[Feature] Add shear pipeline (#163)
* half-done auto_augmentation * remove auto_augcode and support shear pipeline * fix typo * fix typo * use a non-square toy data insteadpull/165/head
LXXXXR
GitHub
parent
fb11a23cfe
commit
8c11c01fdb
|
|
@ -1,3 +1,4 @@
|
|||
from .auto_augment import Shear
|
||||
from .compose import Compose
|
||||
from .formating import (Collect, ImageToTensor, ToNumpy, ToPIL, ToTensor,
|
||||
Transpose, to_tensor)
|
||||
|
|
@ -9,5 +10,5 @@ __all__ = [
|
|||
'Compose', 'to_tensor', 'ToTensor', 'ImageToTensor', 'ToPIL', 'ToNumpy',
|
||||
'Transpose', 'Collect', 'LoadImageFromFile', 'Resize', 'CenterCrop',
|
||||
'RandomFlip', 'Normalize', 'RandomCrop', 'RandomResizedCrop',
|
||||
'RandomGrayscale'
|
||||
'RandomGrayscale', 'Shear'
|
||||
]
|
||||
|
|
|
|||
|
|
@ -0,0 +1,86 @@
|
|||
import mmcv
|
||||
import numpy as np
|
||||
|
||||
from ..builder import PIPELINES
|
||||
|
||||
|
||||
def random_negative(value, random_negative_prob):
|
||||
"""Randomly negate value based on random_negative_prob."""
|
||||
return -value if np.random.rand() < random_negative_prob else value
|
||||
|
||||
|
||||
@PIPELINES.register_module()
|
||||
class Shear(object):
|
||||
"""Shear images.
|
||||
|
||||
Args:
|
||||
magnitude (int | float): The magnitude used for shear.
|
||||
pad_val (int, tuple[int]): Pixel pad_val value for constant fill. If a
|
||||
tuple of length 3, it is used to pad_val R, G, B channels
|
||||
respectively. Defaults to 128.
|
||||
prob (float): The probability for performing Shear therefore should be
|
||||
in range [0, 1]. Defaults to 0.5.
|
||||
direction (str): The shearing direction. Options are 'horizontal' and
|
||||
'vertical'. Defaults to 'horizontal'.
|
||||
random_negative_prob (float): The probability that turns the magnitude
|
||||
negative, which should be in range [0,1]. Defaults to 0.5.
|
||||
interpolation (str): Interpolation method. Options are 'nearest',
|
||||
'bilinear', 'bicubic', 'area', 'lanczos'. Defaults to 'bicubic'.
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
magnitude,
|
||||
pad_val=128,
|
||||
prob=0.5,
|
||||
direction='horizontal',
|
||||
random_negative_prob=0.5,
|
||||
interpolation='bicubic'):
|
||||
assert isinstance(magnitude, (int, float)), 'The magnitude type must '\
|
||||
f'be int or float, but got {type(magnitude)} instead.'
|
||||
if isinstance(pad_val, int):
|
||||
pad_val = tuple([pad_val] * 3)
|
||||
elif isinstance(pad_val, tuple):
|
||||
assert len(pad_val) == 3, 'pad_val as a tuple must have 3 ' \
|
||||
f'elements, got {len(pad_val)} instead.'
|
||||
assert all(isinstance(i, int) for i in pad_val), 'pad_val as a '\
|
||||
'tuple must got elements of int type.'
|
||||
else:
|
||||
raise TypeError('pad_val must be int or tuple with 3 elements.')
|
||||
assert 0 <= prob <= 1.0, 'The prob should be in range [0,1], ' \
|
||||
f'got {prob} instead.'
|
||||
assert direction in ('horizontal', 'vertical'), 'direction must be ' \
|
||||
f'either "horizontal" or "vertical", got {direction} instead.'
|
||||
assert 0 <= random_negative_prob <= 1.0, 'The random_negative_prob ' \
|
||||
f'should be in range [0,1], got {random_negative_prob} instead.'
