import numpy as np
import imgaug.augmenters as iaa


def load_batch(batch_idx):
    # dummy function, implement this
    # Return a numpy array of shape (N, height, width, #channels)
    # or a list of (height, width, #channels) arrays (may have different image
    # sizes).
    # Images should be in RGB for colorspace augmentations.
    # (cv2.imread() returns BGR!)
    # Images should usually be in uint8 with values from 0-255.
    return np.zeros((128, 32, 32, 3), dtype=np.uint8) + (batch_idx % 255)


def train_on_images(images):
    # dummy function, implement this
    pass


seq = iaa.Sequential([
    iaa.Crop(px=(0, 16)), # crop images from each side by 0 to 16px (randomly chosen)
    iaa.Fliplr(0.5), # horizontally flip 50% of the images
    iaa.GaussianBlur(sigma=(0, 3.0)) # blur images with a sigma of 0 to 3.0
])

for batch_idx in range(1000):
    images = load_batch(batch_idx)
    images_aug = seq.augment_images(images)  # done by the library
    train_on_images(images_aug)

import numpy as np
import imgaug as ia
import imgaug.augmenters as iaa


# random example images
images = np.random.randint(0, 255, (16, 128, 128, 3), dtype=np.uint8)

# Sometimes(0.5, ...) applies the given augmenter in 50% of all cases,
# e.g. Sometimes(0.5, GaussianBlur(0.3)) would blur roughly every second image.
sometimes = lambda aug: iaa.Sometimes(0.5, aug)

# Define our sequence of augmentation steps that will be applied to every image
# All augmenters with per_channel=0.5 will sample one value _per image_
# in 50% of all cases. In all other cases they will sample new values
# _per channel_.
seq = iaa.Sequential(
    [
        # apply the following augmenters to most images
        iaa.Fliplr(0.5), # horizontally flip 50% of all images
        iaa.Flipud(0.2), # vertically flip 20% of all images
        # crop images by -5% to 10% of their height/width
        sometimes(iaa.CropAndPad(
            percent=(-0.05, 0.1),
            pad_mode=ia.ALL,
            pad_cval=(0, 255)
        )),
        sometimes(iaa.Affine(
            scale={"x": (0.8, 1.2), "y": (0.8, 1.2)}, # scale images to 80-120% of their size, individually per axis
            translate_percent={"x": (-0.2, 0.2), "y": (-0.2, 0.2)}, # translate by -20 to +20 percent (per axis)
            rotate=(-45, 45), # rotate by -45 to +45 degrees
            shear=(-16, 16), # shear by -16 to +16 degrees
            order=[0, 1], # use nearest neighbour or bilinear interpolation (fast)
            cval=(0, 255), # if mode is constant, use a cval between 0 and 255
            mode=ia.ALL # use any of scikit-image's warping modes (see 2nd image from the top for examples)
        )),
        # execute 0 to 5 of the following (less important) augmenters per image
        # don't execute all of them, as that would often be way too strong
        iaa.SomeOf((0, 5),
            [
                sometimes(iaa.Superpixels(p_replace=(0, 1.0), n_segments=(20, 200))), # convert images into their superpixel representation
                iaa.OneOf([
                    iaa.GaussianBlur((0, 3.0)), # blur images with a sigma between 0 and 3.0
                    iaa.AverageBlur(k=(2, 7)), # blur image using local means with kernel sizes between 2 and 7
                    iaa.MedianBlur(k=(3, 11)), # blur image using local medians with kernel sizes between 2 and 7
                ]),
                iaa.Sharpen(alpha=(0, 1.0), lightness=(0.75, 1.5)), # sharpen images
                iaa.Emboss(alpha=(0, 1.0), strength=(0, 2.0)), # emboss images
                # search either for all edges or for directed edges,
                # blend the result with the original image using a blobby mask
                iaa.SimplexNoiseAlpha(iaa.OneOf([
                    iaa.EdgeDetect(alpha=(0.5, 1.0)),
                    iaa.DirectedEdgeDetect(alpha=(0.5, 1.0), direction=(0.0, 1.0)),
                ])),
                iaa.AdditiveGaussianNoise(loc=0, scale=(0.0, 0.05*255), per_channel=0.5), # add gaussian noise to images
                iaa.OneOf([
                    iaa.Dropout((0.01, 0.1), per_channel=0.5), # randomly remove up to 10% of the pixels
                    iaa.CoarseDropout((0.03, 0.15), size_percent=(0.02, 0.05), per_channel=0.2),
                ]),
                iaa.Invert(0.05, per_channel=True), # invert color channels
                iaa.Add((-10, 10), per_channel=0.5), # change brightness of images (by -10 to 10 of original value)
                iaa.AddToHueAndSaturation((-20, 20)), # change hue and saturation
                # either change the brightness of the whole image (sometimes
                # per channel) or change the brightness of subareas
                iaa.OneOf([
                    iaa.Multiply((0.5, 1.5), per_channel=0.5),
                    iaa.FrequencyNoiseAlpha(
                        exponent=(-4, 0),
                        first=iaa.Multiply((0.5, 1.5), per_channel=True),
                        second=iaa.ContrastNormalization((0.5, 2.0))
                    )
                ]),
                iaa.ContrastNormalization((0.5, 2.0), per_channel=0.5), # improve or worsen the contrast
                iaa.Grayscale(alpha=(0.0, 1.0)),
                sometimes(iaa.ElasticTransformation(alpha=(0.5, 3.5), sigma=0.25)), # move pixels locally around (with random strengths)
                sometimes(iaa.PiecewiseAffine(scale=(0.01, 0.05))), # sometimes move parts of the image around
                sometimes(iaa.PerspectiveTransform(scale=(0.01, 0.1)))
            ],
            random_order=True
        )
    ],
    random_order=True
)

