from copy import deepcopy
import torch
import numpy as np
from matplotlib import pyplot as plt
from detectron2.engine import DefaultTrainer
from detectron2.data import build_detection_train_loader
from detectron2.data import detection_utils as utils
from detectron2.structures import BoxMode
from imgaug import augmenters as aug
from imgaug.parameters import Normal, TruncatedNormal
from imgaug.augmentables.bbs import BoundingBox, BoundingBoxesOnImage
AUGMENTER = aug.Sequential([
aug.Add(Normal(0, 20), per_channel=True),
aug.Multiply(TruncatedNormal(1, .15, low=.5, high=1.5)),
aug.GaussianBlur((0, 2)),
aug.Fliplr(.5),
aug.Flipud(.5),
aug.Affine(
scale={
'x': TruncatedNormal(1, .1, low=.8, high=1.2),
'y': TruncatedNormal(1, .1, low=.8, high=1.2),
},
translate_percent={
'x': TruncatedNormal(0, .1, low=-.2, high=.2),
'y': TruncatedNormal(0, .1, low=-.2, high=.2),
},
rotate=(-180, 180),
shear={
# ______________________________________________________________________________
# Main Process
# ####
prep_algo = config['preprocess']['prep_algo']
exec(prep_algo['src'])
handler = eval(prep_algo['func_name'])
test_df = pd.read_csv(path.join(DATASET_DIR, 'test.csv'))
aug = iaa.Sequential(
[
iaa.Fliplr(0.5), # horizontally flip 50% of all images
# crop images by -5% to 10% of their height/width
iaa.Affine(
# scale={"x": (0.8, 1.2), "y": (0.8, 1.2)}, # scale images to 80-120% of their size, individually per axis
rotate=Clip(Normal(0, 5), minval=-10,
maxval=10), # rotate by -45 to +45 degrees
translate_percent={
"x": Clip(Normal(0, 0.025), minval=-0.05, maxval=0.05),
"y": Clip(Normal(0, 0.025), minval=-0.05, maxval=0.05)
}, # translate by -20 to +20 percent (per axis)
# shear=(-16, 16), # shear by -16 to +16 degrees
order=3, # use nearest neighbour or bilinear interpolation (fast)
cval=0, # if mode is constant, use a cval between 0 and 255
mode=
'constant', # use any of scikit-image's warping modes (see 2nd image from the top for examples)
backend='cv2',
),
iaa.CropAndPad(
percent=Clip(Normal(0, 0.1), minval=-0.2, maxval=0.2),
pad_mode='constant',
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))
#
# plt.figure(figsize=(10, 2))
# df = df.transpose()
# df.plot.bar()
# plt.show()
# =========================
# mu = 1
# variance = 4
# variance2 = 3
# variance3 = 2
# sigma = math.sqrt(variance)
# sigma=4
# sigma2=3
# sigma3=2
# x = np.linspace(mu - 3*sigma, mu + 3*sigma, 100)
# x2 = np.linspace(mu - 3*sigma2, mu + 3*sigma2, 100)
# x3 = np.linspace(mu - 3*sigma3, mu + 3*sigma3, 100)
# plt.plot(x, stats.norm.pdf(x, mu, sigma))
# plt.plot(x2, stats.norm.pdf(x, mu, sigma))
# plt.plot(x3, stats.norm.pdf(x, mu, sigma))
# plt.show()
from imgaug.parameters import show_distributions_grid, Clip, Normal, Absolute, Add
show_distributions_grid(
[
Add(Absolute(Normal(1.0, 2.0)), 1),
],
graph_sizes=(2048, 2048),
)