# Copyright (c) OpenMMLab. All rights reserved.
import numbers
import cv2
import numpy as np
from ..utils import to_2tuple
from .io import imread_backend
try:
from PIL import Image
except ImportError:
Image = None
def _scale_size(size, scale):
"""Rescale a size by a ratio.
Args:
size (tuple[int]): (w, h).
scale (float | tuple(float)): Scaling factor.
Returns:
tuple[int]: scaled size.
"""
if isinstance(scale, (float, int)):
scale = (scale, scale)
w, h = size
return int(w * float(scale[0]) + 0.5), int(h * float(scale[1]) + 0.5)
cv2_interp_codes = {
'nearest': cv2.INTER_NEAREST,
'bilinear': cv2.INTER_LINEAR,
'bicubic': cv2.INTER_CUBIC,
'area': cv2.INTER_AREA,
'lanczos': cv2.INTER_LANCZOS4
}
if Image is not None:
pillow_interp_codes = {
'nearest': Image.NEAREST,
'bilinear': Image.BILINEAR,
'bicubic': Image.BICUBIC,
'box': Image.BOX,
'lanczos': Image.LANCZOS,
'hamming': Image.HAMMING
}
def imresize(img,
size,
return_scale=False,
interpolation='bilinear',
out=None,
backend=None):
"""Resize image to a given size.
Args:
img (ndarray): The input image.
size (tuple[int]): Target size (w, h).
return_scale (bool): Whether to return `w_scale` and `h_scale`.
interpolation (str): Interpolation method, accepted values are
"nearest", "bilinear", "bicubic", "area", "lanczos" for 'cv2'
backend, "nearest", "bilinear" for 'pillow' backend.
out (ndarray): The output destination.
backend (str | None): The image resize backend type. Options are `cv2`,
`pillow`, `None`. If backend is None, the global imread_backend
specified by ``mmcv.use_backend()`` will be used. Default: None.
Returns:
tuple | ndarray: (`resized_img`, `w_scale`, `h_scale`) or
`resized_img`.
"""
h, w = img.shape[:2]
if backend is None:
backend = imread_backend
if backend not in ['cv2', 'pillow']:
raise ValueError(f'backend: {backend} is not supported for resize.'
f"Supported backends are 'cv2', 'pillow'")
if backend == 'pillow':
assert img.dtype == np.uint8, 'Pillow backend only support uint8 type'
pil_image = Image.fromarray(img)
pil_image = pil_image.resize(size, pillow_interp_codes[interpolation])
resized_img = np.array(pil_image)
else:
resized_img = cv2.resize(
img, size, dst=out, interpolation=cv2_interp_codes[interpolation])
if not return_scale:
return resized_img
else:
w_scale = size[0] / w
h_scale = size[1] / h
return resized_img, w_scale, h_scale
def imresize_to_multiple(img,
divisor,
size=None,
scale_factor=None,
keep_ratio=False,
return_scale=False,
interpolation='bilinear',
out=None,
backend=None):
"""Resize image according to a given size or scale factor and then rounds
up the the resized or rescaled image size to the nearest value that can be
divided by the divisor.
Args:
img (ndarray): The input image.
divisor (int | tuple): Resized image size will be a multiple of
divisor. If divisor is a tuple, divisor should be
(w_divisor, h_divisor).
size (None | int | tuple[int]): Target size (w, h). Default: None.
scale_factor (None | float | tuple[float]): Multiplier for spatial
size. Should match input size if it is a tuple and the 2D style is
(w_scale_factor, h_scale_factor). Default: None.
keep_ratio (bool): Whether to keep the aspect ratio when resizing the
image. Default: False.
return_scale (bool): Whether to return `w_scale` and `h_scale`.
interpolation (str): Interpolation method, accepted values are
"nearest", "bilinear", "bicubic", "area", "lanczos" for 'cv2'
backend, "nearest", "bilinear" for 'pillow' backend.
out (ndarray): The output destination.
backend (str | None): The image resize backend type. Options are `cv2`,
`pillow`, `None`. If backend is None, the global imread_backend
specified by ``mmcv.use_backend()`` will be used. Default: None.
Returns:
tuple | ndarray: (`resized_img`, `w_scale`, `h_scale`) or
`resized_img`.
