def chapter_alpha_masks_introduction(): # ----------------------------------------- # example introduction # ----------------------------------------- import imgaug as ia from imgaug import augmenters as iaa ia.seed(2) # Example batch of images. # The array has shape (8, 128, 128, 3) and dtype uint8. images = np.array([ia.quokka(size=(128, 128)) for _ in range(8)], dtype=np.uint8) seqs = [ iaa.BlendAlpha((0.0, 1.0), foreground=iaa.MedianBlur(11), per_channel=True), iaa.BlendAlphaSimplexNoise(foreground=iaa.EdgeDetect(1.0), per_channel=False), iaa.BlendAlphaSimplexNoise(foreground=iaa.EdgeDetect(1.0), background=iaa.LinearContrast((0.5, 2.0)), per_channel=0.5), iaa.BlendAlphaFrequencyNoise(foreground=iaa.Affine(rotate=(-10, 10), translate_px={ "x": (-4, 4), "y": (-4, 4) }), background=iaa.AddToHueAndSaturation( (-40, 40)), per_channel=0.5), iaa.BlendAlphaSimplexNoise(foreground=iaa.BlendAlphaSimplexNoise( foreground=iaa.EdgeDetect(1.0), background=iaa.LinearContrast((0.5, 2.0)), per_channel=True), background=iaa.BlendAlphaFrequencyNoise( exponent=(-2.5, -1.0), foreground=iaa.Affine(rotate=(-10, 10), translate_px={ "x": (-4, 4), "y": (-4, 4) }), background=iaa.AddToHueAndSaturation( (-40, 40)), per_channel=True), per_channel=True, aggregation_method="max", sigmoid=False) ] cells = [] for seq in seqs: images_aug = seq(images=images) cells.extend(images_aug) # ------------ save("alpha", "introduction.jpg", grid(cells, cols=8, rows=5))
def get_preview(images, augmentationList): """ Accepts a list of images and augmentationList as input. Provides a list of augmented images in that order as ouptut. """ augmented = [] for image in images: for augmentation in augmentationList: aug_id = augmentation['id'] params = augmentation['params'] if (aug_id == 1): image = iaa.SaltAndPepper(p=params[0], per_channel=params[1])(image=image) elif (aug_id == 2): image = iaa.imgcorruptlike.GaussianNoise( severity=(params[0], params[1]))(image=image) elif (aug_id == 3): image = iaa.Rain(speed=(params[0], params[1]), drop_size=(params[2], params[3]))(image=image) elif (aug_id == 4): image = iaa.imgcorruptlike.Fog( severity=(params[0], params[1]))(image=image) elif (aug_id == 5): image = iaa.imgcorruptlike.Snow( severity=(params[0], params[1]))(image=image) elif (aug_id == 6): image = iaa.imgcorruptlike.Spatter( severity=(params[0], params[1]))(image=image) elif (aug_id == 7): image = iaa.BlendAlphaSimplexNoise( iaa.EdgeDetect(1))(image=image) elif (aug_id == 8): image = iaa.Rotate(rotate=(params[0], params[1]))(image=image) elif (aug_id == 9): image = iaa.Affine()(image=image) #to be implemented elif (aug_id == 10): image = iaa.MotionBlur(k=params[0], angle=(params[1], params[2]))(image=image) elif (aug_id == 11): image = iaa.imgcorruptlike.ZoomBlur( severity=(params[0], params[1]))(image=image) elif (aug_id == 12): image = iaa.AddToBrightness()(image=image) #to be implemented elif (aug_id == 13): image = iaa.ChangeColorTemperature( kelvin=(params[0], params[1]))(image=image) elif (aug_id == 14): image = iaa.SigmoidContrast()(image=image) #to be implemented elif (aug_id == 15): image = iaa.Cutout(nb_iterations=(params[0], params[1]), size=params[2], squared=params[3])(image=image) else: print("Not implemented") augmented.append(image) return augmented
def __init__(self, folders_train, folders_val, num_classes): ''' All paths to the images to train and validate. Inputs --------- folders_train : list A list of folders where are the dataset to train. folders_val : list A list of folders where are the dataset to validation. num_classes : int Number of classes ''' self.num_classes = num_classes # map paths and split dataset self.path_train = [] self.path_test = [] for path in folders_train: self.path_train.extend(glob(os.path.join(path, '*_image.jpg'))) for path in folders_val: self.path_test.extend(glob(os.path.join(path, '*_image.jpg'))) print( f'Total train: {len(self.path_train)}, Total val: {len(self.path_test)}' ) # options for augmentation self.aug = iaa.SomeOf((0, 3), [ iaa.Affine(rotate=(-10, 10), scale={ "x": (0.5, 1.2), "y": (0.5, 1.2) }), iaa.AdditiveGaussianNoise(scale=0.2 * 255), iaa.GaussianBlur(sigma=(0.0, 3.0)), iaa.BlendAlphaSimplexNoise(iaa.EdgeDetect(1.0), sigmoid_thresh=iap.Normal(10.0, 5.0)), iaa.Add(50, per_channel=True), iaa.WithChannels(0, iaa.Add((10, 100))), iaa.Sharpen(alpha=0.2), iaa.Fliplr(), iaa.Flipud() ])