images_aug = seq.augment_images(images)

import numpy as np
import imgaug.augmenters as iaa


images = np.random.randint(0, 255, (16, 128, 128, 3), dtype=np.uint8)
seq = iaa.Sequential([iaa.Fliplr(0.5), iaa.GaussianBlur((0, 3.0))])

# Show an image with 8*8 augmented versions of image 0 and 8*8 augmented
# versions of image 1. Identical augmentations will be applied to
# image 0 and 1.
seq.show_grid([images[0], images[1]], cols=8, rows=8)

import numpy as np
import imgaug as ia
import imgaug.augmenters as iaa
from imgaug.augmentables.kps import KeypointsOnImage


images = np.random.randint(0, 50, (4, 128, 128, 3), dtype=np.uint8)

# Generate random keypoints, 1-10 per image with float32 coordinates
keypoints = []
for image in images:
    n_keypoints = np.random.randint(1, 10)
    kps = np.random.random((n_keypoints, 2))
    kps[:, 0] *= image.shape[0]
    kps[:, 1] *= image.shape[1]
    keypoints.append(kps)

seq = iaa.Sequential([iaa.GaussianBlur((0, 3.0)),
                      iaa.Affine(scale=(0.5, 0.7))])

# augment keypoints and images
images_aug, keypoints_aug = seq(images=images, keypoints=keypoints)

# Example code to show each image and print the new keypoints coordinates
for i in range(len(images)):
    print("[Image #%d]" % (i,))
    keypoints_before = KeypointsOnImage.from_xy_array(
        keypoints[i], shape=images[i].shape)
    keypoints_after = KeypointsOnImage.from_xy_array(
        keypoints_aug[i], shape=images_aug[i].shape)
    image_before = keypoints_before.draw_on_image(images[i])
    image_after = keypoints_after.draw_on_image(images_aug[i])
    ia.imshow(np.hstack([image_before, image_after]))

    kps_zipped = zip(keypoints_before.keypoints,
                     keypoints_after.keypoints)
    for keypoint_before, keypoint_after in kps_zipped:
        x_before, y_before = keypoint_before.x, keypoint_before.y
        x_after, y_after = keypoint_after.x, keypoint_after.y
        print("before aug: x=%d y=%d | after aug: x=%d y=%d" % (
            x_before, y_before, x_after, y_after))

