float, optional): The flipping probability. Default: None.
direction(str, optional): The flipping direction. Options are
'horizontal' and 'vertical'. Default: 'horizontal'.
"""
def __init__(self, flip_ratio=None, direction='horizontal'):
self.flip_ratio = flip_ratio
self.direction = direction
if flip_ratio is not None:
assert flip_ratio >= 0 and flip_ratio <= 1
assert direction in ['horizontal', 'vertical']
def __call__(self, results):
"""Call function to flip bounding boxes, masks, semantic segmentation
maps.
Args:
results (dict): Result dict from loading pipeline.
Returns:
dict: Flipped results, 'flip', 'flip_direction' keys are added into
result dict.
"""
if 'flip' not in results:
flip = True if np.random.rand() < self.flip_ratio else False
results['flip'] = flip
if 'flip_direction' not in results:
results['flip_direction'] = self.direction
if results['flip']:
# flip image
results['img'] = mmcv.imflip(
results['img'], direction=results['flip_direction'])
# flip segs
for key in results.get('seg_fields', []):
# use copy() to make numpy stride positive
results[key] = mmcv.imflip(
results[key], direction=results['flip_direction']).copy()
return results
def __repr__(self):
return self.__class__.__name__ + f'(flip_ratio={self.flip_ratio})'
@PIPELINES.register_module()
class Pad(object):
"""Pad the image & mask.
There are two padding modes: (1) pad to a fixed size and (2) pad to the
minimum size that is divisible by some number.
Added keys are "pad_shape", "pad_fixed_size", "pad_size_divisor",
Args:
size (tuple, optional): Fixed padding size.
size_divisor (int, optional): The divisor of padded size.
pad_val (float, optional): Padding value. Default: 0.
seg_pad_val (float, optional): Padding value of segmentation map.
Default: 255.
"""
def __init__(self,
size=None,
size_divisor=None,
pad_val=0,
seg_pad_val=255):
self.size = size
self.size_divisor = size_divisor
self.pad_val = pad_val
self.seg_pad_val = seg_pad_val
# only one of size and size_divisor should be valid
assert size is not None or size_divisor is not None
assert size is None or size_divisor is None
def _pad_img(self, results):
"""Pad images according to ``self.size``."""
if self.size is not None:
padded_img = mmcv.impad(
results['img'], shape=self.size, pad_val=self.pad_val)
elif self.size_divisor is not None:
padded_img = mmcv.impad_to_multiple(
results['img'], self.size_divisor, pad_val=self.pad_val)
results['img'] = padded_img
results['pad_shape'] = padded_img.shape
results['pad_fixed_size'] = self.size
results['pad_size_divisor'] = self.size_divisor
def _pad_seg(self, results):
"""Pad masks according to ``results['pad_shape']``."""
for key in results.get('seg_fields', []):
results[key] = mmcv.impad(
results[key],
shape=results['pad_shape'][:2],
pad_val=self.seg_pad_val)
def __call__(self, results):
"""Call function to pad images, masks, semantic segmentation maps.
Args:
results (dict): Result dict from loading pipeline.
Returns:
dict: Updated result dict.
"""
self._pad_img(results)
self._pad_seg(results)
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(size={self.size}, size_divisor={self.size_divisor}, ' \
f'pad_val={self.pad_val})'
return repr_str
@PIPELINES.register_module()
class Normalize(object):
"""Normalize the image.
Added key is "img_norm_cfg".
Args:
mean (sequence): Mean values of 3 channels.
std (sequence): Std values of 3 channels.
to_rgb (bool): Whether to convert the image from BGR to RGB,
default is true.
"""
def __init__(self, mean, std, to_rgb=True):
self.mean = np.array(mean, dtype=np.float32)
self.std = np.array(std, dtype=np.float32)
self.to_rgb = to_rgb
def __call__(self, results):
"""Call function to normalize images.
Args:
results (dict): Result dict from loading pipeline.
Returns:
dict: Normalized results, 'img_norm_cfg' key is added into
result dict.
"""
results['img'] = mmcv.imnormalize(results['img'], self.mean, self.std,
self.to_rgb)
results['img_norm_cfg'] = dict(
mean=self.mean, std=self.std, to_rgb=self.to_rgb)
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(mean={self.mean}, std={self.std}, to_rgb=' \
f'{self.to_rgb})'
return repr_str
@PIPELINES.register_module()
class RandomCrop(object):
"""Random crop the image & seg.
Args:
crop_size (tuple): Expected size after cropping, (h, w).
cat_max_ratio (float): The maximum ratio that single category could
occupy.
"""
def __init__(self, crop_size, cat_max_ratio=1., ignore_index=255):
assert crop_size[0] > 0 and crop_size[1] > 0
self.crop_size = crop_size
self.cat_max_ratio = cat_max_ratio
self.ignore_index = ignore_index
def get_crop_bbox(self, img):
"""Randomly get a crop bounding box."""
margin_h = max(img.shape[0] - self.crop_size[0], 0)
margin_w = max(img.shape[1] - self.crop_size[1], 0)
offset_h = np.random.randint(0, margin_h + 1)
offset_w = np.random.randint(0, margin_w + 1)
crop_y1, crop_y2 = offset_h, offset_h + self.crop_size[0]
crop_x1, crop_x2 = offset_w, offset_w + self.crop_size[1]
return crop_y1, crop_y2, crop_x1, crop_x2
def crop(self, img, crop_bbox):
"""Crop from ``img``"""
crop_y1, crop_y2, crop_x1, crop_x2 = crop_bbox
img = img[crop_y1:crop_y2, crop_x1:crop_x2, ...]
return img
def __call__(self, results):
"""Call function to randomly crop images, semantic segmentation maps.