def _load_augmentation_aug_all(): """ Load image augmentation model """ def sometimes(aug): return iaa.Sometimes(0.5, aug) return 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='constant', pad_cval=(0, 255))), sometimes( iaa.Affine( # scale images to 80-120% of their size, individually per axis scale={ "x": (0.8, 1.2), "y": (0.8, 1.2) }, # translate by -20 to +20 percent (per axis) translate_percent={ "x": (-0.2, 0.2), "y": (-0.2, 0.2) }, rotate=(-45, 45), # rotate by -45 to +45 degrees shear=(-16, 16), # shear by -16 to +16 degrees # use nearest neighbour or bilinear interpolation (fast) order=[0, 1], # if mode is constant, use a cval between 0 and 255 cval=(0, 255), # use any of scikit-image's warping modes # (see 2nd image from the top for examples) mode='constant')), # 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), [ # convert images into their superpixel representation sometimes( iaa.Superpixels(p_replace=(0, 1.0), n_segments=(20, 200))), iaa.OneOf([ # blur images with a sigma between 0 and 3.0 iaa.GaussianBlur((0, 3.0)), # blur image using local means with kernel sizes # between 2 and 7 iaa.AverageBlur(k=(2, 7)), # blur image using local medians with kernel sizes # between 2 and 7 iaa.MedianBlur(k=(3, 11)), ]), 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.BlendAlphaSimplexNoise( iaa.OneOf([ iaa.EdgeDetect(alpha=(0.5, 1.0)), iaa.DirectedEdgeDetect(alpha=(0.5, 1.0), direction=(0.0, 1.0)), ])), # add gaussian noise to images iaa.AdditiveGaussianNoise( loc=0, scale=(0.0, 0.05 * 255), per_channel=0.5), iaa.OneOf([ # randomly remove up to 10% of the pixels iaa.Dropout((0.01, 0.1), per_channel=0.5), iaa.CoarseDropout((0.03, 0.15), size_percent=(0.02, 0.05), per_channel=0.2), ]), # invert color channels iaa.Invert(0.05, per_channel=True), # change brightness of images (by -10 to 10 of original value) iaa.Add((-10, 10), per_channel=0.5), # change hue and saturation iaa.AddToHueAndSaturation((-20, 20)), # 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.BlendAlphaFrequencyNoise( exponent=(-4, 0), foreground=iaa.Multiply( (0.5, 1.5), per_channel=True), background=iaa.contrast.LinearContrast((0.5, 2.0))) ]), # improve or worsen the contrast iaa.contrast.LinearContrast((0.5, 2.0), per_channel=0.5), iaa.Grayscale(alpha=(0.0, 1.0)), # move pixels locally around (with random strengths) sometimes( iaa.ElasticTransformation(alpha=(0.5, 3.5), sigma=0.25) ), # sometimes move parts of the image around sometimes(iaa.PiecewiseAffine(scale=(0.01, 0.05))), sometimes(iaa.PerspectiveTransform(scale=(0.01, 0.1))) ], random_order=True) ], random_order=True)
def test_dtype_preservation(): reseed() size = (4, 16, 16, 3) images = [ np.random.uniform(0, 255, size).astype(np.uint8), np.random.uniform(0, 65535, size).astype(np.uint16), np.random.uniform(0, 4294967295, size).astype(np.uint32), np.random.uniform(-128, 127, size).astype(np.int16), np.random.uniform(-32768, 32767, size).astype(np.int32), np.random.uniform(0.0, 1.0, size).astype(np.float32), np.random.uniform(-1000.0, 1000.0, size).astype(np.float16), np.random.uniform(-1000.0, 1000.0, size).astype(np.float32), np.random.uniform(-1000.0, 1000.0, size).astype(np.float64) ] default_dtypes = set([arr.dtype for arr in images]) # Some dtypes are here removed per augmenter, because the respective # augmenter does not support them. This test currently only checks whether # dtypes are preserved from in- to output for all dtypes that are supported # per augmenter. # dtypes are here removed via list comprehension instead of # `default_dtypes - set([dtype])`, because the latter one simply never # removed the dtype(s) for some reason def _not_dts(dts): return [dt for dt in default_dtypes if dt not in dts] augs = [ (iaa.Add((-5, 5), name="Add"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.AddElementwise((-5, 5), name="AddElementwise"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.AdditiveGaussianNoise(0.01*255, name="AdditiveGaussianNoise"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.Multiply((0.95, 