def draw_single_sequential_images():
image = misc.imresize(ndimage.imread("quokka.jpg")[0:643, 0:643], (128, 128))
st = lambda aug: iaa.Sometimes(0.5, aug)
seq = iaa.Sequential([
iaa.Fliplr(0.5),
iaa.Flipud(0.5),
st(iaa.Crop(percent=(0, 0.1))),
st(iaa.GaussianBlur((0, 3.0))),
st(iaa.AdditiveGaussianNoise(loc=0, scale=(0.0, 0.2), per_channel=0.5)),
st(iaa.Dropout((0.0, 0.1), per_channel=0.5)),
st(iaa.Add((-10, 10), per_channel=0.5)),
st(iaa.Multiply((0.5, 1.5), per_channel=0.5)),
st(iaa.ContrastNormalization((0.5, 2.0), per_channel=0.5)),
st(iaa.Affine(
scale={"x": (0.8, 1.2), "y": (0.8, 1.2)},
translate_px={"x": (-16, 16), "y": (-16, 16)},
rotate=(-45, 45),
shear=(-16, 16),
order=ia.ALL,
cval=(0, 1.0),
mode=ia.ALL
)),
st(iaa.ElasticTransformation(alpha=(0.5, 3.5), sigma=0.25))
],
random_order=True
)
grid = seq.draw_grid(image, cols=8, rows=8)
misc.imsave("examples_grid.jpg", grid)
def main():
images = [
misc.imresize(
ndimage.imread("../quokka.jpg")[0:643, 0:643], (128, 128)),
misc.imresize(data.astronaut(), (128, 128))
]
augmenters = [
iaa.Noop(name="Noop"),
iaa.Crop(px=(0, 8), name="Crop-px"),
iaa.Crop(percent=(0, 0.1), name="Crop-percent"),
iaa.Fliplr(0.5, name="Fliplr"),
iaa.Flipud(0.5, name="Flipud"),
iaa.Grayscale(0.5, name="Grayscale0.5"),
iaa.Grayscale(1.0, name="Grayscale1.0"),
iaa.GaussianBlur((0, 3.0), name="GaussianBlur"),
iaa.AdditiveGaussianNoise(loc=0,
scale=(0.0, 0.1),
name="AdditiveGaussianNoise"),
iaa.Dropout((0.0, 0.1), name="Dropout"),
iaa.Multiply((0.5, 1.5), name="Multiply"),
iaa.ContrastNormalization(alpha=(0.5, 2.0)),
iaa.Affine(scale={
"x": (0.8, 1.2),
"y": (0.8, 1.2)
},
translate_px={
"x": (-16, 16),
"y": (-16, 16)
},
rotate=(-45, 45),
shear=(-16, 16),
order=ia.ALL,
cval=(0, 1.0),
mode=ia.ALL,
name="Affine"),
iaa.ElasticTransformation(alpha=(0.5, 8.0), sigma=1.0)
]
#for i, aug in enumerate(augmenters):
#print(i)
#aug.deepcopy()
#import copy
#copy.deepcopy(aug)
seq = iaa.Sequential([aug.copy() for aug in augmenters], name="Sequential")
st = iaa.Sometimes(0.5, seq.copy(), name="Sometimes")
augmenters.append(seq)
augmenters.append(st)
for augmenter in augmenters:
print("Augmenter: %s" % (augmenter.name, ))
grid = augmenter.draw_grid(images, rows=1, cols=16)
misc.imshow(grid)
def draw_per_augmenter_images():
print("[draw_per_augmenter_images] Loading image...")
image = misc.imresize(ndimage.imread("quokka.jpg")[0:643, 0:643], (128, 128))
#image = misc.imresize(data.chelsea()[0:300, 50:350, :], (128, 128))
#image = misc.imresize(data.astronaut(), (128, 128))
#keypoints = [ia.Keypoint(x=43, y=43), ia.Keypoint(x=78, y=40), ia.Keypoint(x=64, y=73)] # left eye, right eye, mouth
keypoints = [ia.Keypoint(x=34, y=15), ia.Keypoint(x=85, y=13), ia.Keypoint(x=63, y=73)] # left ear, right ear, mouth
keypoints = [ia.KeypointsOnImage(keypoints, shape=image.shape)]
print("[draw_per_augmenter_images] Initializing...")