"""
h, w = img.shape[:2]
if size is not None and scale_factor is not None:
raise ValueError('only one of size or scale_factor should be defined')
elif size is None and scale_factor is None:
raise ValueError('one of size or scale_factor should be defined')
elif size is not None:
size = to_2tuple(size)
if keep_ratio:
size = rescale_size((w, h), size, return_scale=False)
else:
size = _scale_size((w, h), scale_factor)
divisor = to_2tuple(divisor)
size = tuple([int(np.ceil(s / d)) * d for s, d in zip(size, divisor)])
resized_img, w_scale, h_scale = imresize(
img,
size,
return_scale=True,
interpolation=interpolation,
out=out,
backend=backend)
if return_scale:
return resized_img, w_scale, h_scale
else:
return resized_img
def imresize_like(img,
dst_img,
return_scale=False,
interpolation='bilinear',
backend=None):
"""Resize image to the same size of a given image.
Args:
img (ndarray): The input image.
dst_img (ndarray): The target image.
return_scale (bool): Whether to return `w_scale` and `h_scale`.
interpolation (str): Same as :func:`resize`.
backend (str | None): Same as :func:`resize`.
Returns:
tuple or ndarray: (`resized_img`, `w_scale`, `h_scale`) or
`resized_img`.
"""
h, w = dst_img.shape[:2]
return imresize(img, (w, h), return_scale, interpolation, backend=backend)
def rescale_size(old_size, scale, return_scale=False):
"""Calculate the new size to be rescaled to.
Args:
old_size (tuple[int]): The old size (w, h) of image.
scale (float | tuple[int]): The scaling factor or maximum size.
If it is a float number, then the image will be rescaled by this
factor, else if it is a tuple of 2 integers, then the image will
be rescaled as large as possible within the scale.
return_scale (bool): Whether to return the scaling factor besides the
rescaled image size.
Returns:
tuple[int]: The new rescaled image size.
"""
w, h = old_size
if isinstance(scale, (float, int)):
if scale <= 0:
raise ValueError(f'Invalid scale {scale}, must be positive.')
scale_factor = scale
elif isinstance(scale, tuple):
max_long_edge = max(scale)
max_short_edge = min(scale)
scale_factor = min(max_long_edge / max(h, w),
max_short_edge / min(h, w))
else:
raise TypeError(
f'Scale must be a number or tuple of int, but got {type(scale)}')
new_size = _scale_size((w, h), scale_factor)
if return_scale:
return new_size, scale_factor
else:
return new_size
def imrescale(img,
scale,
return_scale=False,
interpolation='bilinear',
backend=None):
"""Resize image while keeping the aspect ratio.
Args:
img (ndarray): The input image.
scale (float | tuple[int]): The scaling factor or maximum size.
If it is a float number, then the image will be rescaled by this
factor, else if it is a tuple of 2 integers, then the image will
be rescaled as large as possible within the scale.
return_scale (bool): Whether to return the scaling factor besides the
rescaled image.
interpolation (str): Same as :func:`resize`.
backend (str | None): Same as :func:`resize`.
Returns:
ndarray: The rescaled image.
"""
h, w = img.shape[:2]
new_size, scale_factor = rescale_size((w, h), scale, return_scale=True)
rescaled_img = imresize(
img, new_size, interpolation=interpolation, backend=backend)
if return_scale:
return rescaled_img, scale_factor
else:
return rescaled_img
def imflip(img, direction='horizontal'):
"""Flip an image horizontally or vertically.
Args:
img (ndarray): Image to be flipped.
direction (str): The flip direction, either "horizontal" or
"vertical" or "diagonal".
Returns:
ndarray: The flipped image.
"""
assert direction in ['horizontal', 'vertical', 'diagonal']
if direction == 'horizontal':
return np.flip(img, axis=1)
elif direction == 'vertical':
return np.flip(img, axis=0)
else:
return np.flip(img, axis=(0, 1))
def imflip_(img, direction='horizontal'):
"""Inplace flip an image horizontally or vertically.
Args:
img (ndarray): Image to be flipped.
direction (str): The flip direction, either "horizontal" or
"vertical" or "diagonal".
Returns:
ndarray: The flipped image (inplace).
"""
assert direction in ['horizontal', 'vertical', 'diagonal']
if direction == 'horizontal':
return cv2.flip(img, 1, img)
elif direction == 'vertical':
return cv2.flip(img, 0, img)
else:
return cv2.flip(img, -1, img)
def imrotate(img,
angle,
center=None,
scale=1.0,
border_value=0,
interpolation='bilinear',
auto_bound=False):
"""Rotate an image.
Args:
img (ndarray): Image to be rotated.
angle (float): Rotation angle in degrees, positive values mean
clockwise rotation.
center (tuple[float], optional): Center point (w, h) of the rotation in
the source image. If not specified, the center of the image will be
used.
scale (float): Isotropic scale factor.
border_value (int): Border value.
interpolation (str): Same as :func:`resize`.
auto_bound (bool): Whether to adjust the image size to cover the whole
rotated image.