1.05), name="Multiply"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.Dropout(0.01, name="Dropout"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.CoarseDropout(0.01, size_px=6, name="CoarseDropout"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.Invert(0.01, per_channel=True, name="Invert"), default_dtypes), (iaa.GaussianBlur(sigma=(0.95, 1.05), name="GaussianBlur"), _not_dts([np.float16])), (iaa.AverageBlur((3, 5), name="AverageBlur"), _not_dts([np.uint32, np.int32, np.float16])), (iaa.MedianBlur((3, 5), name="MedianBlur"), _not_dts([np.uint32, np.int32, np.float16, np.float64])), (iaa.BilateralBlur((3, 5), name="BilateralBlur"), _not_dts([np.uint16, np.uint32, np.int16, np.int32, np.float16, np.float64])), (iaa.Sharpen((0.0, 0.1), lightness=(1.0, 1.2), name="Sharpen"), _not_dts([np.uint32, np.int32, np.float16, np.uint32])), (iaa.Emboss(alpha=(0.0, 0.1), strength=(0.5, 1.5), name="Emboss"), _not_dts([np.uint32, np.int32, np.float16, np.uint32])), (iaa.EdgeDetect(alpha=(0.0, 0.1), name="EdgeDetect"), _not_dts([np.uint32, np.int32, np.float16, np.uint32])), (iaa.DirectedEdgeDetect(alpha=(0.0, 0.1), direction=0, name="DirectedEdgeDetect"), _not_dts([np.uint32, np.int32, np.float16, np.uint32])), (iaa.Fliplr(0.5, name="Fliplr"), default_dtypes), (iaa.Flipud(0.5, name="Flipud"), default_dtypes), (iaa.Affine(translate_px=(-5, 5), name="Affine-translate-px"), _not_dts([np.uint32, np.int32])), (iaa.Affine(translate_percent=(-0.05, 0.05), name="Affine-translate-percent"), _not_dts([np.uint32, np.int32])), (iaa.Affine(rotate=(-20, 20), name="Affine-rotate"), _not_dts([np.uint32, np.int32])), (iaa.Affine(shear=(-20, 20), name="Affine-shear"), _not_dts([np.uint32, np.int32])), (iaa.Affine(scale=(0.9, 1.1), name="Affine-scale"), _not_dts([np.uint32, np.int32])), (iaa.PiecewiseAffine(scale=(0.001, 0.005), name="PiecewiseAffine"), default_dtypes), (iaa.ElasticTransformation(alpha=(0.1, 0.2), sigma=(0.1, 0.2), name="ElasticTransformation"), _not_dts([np.float16])), (iaa.Sequential([iaa.Identity(), iaa.Identity()], name="SequentialNoop"), default_dtypes), (iaa.SomeOf(1, [iaa.Identity(), iaa.Identity()], name="SomeOfNoop"), default_dtypes), (iaa.OneOf([iaa.Identity(), iaa.Identity()], name="OneOfNoop"), default_dtypes), (iaa.Sometimes(0.5, iaa.Identity(), name="SometimesNoop"), default_dtypes), (iaa.Sequential([iaa.Add((-5, 5)), iaa.AddElementwise((-5, 5))], name="Sequential"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.SomeOf(1, [iaa.Add((-5, 5)), iaa.AddElementwise((-5, 5))], name="SomeOf"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.OneOf([iaa.Add((-5, 5)), iaa.AddElementwise((-5, 5))], name="OneOf"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.Sometimes(0.5, iaa.Add((-5, 5)), name="Sometimes"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.Identity(name="Identity"), default_dtypes), (iaa.BlendAlpha((0.0, 0.1), iaa.Identity(), name="BlendAlphaIdentity"), _not_dts([np.float64])), # float64 requires float128 support (iaa.BlendAlphaElementwise((0.0, 0.1), iaa.Identity(), name="BlendAlphaElementwiseIdentity"), _not_dts([np.float64])), # float64 requires float128 support (iaa.BlendAlphaSimplexNoise(iaa.Identity(), name="BlendAlphaSimplexNoiseIdentity"), _not_dts([np.float64])), # float64 requires float128 support (iaa.BlendAlphaFrequencyNoise(exponent=(-2, 2), foreground=iaa.Identity(), name="BlendAlphaFrequencyNoiseIdentity"), _not_dts([np.float64])), (iaa.BlendAlpha((0.0, 0.1), iaa.Add(10), name="BlendAlpha"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.BlendAlphaElementwise((0.0, 0.1), iaa.Add(10), name="BlendAlphaElementwise"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.BlendAlphaSimplexNoise(iaa.Add(10), name="BlendAlphaSimplexNoise"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.BlendAlphaFrequencyNoise(exponent=(-2, 2), foreground=iaa.Add(10), name="BlendAlphaFrequencyNoise"), _not_dts([np.uint32, np.int32, np.float64])), (iaa.Superpixels(p_replace=0.01, n_segments=64), _not_dts([np.float16, np.float32, np.float64])), (iaa.Resize({"height": 4, "width": 4}, name="Resize"), _not_dts([np.uint16, np.uint32, np.int16, np.int32, np.float32, np.float16, np.float64])), (iaa.CropAndPad(px=(-10, 10), name="CropAndPad"), _not_dts([np.uint16, np.uint32, np.int16, np.int32, np.float32, np.float16, np.float64])), (iaa.Pad(px=(0, 10), name="Pad"), _not_dts([np.uint16, np.uint32, np.int16, np.int32, np.float32, np.float16, np.float64])), (iaa.Crop(px=(0, 10), name="Crop"), _not_dts([np.uint16, np.uint32, np.int16, np.int32, np.float32, np.float16, np.float64])) ] for (aug, allowed_dtypes) in augs: for images_i in images: if images_i.dtype in allowed_dtypes: images_aug = aug.augment_images(images_i) assert images_aug.dtype == images_i.dtype
