import inspect
import mmcv
import numpy as np
from numpy import random
from mmdet.core import PolygonMasks
from mmdet.core.evaluation.bbox_overlaps import bbox_overlaps
from ..builder import PIPELINES
try:
from imagecorruptions import corrupt
except ImportError:
corrupt = None
try:
import albumentations
from albumentations import Compose
except ImportError:
albumentations = None
Compose = None
[docs]@PIPELINES.register_module()
class Resize(object):
"""Resize images & bbox & mask.
This transform resizes the input image to some scale. Bboxes and masks are
then resized with the same scale factor. 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):
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):
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):
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):
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):
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_bboxes(self, results):
img_shape = results['img_shape']
for key in results.get('bbox_fields', []):
bboxes = results[key] * results['scale_factor']
bboxes[:, 0::2] = np.clip(bboxes[:, 0::2], 0, img_shape[1])
bboxes[:, 1::2] = np.clip(bboxes[:, 1::2], 0, img_shape[0])
results[key] = bboxes
def _resize_masks(self, results):
for key in results.get('mask_fields', []):
if results[key] is None:
continue
if self.keep_ratio:
results[key] = results[key].rescale(results['scale'])
else:
results[key] = results[key].resize(results['img_shape'][:2])
def _resize_seg(self, results):
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):
if 'scale' not in results:
self._random_scale(results)
self._resize_img(results)
self._resize_bboxes(results)
self._resize_masks(results)
self._resize_seg(results)
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(img_scale={self.img_scale}, '
repr_str += f'multiscale_mode={self.multiscale_mode}, '
repr_str += f'ratio_range={self.ratio_range}, '
repr_str += f'keep_ratio={self.keep_ratio})'
return repr_str
[docs]@PIPELINES.register_module()
class RandomFlip(object):
"""Flip the image & bbox & mask.
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.
"""
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']
[docs] def bbox_flip(self, bboxes, img_shape, direction):
"""Flip bboxes horizontally.
Args:
bboxes(ndarray): shape (..., 4*k)
img_shape(tuple): (height, width)
"""
assert bboxes.shape[-1] % 4 == 0
flipped = bboxes.copy()
if direction == 'horizontal':
w = img_shape[1]
flipped[..., 0::4] = w - bboxes[..., 2::4]
flipped[..., 2::4] = w - bboxes[..., 0::4]
elif direction == 'vertical':
h = img_shape[0]
flipped[..., 1::4] = h - bboxes[..., 3::4]
flipped[..., 3::4] = h - bboxes[..., 1::4]
else:
raise ValueError(f"Invalid flipping direction '{direction}'")
return flipped
def __call__(self, results):
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 bboxes
for key in results.get('bbox_fields', []):
results[key] = self.bbox_flip(results[key],
results['img_shape'],
results['flip_direction'])
# flip masks
for key in results.get('mask_fields', []):
results[key] = results[key].flip(results['flip_direction'])
# flip segs
for key in results.get('seg_fields', []):
results[key] = mmcv.imflip(
results[key], direction=results['flip_direction'])
return results
def __repr__(self):
return self.__class__.__name__ + f'(flip_ratio={self.flip_ratio})'
[docs]@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.
Args:
size (tuple, optional): Fixed padding size.
size_divisor (int, optional): The divisor of padded size.
pad_val (float, optional): Padding value, 0 by default.
"""
def __init__(self, size=None, size_divisor=None, pad_val=0):
self.size = size
self.size_divisor = size_divisor
self.pad_val = 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):
if self.size is not None:
padded_img = mmcv.impad(results['img'], self.size, 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_masks(self, results):
pad_shape = results['pad_shape'][:2]
for key in results.get('mask_fields', []):
results[key] = results[key].pad(
pad_shape[:2], pad_val=self.pad_val)
def _pad_seg(self, results):
for key in results.get('seg_fields', []):
results[key] = mmcv.impad(results[key], results['pad_shape'][:2])
def __call__(self, results):
self._pad_img(results)
self._pad_masks(results)
self._pad_seg(results)
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(size={self.size}, '
repr_str += f'size_divisor={self.size_divisor}, '
repr_str += f'pad_val={self.pad_val})'
return repr_str
[docs]@PIPELINES.register_module()
class Normalize(object):
"""Normalize the image.
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):
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={self.to_rgb})'
return repr_str
[docs]@PIPELINES.register_module()
class RandomCrop(object):
"""Random crop the image & bboxes & masks.
Args:
crop_size (tuple): Expected size after cropping, (h, w).