import numpy as np
import imgaug.augmenters as iaa


# Standard scenario: You have N RGB-images and additionally 21 heatmaps per image.
# You want to augment each image and its heatmaps identically.
images = np.random.randint(0, 255, (16, 128, 128, 3), dtype=np.uint8)
heatmaps = np.random.random(size=(16, 64, 64, 1)).astype(np.float32)

seq = iaa.Sequential([
    iaa.GaussianBlur((0, 3.0)),
    iaa.Affine(translate_px={"x": (-40, 40)}),
    iaa.Crop(px=(0, 10))
])

images_aug, heatmaps_aug = seq(images=images, heatmaps=heatmaps)

from imgaug import augmenters as iaa
import numpy as np


images = np.random.randint(0, 255, (16, 128, 128, 3), dtype=np.uint8)

# always horizontally flip each input image
images_aug = iaa.Fliplr(1.0)(images=images)

# vertically flip each input image with 90% probability
images_aug = iaa.Flipud(0.9)(images=images)

# blur image 2 by a sigma of 3.0
images_aug = iaa.GaussianBlur(3.0)(images=images)

# move each input image by 8 to 16px to the left
images_aug = iaa.Affine(translate_px={"x": (-8, -16)})(images=images)

import numpy as np
from imgaug import augmenters as iaa
from imgaug import parameters as iap


images = np.random.randint(0, 255, (16, 128, 128, 3), dtype=np.uint8)

# Blur by a value sigma which is sampled from a uniform distribution
# of range 0.1 <= x < 3.0.
# The convenience shortcut for this is: GaussianBlur((0.1, 3.0))
blurer = iaa.GaussianBlur(iap.Uniform(0.1, 3.0))
images_aug = blurer.augment_images(images)

# Blur by a value sigma which is sampled from a normal distribution N(1.0, 0.1),
# i.e. sample a value that is usually around 1.0.
# Clip the resulting value so that it never gets below 0.1 or above 3.0.
blurer = iaa.GaussianBlur(iap.Clip(iap.Normal(1.0, 0.1), 0.1, 3.0))
images_aug = blurer.augment_images(images)

# Same again, but this time the mean of the normal distribution is not constant,
# but comes itself from a uniform distribution between 0.5 and 1.5.
blurer = iaa.GaussianBlur(iap.Clip(iap.Normal(iap.Uniform(0.5, 1.5), 0.1), 0.1, 3.0))
images_aug = blurer.augment_images(images)

# Sample sigma from one of exactly three allowed values: 0.5, 1.0 or 1.5.
# The convenience shortcut for this is: GaussianBlur([0.5, 1.0, 1.5])
blurer = iaa.GaussianBlur(iap.Choice([0.5, 1.0, 1.5]))
images_aug = blurer.augment_images(images)

# Sample sigma from a discrete uniform distribution of range 1 <= sigma <= 5,
# i.e. sigma will have any of the following values: 1, 2, 3, 4, 5.
blurer = iaa.GaussianBlur(iap.DiscreteUniform(1, 5))
images_aug = blurer.augment_images(images)

from skimage import data
import imgaug as ia
import imgaug.augmenters as iaa
from imgaug.augmentables.batches import Batch


# Number of batches and batch size for this example
nb_batches = 10
batch_size = 32

# Example augmentation sequence to run in the background
augseq = iaa.Sequential([
    iaa.Fliplr(0.5),
    iaa.CoarseDropout(p=0.1, size_percent=0.1)
])

# For simplicity, we use the same image here many times
astronaut = data.astronaut()
astronaut = ia.imresize_single_image(astronaut, (64, 64))

# Make batches out of the example image (here: 10 batches, each 32 times
# the example image)
batches = []
for _ in range(nb_batches):
    batches.append(Batch(images=[astronaut] * batch_size))