rows_augmenters = [
("Noop", [("", iaa.Noop()) for _ in range(5)]),
#("Crop", [iaa.Crop(px=vals) for vals in [(2, 4), (4, 8), (6, 16), (8, 32), (10, 64)]]),
("Crop\n(top, right,\nbottom, left)", [(str(vals), iaa.Crop(px=vals)) for vals in [(2, 0, 0, 0), (0, 8, 8, 0), (4, 0, 16, 4), (8, 0, 0, 32), (32, 64, 0, 0)]]),
("Fliplr", [(str(p), iaa.Fliplr(p)) for p in [0, 0, 1, 1, 1]]),
("Flipud", [(str(p), iaa.Flipud(p)) for p in [0, 0, 1, 1, 1]]),
("Add", [("value=%d" % (val,), iaa.Add(val)) for val in [-45, -25, 0, 25, 45]]),
("Add\n(per channel)", [("value=(%d, %d)" % (vals[0], vals[1],), iaa.Add(vals, per_channel=True)) for vals in [(-55, -35), (-35, -15), (-10, 10), (15, 35), (35, 55)]]),
("Multiply", [("value=%.2f" % (val,), iaa.Multiply(val)) for val in [0.25, 0.5, 1.0, 1.25, 1.5]]),
("Multiply\n(per channel)", [("value=(%.2f, %.2f)" % (vals[0], vals[1],), iaa.Multiply(vals, per_channel=True)) for vals in [(0.15, 0.35), (0.4, 0.6), (0.9, 1.1), (1.15, 1.35), (1.4, 1.6)]]),
("GaussianBlur", [("sigma=%.2f" % (sigma,), iaa.GaussianBlur(sigma=sigma)) for sigma in [0.25, 0.50, 1.0, 2.0, 4.0]]),
("AdditiveGaussianNoise", [("scale=%.2f" % (scale,), iaa.AdditiveGaussianNoise(scale=scale * 255)) for scale in [0.025, 0.05, 0.1, 0.2, 0.3]]),
("AdditiveGaussianNoise\n(per channel)", [("scale=%.2f" % (scale,), iaa.AdditiveGaussianNoise(scale=scale * 255, per_channel=True)) for scale in [0.025, 0.05, 0.1, 0.2, 0.3]]),
("Dropout", [("p=%.2f" % (p,), iaa.Dropout(p=p)) for p in [0.025, 0.05, 0.1, 0.2, 0.4]]),
("Dropout\n(per channel)", [("p=%.2f" % (p,), iaa.Dropout(p=p, per_channel=True)) for p in [0.025, 0.05, 0.1, 0.2, 0.4]]),
("ContrastNormalization", [("alpha=%.1f" % (alpha,), iaa.ContrastNormalization(alpha=alpha)) for alpha in [0.5, 0.75, 1.0, 1.25, 1.50]]),
("ContrastNormalization\n(per channel)", [("alpha=(%.2f, %.2f)" % (alphas[0], alphas[1],), iaa.ContrastNormalization(alpha=alphas, per_channel=True)) for alphas in [(0.4, 0.6), (0.65, 0.85), (0.9, 1.1), (1.15, 1.35), (1.4, 1.6)]]),
("Affine: Scale", [("%.1fx" % (scale,), iaa.Affine(scale=scale)) for scale in [0.1, 0.5, 1.0, 1.5, 1.9]]),
("Affine: Translate", [("x=%d y=%d" % (x, y), iaa.Affine(translate_px={"x": x, "y": y})) for x, y in [(-32, -16), (-16, -32), (-16, -8), (16, 8), (16, 32)]]),
("Affine: Rotate", [("%d deg" % (rotate,), iaa.Affine(rotate=rotate)) for rotate in [-90, -45, 0, 45, 90]]),
("Affine: Shear", [("%d deg" % (shear,), iaa.Affine(shear=shear)) for shear in [-45, -25, 0, 25, 45]]),
("Affine: Modes", [(mode, iaa.Affine(translate_px=-32, mode=mode)) for mode in ["constant", "edge", "symmetric", "reflect", "wrap"]]),
("Affine: cval", [("%.2f" % (cval,), iaa.Affine(translate_px=-32, cval=cval, mode="constant")) for cval in [0.0, 0.25, 0.5, 0.75, 1.0]]),
(
"Affine: all", [
(
"",
iaa.Affine(
scale={"x": (0.5, 1.5), "y": (0.5, 1.5)},
translate_px={"x": (-32, 32), "y": (-32, 32)},
rotate=(-45, 45),
shear=(-32, 32),
mode=ia.ALL,
cval=(0.0, 1.0)
)
)
for _ in range(5)
]
),
("ElasticTransformation\n(sigma=0.2)", [("alpha=%.1f" % (alpha,), iaa.ElasticTransformation(alpha=alpha, sigma=0.2)) for alpha in [0.1, 0.5, 1.0, 3.0, 9.0]])
]
print("[draw_per_augmenter_images] Augmenting...")