def test_unusual_channel_numbers(): reseed() images = [ (0, create_random_images((4, 16, 16))), (1, create_random_images((4, 16, 16, 1))), (2, create_random_images((4, 16, 16, 2))), (4, create_random_images((4, 16, 16, 4))), (5, create_random_images((4, 16, 16, 5))), (10, create_random_images((4, 16, 16, 10))), (20, create_random_images((4, 16, 16, 20))) ] augs = [ iaa.Add((-5, 5), name="Add"), iaa.AddElementwise((-5, 5), name="AddElementwise"), iaa.AdditiveGaussianNoise(0.01*255, name="AdditiveGaussianNoise"), iaa.Multiply((0.95, 1.05), name="Multiply"), iaa.Dropout(0.01, name="Dropout"), iaa.CoarseDropout(0.01, size_px=6, name="CoarseDropout"), iaa.Invert(0.01, per_channel=True, name="Invert"), iaa.GaussianBlur(sigma=(0.95, 1.05), name="GaussianBlur"), iaa.AverageBlur((3, 5), name="AverageBlur"), iaa.MedianBlur((3, 5), name="MedianBlur"), iaa.Sharpen((0.0, 0.1), lightness=(1.0, 1.2), name="Sharpen"), iaa.Emboss(alpha=(0.0, 0.1), strength=(0.5, 1.5), name="Emboss"), iaa.EdgeDetect(alpha=(0.0, 0.1), name="EdgeDetect"), iaa.DirectedEdgeDetect(alpha=(0.0, 0.1), direction=0, name="DirectedEdgeDetect"), iaa.Fliplr(0.5, name="Fliplr"), iaa.Flipud(0.5, name="Flipud"), iaa.Affine(translate_px=(-5, 5), name="Affine-translate-px"), iaa.Affine(translate_percent=(-0.05, 0.05), name="Affine-translate-percent"), iaa.Affine(rotate=(-20, 20), name="Affine-rotate"), iaa.Affine(shear=(-20, 20), name="Affine-shear"), iaa.Affine(scale=(0.9, 1.1), name="Affine-scale"), iaa.PiecewiseAffine(scale=(0.001, 0.005), name="PiecewiseAffine"), iaa.PerspectiveTransform(scale=(0.01, 0.10), name="PerspectiveTransform"), iaa.ElasticTransformation(alpha=(0.1, 0.2), sigma=(0.1, 0.2), name="ElasticTransformation"), iaa.Sequential([iaa.Add((-5, 5)), iaa.AddElementwise((-5, 5))]), iaa.SomeOf(1, [iaa.Add((-5, 5)), iaa.AddElementwise((-5, 5))]), iaa.OneOf([iaa.Add((-5, 5)), iaa.AddElementwise((-5, 5))]), iaa.Sometimes(0.5, iaa.Add((-5, 5)), name="Sometimes"), iaa.Identity(name="Noop"), iaa.BlendAlpha((0.0, 0.1), iaa.Add(10), name="BlendAlpha"), iaa.BlendAlphaElementwise((0.0, 0.1), iaa.Add(10), name="BlendAlphaElementwise"), iaa.BlendAlphaSimplexNoise(iaa.Add(10), name="BlendAlphaSimplexNoise"), iaa.BlendAlphaFrequencyNoise(exponent=(-2, 2), foreground=iaa.Add(10), name="BlendAlphaSimplexNoise"), iaa.Superpixels(p_replace=0.01, n_segments=64), iaa.Resize({"height": 4, "width": 4}, name="Resize"), iaa.CropAndPad(px=(-10, 10), name="CropAndPad"), iaa.Pad(px=(0, 10), name="Pad"), iaa.Crop(px=(0, 10), name="Crop") ] for aug in augs: for (nb_channels, images_c) in images: if aug.name != "Resize": images_aug = aug.augment_images(images_c) assert images_aug.shape == images_c.shape image_aug = aug.augment_image(images_c[0]) assert image_aug.shape == images_c[0].shape else: images_aug = aug.augment_images(images_c) image_aug = aug.augment_image(images_c[0]) if images_c.ndim == 3: assert images_aug.shape == (4, 4, 4) assert image_aug.shape == (4, 4) else: assert images_aug.shape == (4, 4, 4, images_c.shape[3]) assert image_aug.shape == (4, 4, images_c.shape[3])
def test_many_augmenters(self): keypoints = [] for y in sm.xrange(40//5): for x in sm.xrange(60//5): keypoints.append(ia.Keypoint(y=y*5, x=x*5)) keypoints_oi = ia.KeypointsOnImage(keypoints, shape=(40, 60, 3)) keypoints_oi_empty = ia.KeypointsOnImage([], shape=(40, 60, 3)) augs = [ iaa.Add((-5, 5), name="Add"), iaa.AddElementwise((-5, 5), name="AddElementwise"), iaa.AdditiveGaussianNoise(0.01*255, name="AdditiveGaussianNoise"), iaa.Multiply((0.95, 1.05), name="Multiply"), iaa.Dropout(0.01, name="Dropout"), iaa.CoarseDropout(0.01, size_px=6, name="CoarseDropout"), iaa.Invert(0.01, per_channel=True, name="Invert"), iaa.GaussianBlur(sigma=(0.95, 1.05), name="GaussianBlur"), iaa.AverageBlur((3, 5), name="AverageBlur"), iaa.MedianBlur((3, 5), name="MedianBlur"), iaa.Sharpen((0.0, 0.1), lightness=(1.0, 1.2), name="Sharpen"), iaa.Emboss(alpha=(0.0, 0.1), strength=(0.5, 