# Show the augmented images.
# Note that augment_batches() returns a generator.
for images_aug in augseq.augment_batches(batches, background=True):
    ia.imshow(ia.draw_grid(images_aug, cols=8))

import numpy as np
import imgaug as ia
import imgaug.augmenters as iaa


# Basic augmentation sequence. PiecewiseAffine is slow and therefore well suited
# for augmentation on multiple CPU cores.
aug = iaa.Sequential([
    iaa.Fliplr(0.5),
    iaa.PiecewiseAffine((0.0, 0.1))
])

# generator that yields images
def create_image_generator(nb_batches, size):
    for _ in range(nb_batches):
        # Add e.g. keypoints=... or bounding_boxes=... here to also augment
        # keypoints / bounding boxes on these images.
        yield ia.Batch(
            images=np.random.randint(0, 255, size=size).astype(np.uint8)
        )

# 500 batches of images, each containing 10 images of size 128x128x3
my_generator = create_image_generator(500, (10, 128, 128, 3))

# Start a pool to augment on multiple CPU cores.
#   * processes=-1 means that all CPU cores except one are used for the
#     augmentation, so one is kept free to move data to the GPU
#   * maxtasksperchild=20 restarts child workers every 20 tasks -- only use this
#     if you encounter problems such as memory leaks. Restarting child workers
#     decreases performance.
#   * seed=123 makes the result of the whole augmentation process deterministic
#     between runs of this script, i.e. reproducible results.
with aug.pool(processes=-1, maxtasksperchild=20, seed=123) as pool:
    # Augment on multiple CPU cores.
    #   * The result of imap_batches() is also a generator.
    #   * Use map_batches() if your input is a list.
    #   * chunksize=10 controls how much data to send to each child worker per
    #     transfer, set it higher for better performance.
    batches_aug_generator = pool.imap_batches(my_generator, chunksize=10)

    for i, batch_aug in enumerate(batches_aug_generator):
        # show first augmented image in first batch
        if i == 0:
            ia.imshow(batch_aug.images_aug[0])
        # do something else with the batch here

import numpy as np
import imgaug.augmenters as iaa


# fake RGB images
images = np.random.randint(0, 255, (16, 128, 128, 3), dtype=np.uint8)

# add a random value from the range (-30, 30) to the first two channels of
# input images (e.g. to the R and G channels)
aug = iaa.WithChannels(
  channels=[0, 1],
  children=iaa.Add((-30, 30))
)

images_aug = aug.augment_images(images)

import numpy as np
import imgaug as ia
import imgaug.augmenters as iaa


# images and heatmaps, just arrays filled with value 30
images = np.ones((16, 128, 128, 3), dtype=np.uint8) * 30
heatmaps = np.ones((16, 128, 128, 21), dtype=np.uint8) * 30

# add vertical lines to see the effect of flip
images[:, 16:128-16, 120:124, :] = 120
heatmaps[:, 16:128-16, 120:124, :] = 120

seq = iaa.Sequential([
  iaa.Fliplr(0.5, name="Flipper"),
  iaa.GaussianBlur((0, 3.0), name="GaussianBlur"),
  iaa.Dropout(0.02, name="Dropout"),
  iaa.AdditiveGaussianNoise(scale=0.01*255, name="MyLittleNoise"),
  iaa.AdditiveGaussianNoise(loc=32, scale=0.0001*255, name="SomeOtherNoise"),
  iaa.Affine(translate_px={"x": (-40, 40)}, name="Affine")
])

# change the activated augmenters for heatmaps,
# we only want to execute horizontal flip, affine transformation and one of
# the gaussian noises
def activator_heatmaps(images, augmenter, parents, default):
    if augmenter.name in ["GaussianBlur", "Dropout", "MyLittleNoise"]:
        return False
    else:
        # default value for all other augmenters
        return default
hooks_heatmaps = ia.HooksImages(activator=activator_heatmaps)

seq_det = seq.to_deterministic() # call this for each batch again, NOT only once at the start
images_aug = seq_det.augment_images(images)
heatmaps_aug = seq_det.augment_images(heatmaps, hooks=hooks_heatmaps)