rows = []
for (row_name, augmenters) in rows_augmenters:
row_images = []
row_keypoints = []
row_titles = []
for img_title, augmenter in augmenters:
aug_det = augmenter.to_deterministic()
row_images.append(aug_det.augment_image(image))
row_keypoints.append(aug_det.augment_keypoints(keypoints)[0])
row_titles.append(img_title)
rows.append((row_name, row_images, row_keypoints, row_titles))
print("[draw_per_augmenter_images] Plotting...")
width = 8
height = int(1.5 * len(rows_augmenters))
fig = plt.figure(figsize=(width, height))
grid_rows = len(rows)
grid_cols = 1 + 5
gs = gridspec.GridSpec(grid_rows, grid_cols, width_ratios=[2, 1, 1, 1, 1, 1])
axes = []
for i in range(grid_rows):
axes.append([plt.subplot(gs[i, col_idx]) for col_idx in range(grid_cols)])
fig.tight_layout()
#fig.subplots_adjust(bottom=0.2 / grid_rows, hspace=0.22)
#fig.subplots_adjust(wspace=0.005, hspace=0.425, bottom=0.02)
fig.subplots_adjust(wspace=0.005, hspace=0.005, bottom=0.02)
for row_idx, (row_name, row_images, row_keypoints, row_titles) in enumerate(rows):
axes_row = axes[row_idx]
for col_idx in range(grid_cols):
ax = axes_row[col_idx]
ax.cla()
ax.axis("off")
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
if col_idx == 0:
ax.text(0, 0.5, row_name, color="black")
else:
cell_image = row_images[col_idx-1]
cell_keypoints = row_keypoints[col_idx-1]
cell_image_kp = cell_keypoints.draw_on_image(cell_image, size=5)
ax.imshow(cell_image_kp)
x = 0
y = 145
#ax.text(x, y, row_titles[col_idx-1], color="black", backgroundcolor="white", fontsize=6)
ax.text(x, y, row_titles[col_idx-1], color="black", fontsize=7)
fig.savefig("examples.jpg", bbox_inches="tight")
def augment_data():
aug_data = np.zeros((4000, 227, 227, 3))
st = lambda aug: iaa.Sometimes(0.5, aug)
seq = iaa.Sequential(
[
iaa.Fliplr(0.5), # horizontally flip 50% of all images
iaa.Flipud(0.5), # vertically flip 50% of all images
st(iaa.Crop(
percent=(0,
0.1))), # crop images by 0-10% of their height/width
st(iaa.GaussianBlur(
(0, 3.0))), # blur images with a sigma between 0 and 3.0
st(
iaa.AdditiveGaussianNoise(
loc=0, scale=(0.0, 0.2),
per_channel=0.5)), # add gaussian noise to images
st(iaa.Dropout(
(0.0, 0.1),
per_channel=0.5)), # randomly remove up to 10% of the pixels
st(iaa.Add(
(-10, 10), per_channel=0.5
)), # change brightness of images (by -10 to 10 of original value)
st(iaa.Multiply((0.5, 1.5), per_channel=0.5)
), # change brightness of images (50-150% of original value)
st(iaa.ContrastNormalization(
(0.5, 2.0),
per_channel=0.5)), # improve or worsen the contrast
st(
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_px={
"x": (-16, 16),
"y": (-16, 16)
}, # translate by -16 to +16 pixels (per axis)
rotate=(-45, 45), # rotate by -45 to +45 degrees
shear=(-16, 16), # shear by -16 to +16 degrees
#order=ia.ALL, # use any of scikit-image's interpolation methods
cval=(
0, 1.0
), # if mode is constant, use a cval between 0 and 1.0
#mode=ia.ALL # use any of scikit-image's warping modes (see 2nd image from the top for examples)
)),
st(iaa.ElasticTransformation(alpha=(0.5, 3.5), sigma=0.25)
) # apply elastic transformations with random strengths
],
random_order=True # do all of the above in random order
)
for i in range(4000):
img = plt.imread(trainfileName(i + 1))
image_aug = seq.augment_image(img)
#gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#gray = rgb2gray(img)
aug_data[i, ...] = image_aug.astype(float) / 255
np.save("aug_data_1.npy", aug_data)
#augment_data()
def example_heavy_augmentations():
print("Example: Heavy Augmentations")
import imgaug as ia
#from imgaug import augmenters as iaa
import 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.