|
||||
|
||||
self.magnitude = magnitude
|
||||
self.pad_val = pad_val
|
||||
self.prob = prob
|
||||
self.direction = direction
|
||||
self.random_negative_prob = random_negative_prob
|
||||
self.interpolation = interpolation
|
||||
|
||||
def __call__(self, results):
|
||||
if np.random.rand() > self.prob:
|
||||
return results
|
||||
magnitude = random_negative(self.magnitude, self.random_negative_prob)
|
||||
for key in results.get('img_fields', ['img']):
|
||||
img = results[key]
|
||||
img_sheared = mmcv.imshear(
|
||||
img,
|
||||
magnitude,
|
||||
direction=self.direction,
|
||||
border_value=self.pad_val,
|
||||
interpolation=self.interpolation)
|
||||
results[key] = img_sheared.astype(img.dtype)
|
||||
return results
|
||||
|
||||
def __repr__(self):
|
||||
repr_str = self.__class__.__name__
|
||||
repr_str += f'(magnitude={self.magnitude}, '
|
||||
repr_str += f'pad_val={self.pad_val}, '
|
||||
repr_str += f'prob={self.prob}, '
|
||||
repr_str += f'direction={self.direction}, '
|
||||
repr_str += f'random_negative_prob={self.random_negative_prob}, '
|
||||
repr_str += f'interpolation={self.interpolation})'
|
||||
return repr_str
|
||||
|
|
@ -0,0 +1,107 @@
|
|||
import copy
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
from mmcv.utils import build_from_cfg
|
||||
|
||||
from mmcls.datasets.builder import PIPELINES
|
||||
|
||||
|
||||
def construct_toy_data():
|
||||
img = np.array([[1, 2, 3, 4], [5, 6, 7, 8], [9, 10, 11, 12]],
|
||||
dtype=np.uint8)
|
||||
img = np.stack([img, img, img], axis=-1)
|
||||
results = dict()
|
||||
# image
|
||||
results['ori_img'] = img
|
||||
results['img'] = img
|
||||
results['img2'] = copy.deepcopy(img)
|
||||
results['img_shape'] = img.shape
|
||||
results['ori_shape'] = img.shape
|
||||
results['img_fields'] = ['img', 'img2']
|
||||
return results
|
||||
|
||||
|
||||
def test_shear():
|
||||
# test assertion for invalid type of magnitude
|
||||
with pytest.raises(AssertionError):
|
||||
transform = dict(type='Shear', magnitude=None)
|
||||
build_from_cfg(transform, PIPELINES)
|
||||
|
||||
# test assertion for invalid pad_val
|
||||
with pytest.raises(AssertionError):
|
||||
transform = dict(type='Shear', magnitude=0.5, pad_val=(0, 0))
|
||||
build_from_cfg(transform, PIPELINES)
|
||||
|
||||
# test assertion for invalid value of prob
|
||||
with pytest.raises(AssertionError):
|
||||
transform = dict(type='Shear', magnitude=0.5, prob=100)
|
||||
build_from_cfg(transform, PIPELINES)
|
||||
|
||||
# test assertion for invalid direction
|
||||
with pytest.raises(AssertionError):
|
||||
transform = dict(type='Shear', magnitude=0.5, direction='diagonal')
|
||||
build_from_cfg(transform, PIPELINES)
|
||||
|
||||
# test assertion for invalid value of random_negative_prob
|
||||
with pytest.raises(AssertionError):
|
||||
transform = dict(type='Shear', magnitude=0.5, random_negative_prob=100)
|
||||
build_from_cfg(transform, PIPELINES)
|
||||
|
||||
# test case when magnitude = 0, therefore no shear
|
||||
results = construct_toy_data()
|
||||
transform = dict(type='Shear', magnitude=0., prob=1.)
|
||||
pipeline = build_from_cfg(transform, PIPELINES)
|
||||
results = pipeline(results)
|
||||
assert (results['img'] == results['ori_img']).all()
|
||||
|
||||
# test case when prob = 0, therefore no shear
|
||||
results = construct_toy_data()
|
||||
transform = dict(type='Shear', magnitude=0.5, prob=0.)
|
||||
pipeline = build_from_cfg(transform, PIPELINES)
|
||||
results = pipeline(results)
|
||||
assert (results['img'] == results['ori_img']).all()
|
||||
|
||||
# test shear horizontally, magnitude=1
|
||||
results = construct_toy_data()
|
||||
transform = dict(
|
||||
type='Shear', magnitude=1, pad_val=0, prob=1., random_negative_prob=0.)
|
||||
pipeline = build_from_cfg(transform, PIPELINES)
|
||||
results = pipeline(results)
|
||||
sheared_img = np.array([[1, 2, 3, 4], [0, 5, 6, 7], [0, 0, 9, 10]],
|
||||
dtype=np.uint8)
|
||||
sheared_img = np.stack([sheared_img, sheared_img, sheared_img], axis=-1)
|
||||
assert (results['img'] == sheared_img).all()
|
||||
assert (results['img'] == results['img2']).all()
|
||||
|
||||
# test shear vertically, magnitude=-1
|
||||
results = construct_toy_data()
|
||||
transform = dict(
|
||||
type='Shear',
|
||||
magnitude=-1,
|
||||
pad_val=0,
|
||||
prob=1.,
|
||||
direction='vertical',
|
||||
random_negative_prob=0.)
|
||||
pipeline = build_from_cfg(transform, PIPELINES)
|
||||
results = pipeline(results)
|
||||
sheared_img = np.array([[1, 6, 11, 0], [5, 10, 0, 0], [9, 0, 0, 0]],
|
||||
dtype=np.uint8)
|
||||
sheared_img = np.stack([sheared_img, sheared_img, sheared_img], axis=-1)
|
||||
assert (results['img'] == sheared_img).all()
|
||||
|
||||
# test shear vertically, magnitude=1, random_negative_prob=1
|
||||
results = construct_toy_data()
|
||||
transform = dict(
|
||||
type='Shear',
|
||||
magnitude=1,
|
||||
pad_val=0,
|
||||
prob=1.,
|
||||
direction='vertical',
|
||||
random_negative_prob=1.)
|
||||
pipeline = build_from_cfg(transform, PIPELINES)
|
||||
results = pipeline(results)
|
||||
sheared_img = np.array([[1, 6, 11, 0], [5, 10, 0, 0], [9, 0, 0, 0]],
|
||||
dtype=np.uint8)
|
||||
sheared_img = np.stack([sheared_img, sheared_img, sheared_img], axis=-1)
|
||||
assert (results['img'] == sheared_img).all()
|
||||
Loading…
Reference in New Issue