1.5), name="Emboss"), iaa.EdgeDetect(alpha=(0.0, 0.1), name="EdgeDetect"), iaa.DirectedEdgeDetect(alpha=(0.0, 0.1), direction=0, name="DirectedEdgeDetect"), iaa.Fliplr(0.5, name="Fliplr"), iaa.Flipud(0.5, name="Flipud"), iaa.Affine(translate_px=(-5, 5), name="Affine-translate-px"), iaa.Affine(translate_percent=(-0.05, 0.05), name="Affine-translate-percent"), iaa.Affine(rotate=(-20, 20), name="Affine-rotate"), iaa.Affine(shear=(-20, 20), name="Affine-shear"), iaa.Affine(scale=(0.9, 1.1), name="Affine-scale"), iaa.PiecewiseAffine(scale=(0.001, 0.005), name="PiecewiseAffine"), iaa.ElasticTransformation(alpha=(0.1, 0.2), sigma=(0.1, 0.2), name="ElasticTransformation"), iaa.BlendAlpha((0.0, 0.1), iaa.Add(10), name="BlendAlpha"), iaa.BlendAlphaElementwise((0.0, 0.1), iaa.Add(10), name="BlendAlphaElementwise"), iaa.BlendAlphaSimplexNoise(iaa.Add(10), name="BlendAlphaSimplexNoise"), iaa.BlendAlphaFrequencyNoise(exponent=(-2, 2), foreground=iaa.Add(10), name="BlendAlphaSimplexNoise"), iaa.Superpixels(p_replace=0.01, n_segments=64), iaa.Resize(0.5, name="Resize"), iaa.CropAndPad(px=(-10, 10), name="CropAndPad"), iaa.Pad(px=(0, 10), name="Pad"), iaa.Crop(px=(0, 10), name="Crop") ] for aug in augs: dss = [] for i in sm.xrange(10): aug_det = aug.to_deterministic() kp_fully_empty_aug = aug_det.augment_keypoints([]) assert kp_fully_empty_aug == [] kp_first_empty_aug = aug_det.augment_keypoints(keypoints_oi_empty) assert len(kp_first_empty_aug.keypoints) == 0 kp_image = keypoints_oi.to_keypoint_image(size=5) with assertWarns(self, iaa.SuspiciousSingleImageShapeWarning): kp_image_aug = aug_det.augment_image(kp_image) kp_image_aug_rev = ia.KeypointsOnImage.from_keypoint_image( kp_image_aug, if_not_found_coords={"x": -9999, "y": -9999}, nb_channels=1 ) kp_aug = aug_det.augment_keypoints([keypoints_oi])[0] ds = [] assert len(kp_image_aug_rev.keypoints) == len(kp_aug.keypoints), ( "Lost keypoints for '%s' (%d vs expected %d)" % ( aug.name, len(kp_aug.keypoints), len(kp_image_aug_rev.keypoints)) ) gen = zip(kp_aug.keypoints, kp_image_aug_rev.keypoints) for kp_pred, kp_pred_img in gen: kp_pred_lost = (kp_pred.x == -9999 and kp_pred.y == -9999) kp_pred_img_lost = (kp_pred_img.x == -9999 and kp_pred_img.y == -9999) if not kp_pred_lost and not kp_pred_img_lost: d = np.sqrt((kp_pred.x - kp_pred_img.x) ** 2 + (kp_pred.y - kp_pred_img.y) ** 2) ds.append(d) dss.extend(ds) if len(ds) == 0: print("[INFO] No valid keypoints found for '%s' " "in test_keypoint_augmentation()" % (str(aug),)) assert np.average(dss) < 5.0, \ "Average distance too high (%.2f, with ds: %s)" \ % (np.average(dss), str(dss))
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.BlendAlphaSimplexNoise( 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
def __init__(self, rgb_mean, randomImg, insize): sometimes = lambda aug: iaa.Sometimes(0.7, aug) self.rand_img_dir = randomImg self.rgb_mean = rgb_mean self.inp_dim = insize # self.randomImgList = glob.glob( randomImg + '*.jpg') self.aug = iaa.Sequential([ 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": (-0.1, 0.1), "y": (-0.1, 0.1)}, # translate by -20 to +20 percent (per axis) rotate=(-25, 25), # rotate by -45 to +45 degrees shear=(-6, 6), # 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) )), iaa.OneOf([ iaa.Fliplr(0.5), iaa.GaussianBlur( sigma=iap.Uniform(0.0, 1.0) ), iaa.BlendAlphaSimplexNoise( foreground=iaa.BlendAlphaSimplexNoise( foreground=iaa.EdgeDetect(1.0), background=iaa.LinearContrast((0.1, .8)), per_channel=True ), background=iaa.BlendAlphaFrequencyNoise( exponent=(-.5, -.1), foreground=iaa.Affine( rotate=(-10, 10), translate_px={"x": (-1, 1), "y": (-1, 1)} ), # background=iaa.AddToHueAndSaturation((-4, 4)), # per_channel=True ), per_channel=True, aggregation_method="max", sigmoid=False ), iaa.BlendAlpha( factor=(0.2, 0.8), foreground=iaa.Sharpen(1.0, lightness=2), background=iaa.CoarseDropout(p=0.1, size_px=8) ), iaa.BlendAlpha( factor=(0.2, 0.8), foreground=iaa.Affine(rotate=(-5, 5)), per_channel=True ), iaa.MotionBlur(k=15, angle=[-5, 5]), iaa.BlendAlphaCheckerboard(nb_rows=2, nb_cols=(1, 4), foreground=iaa.AddToHue((-10, 10))), iaa.BlendAlphaElementwise((0, 1.0), iaa.AddToHue(10)), iaa.BilateralBlur( d=(3, 10), sigma_color=(1, 5), sigma_space=(1, 5)), iaa.AdditiveGaussianNoise(scale=0.02 * 255), iaa.AddElementwise((-5, 5), per_channel=0.5), iaa.AdditiveLaplaceNoise(scale=0.01 * 255), iaa.AdditivePoissonNoise(20), iaa.Cutout(fill_mode="gaussian", fill_per_channel=True), iaa.CoarseDropout(0.02, size_percent=0.1), iaa.SaltAndPepper(0.1, per_channel=True), iaa.JpegCompression(compression=(70, 99)), iaa.ImpulseNoise(0.02), iaa.Dropout(p=(0, 0.04)), iaa.Sharpen(alpha=0.1), ]) # oneof ])