Returns:
ndarray: The rotated image.
"""
if center is not None and auto_bound:
raise ValueError('`auto_bound` conflicts with `center`')
h, w = img.shape[:2]
if center is None:
center = ((w - 1) * 0.5, (h - 1) * 0.5)
assert isinstance(center, tuple)
matrix = cv2.getRotationMatrix2D(center, -angle, scale)
if auto_bound:
cos = np.abs(matrix[0, 0])
sin = np.abs(matrix[0, 1])
new_w = h * sin + w * cos
new_h = h * cos + w * sin
matrix[0, 2] += (new_w - w) * 0.5
matrix[1, 2] += (new_h - h) * 0.5
w = int(np.round(new_w))
h = int(np.round(new_h))
rotated = cv2.warpAffine(
img,
matrix, (w, h),
flags=cv2_interp_codes[interpolation],
borderValue=border_value)
return rotated
def bbox_clip(bboxes, img_shape):
"""Clip bboxes to fit the image shape.
Args:
bboxes (ndarray): Shape (..., 4*k)
img_shape (tuple[int]): (height, width) of the image.
Returns:
ndarray: Clipped bboxes.
"""
assert bboxes.shape[-1] % 4 == 0
cmin = np.empty(bboxes.shape[-1], dtype=bboxes.dtype)
cmin[0::2] = img_shape[1] - 1
cmin[1::2] = img_shape[0] - 1
clipped_bboxes = np.maximum(np.minimum(bboxes, cmin), 0)
return clipped_bboxes
def bbox_scaling(bboxes, scale, clip_shape=None):
"""Scaling bboxes w.r.t the box center.
Args:
bboxes (ndarray): Shape(..., 4).
scale (float): Scaling factor.
clip_shape (tuple[int], optional): If specified, bboxes that exceed the
boundary will be clipped according to the given shape (h, w).
Returns:
ndarray: Scaled bboxes.
"""
if float(scale) == 1.0:
scaled_bboxes = bboxes.copy()
else:
w = bboxes[..., 2] - bboxes[..., 0] + 1
h = bboxes[..., 3] - bboxes[..., 1] + 1
dw = (w * (scale - 1)) * 0.5
dh = (h * (scale - 1)) * 0.5
scaled_bboxes = bboxes + np.stack((-dw, -dh, dw, dh), axis=-1)
if clip_shape is not None:
return bbox_clip(scaled_bboxes, clip_shape)
else:
return scaled_bboxes
def imcrop(img, bboxes, scale=1.0, pad_fill=None):
"""Crop image patches.
3 steps: scale the bboxes -> clip bboxes -> crop and pad.
Args:
img (ndarray): Image to be cropped.
bboxes (ndarray): Shape (k, 4) or (4, ), location of cropped bboxes.
scale (float, optional): Scale ratio of bboxes, the default value
1.0 means no padding.
pad_fill (Number | list[Number]): Value to be filled for padding.
Default: None, which means no padding.
Returns:
list[ndarray] | ndarray: The cropped image patches.
"""
chn = 1 if img.ndim == 2 else img.shape[2]
if pad_fill is not None:
if isinstance(pad_fill, (int, float)):
pad_fill = [pad_fill for _ in range(chn)]
assert len(pad_fill) == chn
_bboxes = bboxes[None, ...] if bboxes.ndim == 1 else bboxes
scaled_bboxes = bbox_scaling(_bboxes, scale).astype(np.int32)
clipped_bbox = bbox_clip(scaled_bboxes, img.shape)
patches = []
for i in range(clipped_bbox.shape[0]):
x1, y1, x2, y2 = tuple(clipped_bbox[i, :])
if pad_fill is None:
patch = img[y1:y2 + 1, x1:x2 + 1, ...]
else:
_x1, _y1, _x2, _y2 = tuple(scaled_bboxes[i, :])
if chn == 1:
patch_shape = (_y2 - _y1 + 1, _x2 - _x1 + 1)
else:
patch_shape = (_y2 - _y1 + 1, _x2 - _x1 + 1, chn)
patch = np.array(
pad_fill, dtype=img.dtype) * np.ones(
patch_shape, dtype=img.dtype)
x_start = 0 if _x1 >= 0 else -_x1
y_start = 0 if _y1 >= 0 else -_y1
w = x2 - x1 + 1
h = y2 - y1 + 1
patch[y_start:y_start + h, x_start:x_start + w,
...] = img[y1:y1 + h, x1:x1 + w, ...]
patches.append(patch)
if bboxes.ndim == 1:
return patches[0]
else:
return patches
def impad(img,
*,
shape=None,
padding=None,
pad_val=0,
padding_mode='constant'):
"""Pad the given image to a certain shape or pad on all sides with
specified padding mode and padding value.