st = 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(
[
iaa.Fliplr(0.5), # horizontally flip 50% of all images
iaa.Flipud(0.5), # vertically flip 50% of all images
st(iaa.Crop(
percent=(0,
0.1))), # crop images by 0-10% of their height/width
st(iaa.GaussianBlur(
(0, 3.0))), # blur images with a sigma between 0 and 3.0
st(
iaa.AdditiveGaussianNoise(
loc=0, scale=(0.0, 0.05 * 255),
per_channel=0.5)), # add gaussian noise to images
st(iaa.Dropout(
(0.0, 0.1),
per_channel=0.5)), # randomly remove up to 10% of the pixels
st(iaa.Add(
(-10, 10), per_channel=0.5
)), # change brightness of images (by -10 to 10 of original value)
st(iaa.Multiply((0.5, 1.5), per_channel=0.5)
), # change brightness of images (50-150% of original value)
st(iaa.ContrastNormalization(
(0.5, 2.0),
per_channel=0.5)), # improve or worsen the contrast
st(iaa.Grayscale((0.0, 1.0))), # blend with grayscale image
st(
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_px={
"x": (-16, 16),
"y": (-16, 16)
}, # translate by -16 to +16 pixels (per axis)
rotate=(-45, 45), # rotate by -45 to +45 degrees
shear=(-16, 16), # shear by -16 to +16 degrees
order=[
0,
1
], # use scikit-image's interpolation orders 0 (nearest neighbour) and 1 (bilinear)
cval=(
0, 1.0
), # if mode is constant, use a cval between 0 and 1.0
mode=ia.
ALL # use any of scikit-image's warping modes (see 2nd image from the top for examples)
)),
st(iaa.ElasticTransformation(alpha=(0.5, 3.5), sigma=0.25)
) # apply elastic transformations with random strengths
],
random_order=True # do all of the above in random order
)
images_aug = seq.augment_images(images)
# -----
# Make sure that the example really does something
assert not np.array_equal(images, images_aug)
def main():
augmenters = [
iaa.Noop(name="Noop"),
iaa.Crop(px=(0, 8), name="Crop-px"),
iaa.Crop(percent=(0, 0.1), name="Crop-percent"),
iaa.Fliplr(0.5, name="Fliplr"),
iaa.Flipud(0.5, name="Flipud"),
iaa.Grayscale((0.0, 1.0), name="Grayscale"),
iaa.GaussianBlur((0, 3.0), name="GaussianBlur"),
iaa.AdditiveGaussianNoise(loc=0,
scale=(0.0, 0.1),
name="AdditiveGaussianNoise"),
iaa.Dropout((0.0, 0.1), name="Dropout"),
iaa.Multiply((0.5, 1.5), name="Multiply"),
iaa.ContrastNormalization(alpha=(0.5, 2.0),
name="ContrastNormalization"),
iaa.Grayscale(alpha=(0.0, 1.0), name="Grayscale"),
iaa.ElasticTransformation(alpha=(0.5, 8.0),
sigma=1.0,
name="ElasticTransformation"),
iaa.Affine(scale={
"x": (0.8, 1.2),
"y": (0.8, 1.2)
},
translate_px={
"x": (-16, 16),
"y": (-16, 16)
},
rotate=(-45, 45),
shear=(-16, 16),
order=0,
cval=(0, 1.0),
mode="constant",
name="AffineOrder0ModeConstant")
]
for order in [0, 1]:
augmenters.append(
iaa.Affine(scale={
"x": (0.8, 1.2),
"y": (0.8, 1.2)
},
translate_px={