"""
def __init__(self, crop_size):
self.crop_size = crop_size
def __call__(self, results):
img = results['img']
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]
# crop the image
img = img[crop_y1:crop_y2, crop_x1:crop_x2, ...]
img_shape = img.shape
results['img'] = img
results['img_shape'] = img_shape
# crop bboxes accordingly and clip to the image boundary
for key in results.get('bbox_fields', []):
bbox_offset = np.array([offset_w, offset_h, offset_w, offset_h],
dtype=np.float32)
bboxes = results[key] - bbox_offset
bboxes[:, 0::2] = np.clip(bboxes[:, 0::2], 0, img_shape[1])
bboxes[:, 1::2] = np.clip(bboxes[:, 1::2], 0, img_shape[0])
results[key] = bboxes
# crop semantic seg
for key in results.get('seg_fields', []):
results[key] = results[key][crop_y1:crop_y2, crop_x1:crop_x2]
# filter out the gt bboxes that are completely cropped
if 'gt_bboxes' in results:
gt_bboxes = results['gt_bboxes']
valid_inds = (gt_bboxes[:, 2] > gt_bboxes[:, 0]) & (
gt_bboxes[:, 3] > gt_bboxes[:, 1])
# if no gt bbox remains after cropping, just skip this image
if not np.any(valid_inds):
return None
results['gt_bboxes'] = gt_bboxes[valid_inds, :]
if 'gt_labels' in results:
results['gt_labels'] = results['gt_labels'][valid_inds]
# filter and crop the masks
if 'gt_masks' in results:
results['gt_masks'] = results['gt_masks'].crop(
np.asarray([crop_x1, crop_y1, crop_x2, crop_y2]))
return results
def __repr__(self):
return self.__class__.__name__ + f'(crop_size={self.crop_size})'
[docs]@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):
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})'
[docs]@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 __call__(self, results):
img = results['img']
assert img.dtype == np.float32, \
'PhotoMetricDistortion needs the input image of dtype np.float32,'\
' please set "to_float32=True" in "LoadImageFromFile" pipeline'
# random brightness
if random.randint(2):
delta = random.uniform(-self.brightness_delta,
self.brightness_delta)
img += delta
# mode == 0 --> do random contrast first
# mode == 1 --> do random contrast last
mode = random.randint(2)
if mode == 1:
if random.randint(2):
alpha = random.uniform(self.contrast_lower,
self.contrast_upper)
img *= alpha
# convert color from BGR to HSV
img = mmcv.bgr2hsv(img)
# random saturation
if random.randint(2):
img[..., 1] *= random.uniform(self.saturation_lower,
self.saturation_upper)
# random hue
if random.randint(2):
img[..., 0] += random.uniform(-self.hue_delta, self.hue_delta)
img[..., 0][img[..., 0] > 360] -= 360
img[..., 0][img[..., 0] < 0] += 360
# convert color from HSV to BGR
img = mmcv.hsv2bgr(img)
# random contrast
if mode == 0:
if random.randint(2):
alpha = random.uniform(self.contrast_lower,
self.contrast_upper)
img *= alpha
# randomly swap channels
if random.randint(2):
img = img[..., random.permutation(3)]
results['img'] = img
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(\nbrightness_delta={self.brightness_delta},\n'
repr_str += f'contrast_range='
repr_str += f'{(self.contrast_lower, self.contrast_upper)},\n'
repr_str += f'saturation_range='
repr_str += f'{(self.saturation_lower, self.saturation_upper)},\n'
repr_str += f'hue_delta={self.hue_delta})'
return repr_str
[docs]@PIPELINES.register_module()
class Expand(object):
"""Random expand the image & bboxes.
Randomly place the original image on a canvas of 'ratio' x original image
size filled with mean values. The ratio is in the range of ratio_range.
Args:
mean (tuple): mean value of dataset.
to_rgb (bool): if need to convert the order of mean to align with RGB.
ratio_range (tuple): range of expand ratio.