Args:
img (ndarray): Image to be padded.
shape (tuple[int]): Expected padding shape (h, w). Default: None.
padding (int or tuple[int]): Padding on each border. If a single int is
provided this is used to pad all borders. If tuple of length 2 is
provided this is the padding on left/right and top/bottom
respectively. If a tuple of length 4 is provided this is the
padding for the left, top, right and bottom borders respectively.
Default: None. Note that `shape` and `padding` can not be both
set.
pad_val (Number | Sequence[Number]): Values to be filled in padding
areas when padding_mode is 'constant'. Default: 0.
padding_mode (str): Type of padding. Should be: constant, edge,
reflect or symmetric. Default: constant.
- constant: pads with a constant value, this value is specified
with pad_val.
- edge: pads with the last value at the edge of the image.
- reflect: pads with reflection of image without repeating the
last value on the edge. For example, padding [1, 2, 3, 4]
with 2 elements on both sides in reflect mode will result
in [3, 2, 1, 2, 3, 4, 3, 2].
- symmetric: pads with reflection of image repeating the last
value on the edge. For example, padding [1, 2, 3, 4] with
2 elements on both sides in symmetric mode will result in
[2, 1, 1, 2, 3, 4, 4, 3]
Returns:
ndarray: The padded image.
"""
assert (shape is not None) ^ (padding is not None)
if shape is not None:
padding = (0, 0, shape[1] - img.shape[1], shape[0] - img.shape[0])
# check pad_val
if isinstance(pad_val, tuple):
assert len(pad_val) == img.shape[-1]
elif not isinstance(pad_val, numbers.Number):
raise TypeError('pad_val must be a int or a tuple. '
f'But received {type(pad_val)}')
# check padding
if isinstance(padding, tuple) and len(padding) in [2, 4]:
if len(padding) == 2:
padding = (padding[0], padding[1], padding[0], padding[1])
elif isinstance(padding, numbers.Number):
padding = (padding, padding, padding, padding)
else:
raise ValueError('Padding must be a int or a 2, or 4 element tuple.'
f'But received {padding}')
# check padding mode
assert padding_mode in ['constant', 'edge', 'reflect', 'symmetric']
border_type = {
'constant': cv2.BORDER_CONSTANT,
'edge': cv2.BORDER_REPLICATE,
'reflect': cv2.BORDER_REFLECT_101,
'symmetric': cv2.BORDER_REFLECT
}
img = cv2.copyMakeBorder(
img,
padding[1],
padding[3],
padding[0],
padding[2],
border_type[padding_mode],
value=pad_val)
return img
def impad_to_multiple(img, divisor, pad_val=0):
"""Pad an image to ensure each edge to be multiple to some number.
Args:
img (ndarray): Image to be padded.
divisor (int): Padded image edges will be multiple to divisor.
pad_val (Number | Sequence[Number]): Same as :func:`impad`.
Returns:
ndarray: The padded image.
"""
pad_h = int(np.ceil(img.shape[0] / divisor)) * divisor
pad_w = int(np.ceil(img.shape[1] / divisor)) * divisor
return impad(img, shape=(pad_h, pad_w), pad_val=pad_val)
def cutout(img, shape, pad_val=0):
"""Randomly cut out a rectangle from the original img.
Args:
img (ndarray): Image to be cutout.
shape (int | tuple[int]): Expected cutout shape (h, w). If given as a
int, the value will be used for both h and w.
pad_val (int | float | tuple[int | float]): Values to be filled in the
cut area. Defaults to 0.
Returns:
ndarray: The cutout image.
"""
channels = 1 if img.ndim == 2 else img.shape[2]
if isinstance(shape, int):
cut_h, cut_w = shape, shape
else:
assert isinstance(shape, tuple) and len(shape) == 2, \
f'shape must be a int or a tuple with length 2, but got type ' \
f'{type(shape)} instead.'
cut_h, cut_w = shape
if isinstance(pad_val, (int, float)):
pad_val = tuple([pad_val] * channels)
elif isinstance(pad_val, tuple):
assert len(pad_val) == channels, \
'Expected the num of elements in tuple equals the channels' \
'of input image. Found {} vs {}'.format(
len(pad_val), channels)
else:
raise TypeError(f'Invalid type {type(pad_val)} for `pad_val`')
img_h, img_w = img.shape[:2]
y0 = np.random.uniform(img_h)
x0 = np.random.uniform(img_w)
y1 = int(max(0, y0 - cut_h / 2.))
x1 = int(max(0, x0 - cut_w / 2.))
y2 = min(img_h, y1 + cut_h)
x2 = min(img_w, x1 + cut_w)
if img.ndim == 2:
patch_shape = (y2 - y1, x2 - x1)
else:
patch_shape = (y2 - y1, x2 - x1, channels)
img_cutout = img.copy()
patch = np.array(
pad_val, dtype=img.dtype) * np.ones(
patch_shape, dtype=img.dtype)
img_cutout[y1:y2, x1:x2, ...] = patch
return img_cutout
def _get_shear_matrix(magnitude, direction='horizontal'):
"""Generate the shear matrix for transformation.