def create_augmenters(height, width, height_augmentable, width_augmentable, only_augmenters): def lambda_func_images(images, random_state, parents, hooks): return images def lambda_func_heatmaps(heatmaps, random_state, parents, hooks): return heatmaps def lambda_func_keypoints(keypoints, random_state, parents, hooks): return keypoints def assertlambda_func_images(images, random_state, parents, hooks): return True def assertlambda_func_heatmaps(heatmaps, random_state, parents, hooks): return True def assertlambda_func_keypoints(keypoints, random_state, parents, hooks): return True augmenters_meta = [ iaa.Sequential([iaa.Noop(), iaa.Noop()], random_order=False, name="Sequential_2xNoop"), iaa.Sequential([iaa.Noop(), iaa.Noop()], random_order=True, name="Sequential_2xNoop_random_order"), iaa.SomeOf((1, 3), [iaa.Noop(), iaa.Noop(), iaa.Noop()], random_order=False, name="SomeOf_3xNoop"), iaa.SomeOf((1, 3), [iaa.Noop(), iaa.Noop(), iaa.Noop()], random_order=True, name="SomeOf_3xNoop_random_order"), iaa.OneOf([iaa.Noop(), iaa.Noop(), iaa.Noop()], name="OneOf_3xNoop"), iaa.Sometimes(0.5, iaa.Noop(), name="Sometimes_Noop"), iaa.WithChannels([1, 2], iaa.Noop(), name="WithChannels_1_and_2_Noop"), iaa.Identity(name="Identity"), iaa.Noop(name="Noop"), iaa.Lambda(func_images=lambda_func_images, func_heatmaps=lambda_func_heatmaps, func_keypoints=lambda_func_keypoints, name="Lambda"), iaa.AssertLambda(func_images=assertlambda_func_images, func_heatmaps=assertlambda_func_heatmaps, func_keypoints=assertlambda_func_keypoints, name="AssertLambda"), iaa.AssertShape((None, height_augmentable, width_augmentable, None), name="AssertShape"), iaa.ChannelShuffle(0.5, name="ChannelShuffle") ] augmenters_arithmetic = [ iaa.Add((-10, 10), name="Add"), iaa.AddElementwise((-10, 10), name="AddElementwise"), #iaa.AddElementwise((-500, 500), name="AddElementwise"), iaa.AdditiveGaussianNoise(scale=(5, 10), name="AdditiveGaussianNoise"), iaa.AdditiveLaplaceNoise(scale=(5, 10), name="AdditiveLaplaceNoise"), iaa.AdditivePoissonNoise(lam=(1, 5), name="AdditivePoissonNoise"), iaa.Multiply((0.5, 1.5), name="Multiply"), iaa.MultiplyElementwise((0.5, 1.5), name="MultiplyElementwise"), iaa.Cutout(nb_iterations=1, name="Cutout-fill_constant"), iaa.Dropout((0.01, 0.05), name="Dropout"), iaa.CoarseDropout((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarseDropout"), iaa.Dropout2d(0.1, name="Dropout2d"), iaa.TotalDropout(0.1, name="TotalDropout"), iaa.ReplaceElementwise((0.01, 0.05), (0, 255), name="ReplaceElementwise"), #iaa.ReplaceElementwise((0.95, 0.99), (0, 255), name="ReplaceElementwise"), iaa.SaltAndPepper((0.01, 0.05), name="SaltAndPepper"), iaa.ImpulseNoise((0.01, 0.05), name="ImpulseNoise"), iaa.CoarseSaltAndPepper((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarseSaltAndPepper"), iaa.Salt((0.01, 0.05), name="Salt"), iaa.CoarseSalt((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarseSalt"), iaa.Pepper((0.01, 0.05), name="Pepper"), iaa.CoarsePepper((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarsePepper"), iaa.Invert(0.1, name="Invert"), # ContrastNormalization iaa.JpegCompression((50, 99), name="JpegCompression") ] augmenters_artistic = [ iaa.Cartoon(name="Cartoon") ] augmenters_blend = [ iaa.BlendAlpha((0.01, 0.99), iaa.Identity(), name="Alpha"), iaa.BlendAlphaElementwise((0.01, 0.99), iaa.Identity(), name="AlphaElementwise"), iaa.BlendAlphaSimplexNoise(iaa.Identity(), name="SimplexNoiseAlpha"), iaa.BlendAlphaFrequencyNoise((-2.0, 2.0), iaa.Identity(), name="FrequencyNoiseAlpha"), iaa.BlendAlphaSomeColors(iaa.Identity(), name="BlendAlphaSomeColors"), iaa.BlendAlphaHorizontalLinearGradient(iaa.Identity(), name="BlendAlphaHorizontalLinearGradient"), iaa.BlendAlphaVerticalLinearGradient(iaa.Identity(), name="BlendAlphaVerticalLinearGradient"), iaa.BlendAlphaRegularGrid(nb_rows=(2, 8), nb_cols=(2, 