Args:
results (dict): Result dict from loading pipeline.
Returns:
dict: Randomly cropped results, 'img_shape' key in result dict is
updated according to crop size.
"""
img = results['img']
crop_bbox = self.get_crop_bbox(img)
if self.cat_max_ratio < 1.:
# Repeat 10 times
for _ in range(10):
seg_temp = self.crop(results['gt_semantic_seg'], crop_bbox)
labels, cnt = np.unique(seg_temp, return_counts=True)
cnt = cnt[labels != self.ignore_index]
if len(cnt) > 1 and np.max(cnt) / np.sum(
cnt) < self.cat_max_ratio:
break
crop_bbox = self.get_crop_bbox(img)
# crop the image
img = self.crop(img, crop_bbox)
img_shape = img.shape
results['img'] = img
results['img_shape'] = img_shape
# crop semantic seg
for key in results.get('seg_fields', []):
results[key] = self.crop(results[key], crop_bbox)
return results
def __repr__(self):
return self.__class__.__name__ + f'(crop_size={self.crop_size})'
@PIPELINES.register_module()
class SegRescale(object):
"""Rescale semantic segmentation maps.
Args:
scale_factor (float): The scale factor of the final output.
"""
def __init__(self, scale_factor=1):
self.scale_factor = scale_factor
def __call__(self, results):
"""Call function to scale the semantic segmentation map.
Args:
results (dict): Result dict from loading pipeline.
Returns:
dict: Result dict with semantic segmentation map scaled.
"""
for key in results.get('seg_fields', []):
if self.scale_factor != 1:
results[key] = mmcv.imrescale(
results[key], self.scale_factor, interpolation='nearest')
return results
def __repr__(self):
return self.__class__.__name__ + f'(scale_factor={self.scale_factor})'
@PIPELINES.register_module()
class PhotoMetricDistortion(object):
"""Apply photometric distortion to image sequentially, every transformation
is applied with a probability of 0.5. The position of random contrast is in
second or second to last.
1. random brightness
2. random contrast (mode 0)
3. convert color from BGR to HSV
4. random saturation
5. random hue
6. convert color from HSV to BGR
7. random contrast (mode 1)
8. randomly swap channels
Args:
brightness_delta (int): delta of brightness.
contrast_range (tuple): range of contrast.
saturation_range (tuple): range of saturation.
hue_delta (int): delta of hue.
"""
def __init__(self,
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18):
self.brightness_delta = brightness_delta
self.contrast_lower, self.contrast_upper = contrast_range
self.saturation_lower, self.saturation_upper = saturation_range
self.hue_delta = hue_delta
def convert(self, img, alpha=1, beta=0):
"""Multiple with alpha and add beat with clip."""
img = img.astype(np.float32) * alpha + beta
img = np.clip(img, 0, 255)
return img.astype(np.uint8)
def brightness(self, img):
"""Brightness distortion."""
if random.randint(2):
return self.convert(
img,
beta=random.uniform(-self.brightness_delta,
self.brightness_delta))
return img
def contrast(self, img):
"""Contrast distortion."""
if random.randint(2):
return self.convert(
img,
alpha=random.uniform(self.contrast_lower, self.contrast_upper))
return img
def saturation(self, img):
"""Saturation distortion."""
if random.randint(2):
img = mmcv.bgr2hsv(img)
img[:, :, 1] = self.convert(
img[:, :, 1],
alpha=random.uniform(self.saturation_lower,
self.saturation_upper))
img = mmcv.hsv2bgr(img)
return img
def hue(self, img):
"""Hue distortion."""
if random.randint(2):
img = mmcv.bgr2hsv(img)
img[:, :,
0] = (img[:, :, 0].astype(int) +
random.randint(-self.hue_delta, self.hue_delta)) % 180
img = mmcv.hsv2bgr(img)
return img
def __call__(self, results):
"""Call function to perform photometric distortion on images.
Args:
results (dict): Result dict from loading pipeline.
Returns:
dict: Result dict with images distorted.
"""
img = results['img']
# random brightness
img = self.brightness(img)
# mode == 0 --> do random contrast first
# mode == 1 --> do random contrast last
mode = random.randint(2)
if mode == 1:
img = self.contrast(img)
# random saturation
img = self.saturation(img)
# random hue
img = self.hue(img)
# random contrast
if mode == 0:
img = self.contrast(img)
results['img'] = img
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += (f'(brightness_delta={self.brightness_delta}, '
f'contrast_range=({self.contrast_lower}, '
f'{self.contrast_upper}), '
f'saturation_range=({self.saturation_lower}, '
f'{self.saturation_upper}), '
f'hue_delta={self.hue_delta})')
return repr_str