prob (float): probability of applying this transformation
"""
def __init__(self,
mean=(0, 0, 0),
to_rgb=True,
ratio_range=(1, 4),
seg_ignore_label=None,
prob=0.5):
self.to_rgb = to_rgb
self.ratio_range = ratio_range
if to_rgb:
self.mean = mean[::-1]
else:
self.mean = mean
self.min_ratio, self.max_ratio = ratio_range
self.seg_ignore_label = seg_ignore_label
self.prob = prob
def __call__(self, results):
if random.uniform(0, 1) > self.prob:
return results
img, boxes = [results[k] for k in ('img', 'gt_bboxes')]
h, w, c = img.shape
ratio = random.uniform(self.min_ratio, self.max_ratio)
expand_img = np.full((int(h * ratio), int(w * ratio), c),
self.mean).astype(img.dtype)
left = int(random.uniform(0, w * ratio - w))
top = int(random.uniform(0, h * ratio - h))
expand_img[top:top + h, left:left + w] = img
boxes = boxes + np.tile((left, top), 2).astype(boxes.dtype)
results['img'] = expand_img
results['gt_bboxes'] = boxes
if 'gt_masks' in results:
results['gt_masks'] = results['gt_masks'].expand(
int(h * ratio), int(w * ratio), top, left)
# not tested
if 'gt_semantic_seg' in results:
assert self.seg_ignore_label is not None
gt_seg = results['gt_semantic_seg']
expand_gt_seg = np.full((int(h * ratio), int(w * ratio)),
self.seg_ignore_label).astype(gt_seg.dtype)
expand_gt_seg[top:top + h, left:left + w] = gt_seg
results['gt_semantic_seg'] = expand_gt_seg
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(mean={self.mean}, to_rgb={self.to_rgb}, '
repr_str += f'ratio_range={self.ratio_range}, '
repr_str += f'seg_ignore_label={self.seg_ignore_label})'
return repr_str
[docs]@PIPELINES.register_module()
class MinIoURandomCrop(object):
"""Random crop the image & bboxes, the cropped patches have minimum IoU
requirement with original image & bboxes, the IoU threshold is randomly
selected from min_ious.
Args:
min_ious (tuple): minimum IoU threshold for all intersections with
bounding boxes
min_crop_size (float): minimum crop's size (i.e. h,w := a*h, a*w,
where a >= min_crop_size).
"""
def __init__(self, min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3):
# 1: return ori img
self.min_ious = min_ious
self.sample_mode = (1, *min_ious, 0)
self.min_crop_size = min_crop_size
def __call__(self, results):
img, boxes, labels = [
results[k] for k in ('img', 'gt_bboxes', 'gt_labels')
]
h, w, c = img.shape
while True:
mode = random.choice(self.sample_mode)
if mode == 1:
return results
min_iou = mode
for i in range(50):
new_w = random.uniform(self.min_crop_size * w, w)
new_h = random.uniform(self.min_crop_size * h, h)
# h / w in [0.5, 2]
if new_h / new_w < 0.5 or new_h / new_w > 2:
continue
left = random.uniform(w - new_w)
top = random.uniform(h - new_h)
patch = np.array(
(int(left), int(top), int(left + new_w), int(top + new_h)))
overlaps = bbox_overlaps(
patch.reshape(-1, 4), boxes.reshape(-1, 4)).reshape(-1)
if len(overlaps) > 0 and overlaps.min() < min_iou:
continue
# center of boxes should inside the crop img
# only adjust boxes and instance masks when the gt is not empty
if len(overlaps) > 0:
# adjust boxes
center = (boxes[:, :2] + boxes[:, 2:]) / 2
mask = ((center[:, 0] > patch[0]) *
(center[:, 1] > patch[1]) *
(center[:, 0] < patch[2]) *
(center[:, 1] < patch[3]))
if not mask.any():
continue
boxes = boxes[mask]
labels = labels[mask]
boxes[:, 2:] = boxes[:, 2:].clip(max=patch[2:])
boxes[:, :2] = boxes[:, :2].clip(min=patch[:2])
boxes -= np.tile(patch[:2], 2)
results['gt_bboxes'] = boxes
results['gt_labels'] = labels
if 'gt_masks' in results:
results['gt_masks'] = results['gt_masks'][
mask.nonzero()[0]].crop(patch)
# adjust the img no matter whether the gt is empty before crop
img = img[patch[1]:patch[3], patch[0]:patch[2]]
results['img'] = img
# not tested
if 'gt_semantic_seg' in results:
results['gt_semantic_seg'] = results['gt_semantic_seg'][
patch[1]:patch[3], patch[0]:patch[2]]
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(min_ious={self.min_ious}, '
repr_str += f'min_crop_size={self.min_crop_size})'
return repr_str
@PIPELINES.register_module()
class Corrupt(object):
def __init__(self, corruption, severity=1):
self.corruption = corruption
self.severity = severity
def __call__(self, results):
if corrupt is None:
raise RuntimeError('imagecorruptions is not installed')
results['img'] = corrupt(
results['img'].astype(np.uint8),
corruption_name=self.corruption,
severity=self.severity)
return results
def __repr__(self):
repr_str = self.__class__.__name__
repr_str += f'(corruption={self.corruption}, '
repr_str += f'severity={self.severity})'
return repr_str
@PIPELINES.register_module()
class Albu(object):
def __init__(self,
transforms,
bbox_params=None,
keymap=None,
update_pad_shape=False,
skip_img_without_anno=False):
"""
Adds custom transformations from Albumentations lib.