"x": (-16, 16),
"y": (-16, 16)
},
rotate=(-45, 45),
shear=(-16, 16),
order=order,
cval=(0, 1.0),
mode=ia.ALL,
name="AffineOrder%d" % (order, )))
augmenters.append(
iaa.Affine(scale={
"x": (0.8, 1.2),
"y": (0.8, 1.2)
},
translate_px={
"x": (-16, 16),
"y": (-16, 16)
},
rotate=(-45, 45),
shear=(-16, 16),
order=ia.ALL,
cval=(0, 1.0),
mode=ia.ALL,
name="AffineAll"))
kps = []
for _ in range(20):
x = random.randint(0, 31)
y = random.randint(0, 31)
kps.append(ia.Keypoint(x=x, y=y))
kps = ia.KeypointsOnImage(kps, shape=(32, 32, 3))
#small_keypoints_one = ia.KeypointsOnImage([ia.Keypoint(x=0, y=0), ia.Keypoint(x=1, y=1), ia.Keypoint(x=3, y=3)], shape=(4, 4, 3))
#medium_keypoints_one = ia.KeypointsOnImage([ia.Keypoint(x=0, y=0), ia.Keypoint(x=16, y=16), ia.Keypoint(x=31, y=31)], shape=(32, 32, 3))
#large_keypoints_one = ia.KeypointsOnImage([ia.Keypoint(x=0, y=0), ia.Keypoint(x=128, y=128), ia.Keypoint(x=255, y=255)], shape=(256, 256, 3))
small_keypoints_one = kps.on((4, 4, 3))
medium_keypoints_one = kps.on((32, 32, 3))
large_keypoints_one = kps.on((256, 256, 3))
small_keypoints = [small_keypoints_one.deepcopy() for _ in range(16)]
medium_keypoints = [medium_keypoints_one.deepcopy() for _ in range(16)]
large_keypoints = [large_keypoints_one.deepcopy() for _ in range(16)]
small_images = np.random.randint(0, 255, (16, 4, 4, 3)).astype(np.uint8)
medium_images = np.random.randint(0, 255, (16, 32, 32, 3)).astype(np.uint8)
large_images = np.random.randint(0, 255,
(16, 256, 256, 3)).astype(np.uint8)
print("---------------------------")
print("Keypoints")
print("---------------------------")
for augmenter in augmenters:
print("[Augmenter: %s]" % (augmenter.name, ))
for keypoints in [small_keypoints, medium_keypoints, large_keypoints]:
times = []
for i in range(100):
time_start = time.time()
img_aug = augmenter.augment_keypoints(keypoints)
time_end = time.time()
times.append(time_end - time_start)
times = np.array(times)
img_str = "{:20s}".format(keypoints[0].shape)
print("%s | SUM %.5fs | PER ITER avg %.5fs, min %.5fs, max %.5fs" %
(img_str, np.sum(times), np.average(times), np.min(times),
np.max(times)))
print("---------------------------")
print("Images")
print("---------------------------")
for augmenter in augmenters:
print("[Augmenter: %s]" % (augmenter.name, ))
for images in [small_images, medium_images, large_images]:
times = []
for i in range(100):
time_start = time.time()
img_aug = augmenter.augment_images(images)
time_end = time.time()
times.append(time_end - time_start)
times = np.array(times)
img_str = "{:20s}".format(images.shape)
print("%s | SUM %.5fs | PER ITER avg %.5fs, min %.5fs, max %.5fs" %
(img_str, np.sum(times), np.average(times), np.min(times),
np.max(times)))