def load_images(self, ids: List[int]) -> Tensor:
"""
Returns:
(l, c, w, h) Tensor:
Tensor of images.
"""
images: List[Tensor] = [
imread(self.frame_template.format(i)) for i in ids
]
# Using deterministic parameters to apply exactly
# the same augmentations to all images in the sequence.
if self.augment:
augmenter = Sequential([
LinearContrast(Deterministic(Uniform(0.7, 1.3))),
Multiply(
Deterministic(Uniform(0.7, 1.3)),
per_channel=Deterministic(DiscreteUniform(0, 1)),
),
Sometimes(
Deterministic(DiscreteUniform(0, 1)),
GaussianBlur(sigma=Deterministic(Uniform(0, 0.7))),
),
],
random_order=True)
images = augmenter(images=images)
for i in range(len(images)):
image = images[i].astype("float32") / 255
images[i] = tensor(image).permute(2, 0, 1).unsqueeze_(0)
return cat(images, dim=0)
def prepare_augmentation_pipeline(self, config):
from imgaug.parameters import DiscreteUniform
br_change = config['trn']['brightness_augmentation_amount'] # (was 70)
contrast_min = config['trn']['augmentation_contrast_min']
contrast_max = config['trn']['augmentation_contrast_max']
rotation = config['trn']['augmentation_rotation']
if rotation == 'uniform':
rotation = DiscreteUniform(0, 360)
translation = config['trn']['augmentation_translation']
scale_min = config['trn']['augmentation_scale_min']
scale_max = config['trn']['augmentation_scale_max']
shear = config['trn']['augmentation_shear']
from imgaug import augmenters as iaa
return iaa.Sequential(
[
iaa.Add(
(-br_change, br_change), per_channel=False
), # change brightness of images (by -10 to 10 of original value)
iaa.contrast.LinearContrast(
(contrast_min, contrast_max),
per_channel=False), # improve or worsen the contrast
iaa.Affine(rotate=rotation,
translate_percent={
"x": (-translation, translation),
'y': (-translation, translation)
},
scale=(scale_min, scale_max),
shear=(-shear, shear),
cval=128),
iaa.Fliplr(p=0.5)
],
random_order=True)
def _draw_sample_point(self, box_w, box_h, img_w, img_h, seed):
x1 = math.ceil(box_w / 2)
y1 = math.ceil(box_h / 2)
x2 = math.floor(img_w - x1)
y2 = math.floor(img_h - y1)
random_state = ia.new_random_state(seed)
x = DiscreteUniform(x1, x2)
y = DiscreteUniform(y1, y2)
center_x = x.draw_sample(random_state=random_state)
center_y = y.draw_sample(random_state=random_state)
return center_x, center_y
def main():
params = [
("Binomial(0.1)", Binomial(0.1)),
("Choice", Choice([0, 1, 2])),
("Choice with p", Choice([0, 1, 2], p=[0.1, 0.2, 0.7])),
("DiscreteUniform(0, 10)", DiscreteUniform(0, 10)),
("Poisson(0)", Poisson(0)),
("Poisson(5)", Poisson(5)),
("Discretize(Poisson(5))", Discretize(Poisson(5))),
("Normal(0, 1)", Normal(0, 1)),
("Normal(1, 1)", Normal(1, 1)),
("Normal(1, 2)", Normal(0, 2)),
("Normal(Choice([-1, 1]), 2)", Normal(Choice([-1, 1]), 2)),
("Discretize(Normal(0, 1.0))", Discretize(Normal(0, 1.0))),
("Positive(Normal(0, 1.0))", Positive(Normal(0, 1.0))),
("Positive(Normal(0, 1.0), mode='reroll')", Positive(Normal(0, 1.0), mode="reroll")),
("Negative(Normal(0, 1.0))", Negative(Normal(0, 1.0))),
("Negative(Normal(0, 1.0), mode='reroll')", Negative(Normal(0, 1.0), mode="reroll")),
("Laplace(0, 1.0)", Laplace(0, 1.0)),
("Laplace(1.0, 3.0)", Laplace(1.0, 3.0)),
("Laplace([-1.0, 1.0], 1.0)", Laplace([-1.0, 1.0], 1.0)),
("ChiSquare(1)", ChiSquare(1)),
("ChiSquare([1, 6])", ChiSquare([1, 6])),
("Weibull(0.5)", Weibull(0.5)),
("Weibull((1.0, 3.0))", Weibull((1.0, 3.0))),
("Uniform(0, 10)", Uniform(0, 10)),
("Beta(0.5, 0.5)", Beta(0.5, 0.5)),
("Deterministic(1)", Deterministic(1)),
("Clip(Normal(0, 1), 0, None)", Clip(Normal(0, 1), minval=0, maxval=None)),
("Multiply(Uniform(0, 10), 2)", Multiply(Uniform(0, 10), 2)),
("Add(Uniform(0, 10), 5)", Add(Uniform(0, 10), 5)),
("Absolute(Normal(0, 1))", Absolute(Normal(0, 1))),
("RandomSign(Poisson(1))", RandomSign(Poisson(1))),
("RandomSign(Poisson(1), 0.9)", RandomSign(Poisson(1), 0.9))
]
params_arithmetic = [
("Normal(0, 1.0)", Normal(0.0, 1.0)),
("Normal(0, 1.0) + 5", Normal(0.0, 1.0) + 5),
("Normal(0, 1.0) * 10", Normal(0.0, 1.0) * 10),
("Normal(0, 1.0) / 10", Normal(0.0, 1.0) / 10),
("Normal(0, 1.0) ** 2", Normal(0.0, 1.0) ** 2)
]
params_noise = [
("SimplexNoise", SimplexNoise()),
("Sigmoid(SimplexNoise)", Sigmoid(SimplexNoise())),
("SimplexNoise(linear)", SimplexNoise(upscale_method="linear")),
("SimplexNoise(nearest)", SimplexNoise(upscale_method="nearest")),
("FrequencyNoise((-4, 4))", FrequencyNoise(exponent=(-4, 4))),
("FrequencyNoise(-2)", FrequencyNoise(exponent=-2)),
("FrequencyNoise(2)", FrequencyNoise(exponent=2))
]
images_params = [param.draw_distribution_graph() for (title, param) in params]
images_arithmetic = [param.draw_distribution_graph() for (title, param) in params_arithmetic]
images_noise = [param.draw_distribution_graph(size=(1000, 10, 10)) for (title, param) in params_noise]
misc.imshow(np.vstack(images_params))
misc.imshow(np.vstack(images_arithmetic))
misc.imshow(np.vstack(images_noise))