8), foreground=iaa.Identity(), name="BlendAlphaRegularGrid"), iaa.BlendAlphaCheckerboard(nb_rows=(2, 8), nb_cols=(2, 8), foreground=iaa.Identity(), name="BlendAlphaCheckerboard"), # TODO BlendAlphaSegMapClassId # TODO BlendAlphaBoundingBoxes ] augmenters_blur = [ iaa.GaussianBlur(sigma=(1.0, 5.0), name="GaussianBlur"), iaa.AverageBlur(k=(3, 11), name="AverageBlur"), iaa.MedianBlur(k=(3, 11), name="MedianBlur"), iaa.BilateralBlur(d=(3, 11), name="BilateralBlur"), iaa.MotionBlur(k=(3, 11), name="MotionBlur"), iaa.MeanShiftBlur(spatial_radius=(5.0, 40.0), color_radius=(5.0, 40.0), name="MeanShiftBlur") ] augmenters_collections = [ iaa.RandAugment(n=2, m=(6, 12), name="RandAugment") ] augmenters_color = [ # InColorspace (deprecated) iaa.WithColorspace(to_colorspace="HSV", children=iaa.Noop(), name="WithColorspace"), iaa.WithBrightnessChannels(iaa.Identity(), name="WithBrightnessChannels"), iaa.MultiplyAndAddToBrightness(mul=(0.7, 1.3), add=(-30, 30), name="MultiplyAndAddToBrightness"), iaa.MultiplyBrightness((0.7, 1.3), name="MultiplyBrightness"), iaa.AddToBrightness((-30, 30), name="AddToBrightness"), iaa.WithHueAndSaturation(children=iaa.Noop(), name="WithHueAndSaturation"), iaa.MultiplyHueAndSaturation((0.8, 1.2), name="MultiplyHueAndSaturation"), iaa.MultiplyHue((-1.0, 1.0), name="MultiplyHue"), iaa.MultiplySaturation((0.8, 1.2), name="MultiplySaturation"), iaa.RemoveSaturation((0.01, 0.99), name="RemoveSaturation"), iaa.AddToHueAndSaturation((-10, 10), name="AddToHueAndSaturation"), iaa.AddToHue((-10, 10), name="AddToHue"), iaa.AddToSaturation((-10, 10), name="AddToSaturation"), iaa.ChangeColorspace(to_colorspace="HSV", name="ChangeColorspace"), iaa.Grayscale((0.01, 0.99), name="Grayscale"), iaa.KMeansColorQuantization((2, 16), name="KMeansColorQuantization"), iaa.UniformColorQuantization((2, 16), name="UniformColorQuantization"), iaa.UniformColorQuantizationToNBits((1, 7), name="UniformQuantizationToNBits"), iaa.Posterize((1, 7), name="Posterize") ] augmenters_contrast = [ iaa.GammaContrast(gamma=(0.5, 2.0), name="GammaContrast"), iaa.SigmoidContrast(gain=(5, 20), cutoff=(0.25, 0.75), name="SigmoidContrast"), iaa.LogContrast(gain=(0.7, 1.0), name="LogContrast"), iaa.LinearContrast((0.5, 1.5), name="LinearContrast"), iaa.AllChannelsCLAHE(clip_limit=(2, 10), tile_grid_size_px=(3, 11), name="AllChannelsCLAHE"), iaa.CLAHE(clip_limit=(2, 10), tile_grid_size_px=(3, 11), to_colorspace="HSV", name="CLAHE"), iaa.AllChannelsHistogramEqualization(name="AllChannelsHistogramEqualization"), iaa.HistogramEqualization(to_colorspace="HSV", name="HistogramEqualization"), ] augmenters_convolutional = [ iaa.Convolve(np.float32([[0, 0, 0], [0, 1, 0], [0, 0, 0]]), name="Convolve_3x3"), iaa.Sharpen(alpha=(0.01, 0.99), lightness=(0.5, 2), name="Sharpen"), iaa.Emboss(alpha=(0.01, 0.99), strength=(0, 2), name="Emboss"), iaa.EdgeDetect(alpha=(0.01, 0.99), name="EdgeDetect"), iaa.DirectedEdgeDetect(alpha=(0.01, 0.99), name="DirectedEdgeDetect") ] augmenters_edges = [ iaa.Canny(alpha=(0.01, 0.99), name="Canny") ] augmenters_flip = [ iaa.Fliplr(1.0, name="Fliplr"), iaa.Flipud(1.0, name="Flipud") ] augmenters_geometric = [ iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10), shear=(-10, 10), order=0, mode="constant", cval=(0, 255), name="Affine_order_0_constant"), iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10), shear=(-10, 10), order=1, mode="constant", cval=(0, 255), name="Affine_order_1_constant"), iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10), shear=(-10, 10), order=3, mode="constant", cval=(0, 255), name="Affine_order_3_constant"), iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10), shear=(-10, 10), order=1, mode="edge", cval=(0, 255), name="Affine_order_1_edge"), iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10), shear=(-10, 10), order=1, mode="constant", cval=(0, 255), backend="skimage", name="Affine_order_1_constant_skimage"), iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=4, nb_cols=4, order=1, mode="constant", name="PiecewiseAffine_4x4_order_1_constant"), iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=4, nb_cols=4, order=0, mode="constant", name="PiecewiseAffine_4x4_order_0_constant"), iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=4, nb_cols=4, order=1, mode="edge", name="PiecewiseAffine_4x4_order_1_edge"), iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=8, nb_cols=8, order=1, mode="constant", name="PiecewiseAffine_8x8_order_1_constant"), iaa.PerspectiveTransform(scale=(0.01, 