Please, visit `https://albumentations.readthedocs.io`
to get more information.
transforms (list): list of albu transformations
bbox_params (dict): bbox_params for albumentation `Compose`
keymap (dict): contains {'input key':'albumentation-style key'}
skip_img_without_anno (bool): whether to skip the image
if no ann left after aug
"""
if Compose is None:
raise RuntimeError('albumentations is not installed')
self.transforms = transforms
self.filter_lost_elements = False
self.update_pad_shape = update_pad_shape
self.skip_img_without_anno = skip_img_without_anno
# A simple workaround to remove masks without boxes
if (isinstance(bbox_params, dict) and 'label_fields' in bbox_params
and 'filter_lost_elements' in bbox_params):
self.filter_lost_elements = True
self.origin_label_fields = bbox_params['label_fields']
bbox_params['label_fields'] = ['idx_mapper']
del bbox_params['filter_lost_elements']
self.bbox_params = (
self.albu_builder(bbox_params) if bbox_params else None)
self.aug = Compose([self.albu_builder(t) for t in self.transforms],
bbox_params=self.bbox_params)
if not keymap:
self.keymap_to_albu = {
'img': 'image',
'gt_masks': 'masks',
'gt_bboxes': 'bboxes'
}
else:
self.keymap_to_albu = keymap
self.keymap_back = {v: k for k, v in self.keymap_to_albu.items()}
def albu_builder(self, cfg):
"""Import a module from albumentations.
Inherits some of `build_from_cfg` logic.
Args:
cfg (dict): Config dict. It should at least contain the key "type".
Returns:
obj: The constructed object.
"""
assert isinstance(cfg, dict) and 'type' in cfg
args = cfg.copy()
obj_type = args.pop('type')
if mmcv.is_str(obj_type):
if albumentations is None:
raise RuntimeError('albumentations is not installed')
obj_cls = getattr(albumentations, obj_type)
elif inspect.isclass(obj_type):
obj_cls = obj_type
else:
raise TypeError(
f'type must be a str or valid type, but got {type(obj_type)}')
if 'transforms' in args:
args['transforms'] = [
self.albu_builder(transform)
for transform in args['transforms']
]
return obj_cls(**args)
@staticmethod
def mapper(d, keymap):
"""
Dictionary mapper.
Renames keys according to keymap provided.
Args:
d (dict): old dict
keymap (dict): {'old_key':'new_key'}
Returns:
dict: new dict.
"""
updated_dict = {}
for k, v in zip(d.keys(), d.values()):
new_k = keymap.get(k, k)
updated_dict[new_k] = d[k]
return updated_dict
def __call__(self, results):
# dict to albumentations format
results = self.mapper(results, self.keymap_to_albu)
if 'bboxes' in results:
# to list of boxes
if isinstance(results['bboxes'], np.ndarray):
results['bboxes'] = [x for x in results['bboxes']]
# add pseudo-field for filtration
if self.filter_lost_elements:
results['idx_mapper'] = np.arange(len(results['bboxes']))
# TODO: Support mask structure in albu
if 'masks' in results:
if isinstance(results['masks'], PolygonMasks):
raise NotImplementedError(
'Albu only supports BitMap masks now')
ori_masks = results['masks']
results['masks'] = results['masks'].masks
results = self.aug(**results)
if 'bboxes' in results:
if isinstance(results['bboxes'], list):
results['bboxes'] = np.array(
results['bboxes'], dtype=np.float32)
results['bboxes'] = results['bboxes'].reshape(-1, 4)
# filter label_fields
if self.filter_lost_elements:
for label in self.origin_label_fields:
results[label] = np.array(
[results[label][i] for i in results['idx_mapper']])
if 'masks' in results:
results['masks'] = np.array(
[results['masks'][i] for i in results['idx_mapper']])
results['masks'] = ori_masks.__class__(
results['masks'], results['image'].shape[0],
results['image'].shape[1])
if (not len(results['idx_mapper'])
and self.skip_img_without_anno):
return None
if 'gt_labels' in results:
if isinstance(results['gt_labels'], list):
results['gt_labels'] = np.array(results['gt_labels'])
results['gt_labels'] = results['gt_labels'].astype(np.int64)
# back to the original format
results = self.mapper(results, self.keymap_back)
# update final shape
if self.update_pad_shape:
results['pad_shape'] = results['img'].shape
return results
def __repr__(self):
repr_str = self.__class__.__name__ + f'(transforms={self.transforms})'
return repr_str