Args:
magnitude (int | float): The magnitude used for shear.
direction (str): The flip direction, either "horizontal"
or "vertical".
Returns:
ndarray: The shear matrix with dtype float32.
"""
if direction == 'horizontal':
shear_matrix = np.float32([[1, magnitude, 0], [0, 1, 0]])
elif direction == 'vertical':
shear_matrix = np.float32([[1, 0, 0], [magnitude, 1, 0]])
return shear_matrix
def imshear(img,
magnitude,
direction='horizontal',
border_value=0,
interpolation='bilinear'):
"""Shear an image.
Args:
img (ndarray): Image to be sheared with format (h, w)
or (h, w, c).
magnitude (int | float): The magnitude used for shear.
direction (str): The flip direction, either "horizontal"
or "vertical".
border_value (int | tuple[int]): Value used in case of a
constant border.
interpolation (str): Same as :func:`resize`.
Returns:
ndarray: The sheared image.
"""
assert direction in ['horizontal',
'vertical'], f'Invalid direction: {direction}'
height, width = img.shape[:2]
if img.ndim == 2:
channels = 1
elif img.ndim == 3:
channels = img.shape[-1]
if isinstance(border_value, int):
border_value = tuple([border_value] * channels)
elif isinstance(border_value, tuple):
assert len(border_value) == channels, \
'Expected the num of elements in tuple equals the channels' \
'of input image. Found {} vs {}'.format(
len(border_value), channels)
else:
raise ValueError(
f'Invalid type {type(border_value)} for `border_value`')
shear_matrix = _get_shear_matrix(magnitude, direction)
sheared = cv2.warpAffine(
img,
shear_matrix,
(width, height),
# Note case when the number elements in `border_value`
# greater than 3 (e.g. shearing masks whose channels large
# than 3) will raise TypeError in `cv2.warpAffine`.
# Here simply slice the first 3 values in `border_value`.
borderValue=border_value[:3],
flags=cv2_interp_codes[interpolation])
return sheared
def _get_translate_matrix(offset, direction='horizontal'):
"""Generate the translate matrix.
Args:
offset (int | float): The offset used for translate.
direction (str): The translate direction, either
"horizontal" or "vertical".
Returns:
ndarray: The translate matrix with dtype float32.
"""
if direction == 'horizontal':
translate_matrix = np.float32([[1, 0, offset], [0, 1, 0]])
elif direction == 'vertical':
translate_matrix = np.float32([[1, 0, 0], [0, 1, offset]])
return translate_matrix
def imtranslate(img,
offset,
direction='horizontal',
border_value=0,
interpolation='bilinear'):
"""Translate an image.
Args:
img (ndarray): Image to be translated with format
(h, w) or (h, w, c).
offset (int | float): The offset used for translate.
direction (str): The translate direction, either "horizontal"
or "vertical".
border_value (int | tuple[int]): Value used in case of a
constant border.
interpolation (str): Same as :func:`resize`.
Returns:
ndarray: The translated image.
"""
assert direction in ['horizontal',
'vertical'], f'Invalid direction: {direction}'
height, width = img.shape[:2]
if img.ndim == 2:
channels = 1
elif img.ndim == 3:
channels = img.shape[-1]
if isinstance(border_value, int):
border_value = tuple([border_value] * channels)
elif isinstance(border_value, tuple):
assert len(border_value) == channels, \
'Expected the num of elements in tuple equals the channels' \
'of input image. Found {} vs {}'.format(
len(border_value), channels)
else:
raise ValueError(
f'Invalid type {type(border_value)} for `border_value`.')
translate_matrix = _get_translate_matrix(offset, direction)
translated = cv2.warpAffine(
img,
translate_matrix,
(width, height),
# Note case when the number elements in `border_value`
# greater than 3 (e.g. translating masks whose channels
# large than 3) will raise TypeError in `cv2.warpAffine`.
# Here simply slice the first 3 values in `border_value`.
borderValue=border_value[:3],
flags=cv2_interp_codes[interpolation])
return translated