0.05), keep_size=False, name="PerspectiveTransform"), iaa.PerspectiveTransform(scale=(0.01, 0.05), keep_size=True, name="PerspectiveTransform_keep_size"), iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=0, mode="constant", cval=0, name="ElasticTransformation_order_0_constant"), iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=1, mode="constant", cval=0, name="ElasticTransformation_order_1_constant"), iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=1, mode="nearest", cval=0, name="ElasticTransformation_order_1_nearest"), iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=1, mode="reflect", cval=0, name="ElasticTransformation_order_1_reflect"), iaa.Rot90((1, 3), keep_size=False, name="Rot90"), iaa.Rot90((1, 3), keep_size=True, name="Rot90_keep_size"), iaa.WithPolarWarping(iaa.Identity(), name="WithPolarWarping"), iaa.Jigsaw(nb_rows=(3, 8), nb_cols=(3, 8), max_steps=1, name="Jigsaw") ] augmenters_pooling = [ iaa.AveragePooling(kernel_size=(1, 16), keep_size=False, name="AveragePooling"), iaa.AveragePooling(kernel_size=(1, 16), keep_size=True, name="AveragePooling_keep_size"), iaa.MaxPooling(kernel_size=(1, 16), keep_size=False, name="MaxPooling"), iaa.MaxPooling(kernel_size=(1, 16), keep_size=True, name="MaxPooling_keep_size"), iaa.MinPooling(kernel_size=(1, 16), keep_size=False, name="MinPooling"), iaa.MinPooling(kernel_size=(1, 16), keep_size=True, name="MinPooling_keep_size"), iaa.MedianPooling(kernel_size=(1, 16), keep_size=False, name="MedianPooling"), iaa.MedianPooling(kernel_size=(1, 16), keep_size=True, name="MedianPooling_keep_size") ] augmenters_imgcorruptlike = [ iaa.imgcorruptlike.GaussianNoise(severity=(1, 5), name="imgcorruptlike.GaussianNoise"), iaa.imgcorruptlike.ShotNoise(severity=(1, 5), name="imgcorruptlike.ShotNoise"), iaa.imgcorruptlike.ImpulseNoise(severity=(1, 5), name="imgcorruptlike.ImpulseNoise"), iaa.imgcorruptlike.SpeckleNoise(severity=(1, 5), name="imgcorruptlike.SpeckleNoise"), iaa.imgcorruptlike.GaussianBlur(severity=(1, 5), name="imgcorruptlike.GaussianBlur"), iaa.imgcorruptlike.GlassBlur(severity=(1, 5), name="imgcorruptlike.GlassBlur"), iaa.imgcorruptlike.DefocusBlur(severity=(1, 5), name="imgcorruptlike.DefocusBlur"), iaa.imgcorruptlike.MotionBlur(severity=(1, 5), name="imgcorruptlike.MotionBlur"), iaa.imgcorruptlike.ZoomBlur(severity=(1, 5), name="imgcorruptlike.ZoomBlur"), iaa.imgcorruptlike.Fog(severity=(1, 5), name="imgcorruptlike.Fog"), iaa.imgcorruptlike.Frost(severity=(1, 5), name="imgcorruptlike.Frost"), iaa.imgcorruptlike.Snow(severity=(1, 5), name="imgcorruptlike.Snow"), iaa.imgcorruptlike.Spatter(severity=(1, 5), name="imgcorruptlike.Spatter"), iaa.imgcorruptlike.Contrast(severity=(1, 5), name="imgcorruptlike.Contrast"), iaa.imgcorruptlike.Brightness(severity=(1, 5), name="imgcorruptlike.Brightness"), iaa.imgcorruptlike.Saturate(severity=(1, 5), name="imgcorruptlike.Saturate"), iaa.imgcorruptlike.JpegCompression(severity=(1, 5), name="imgcorruptlike.JpegCompression"), iaa.imgcorruptlike.Pixelate(severity=(1, 5), name="imgcorruptlike.Pixelate"), iaa.imgcorruptlike.ElasticTransform(severity=(1, 5), name="imgcorruptlike.ElasticTransform") ] augmenters_pillike = [ iaa.pillike.Solarize(p=1.0, threshold=(32, 128), name="pillike.Solarize"), iaa.pillike.Posterize((1, 7), name="pillike.Posterize"), iaa.pillike.Equalize(name="pillike.Equalize"), iaa.pillike.Autocontrast(name="pillike.Autocontrast"), iaa.pillike.EnhanceColor((0.0, 3.0), name="pillike.EnhanceColor"), iaa.pillike.EnhanceContrast((0.0, 3.0), name="pillike.EnhanceContrast"), iaa.pillike.EnhanceBrightness((0.0, 3.0), name="pillike.EnhanceBrightness"), iaa.pillike.EnhanceSharpness((0.0, 3.0), name="pillike.EnhanceSharpness"), iaa.pillike.FilterBlur(name="pillike.FilterBlur"), iaa.pillike.FilterSmooth(name="pillike.FilterSmooth"), iaa.pillike.FilterSmoothMore(name="pillike.FilterSmoothMore"), iaa.pillike.FilterEdgeEnhance(name="pillike.FilterEdgeEnhance"), iaa.pillike.FilterEdgeEnhanceMore(name="pillike.FilterEdgeEnhanceMore"), iaa.pillike.FilterFindEdges(name="pillike.FilterFindEdges"), iaa.pillike.FilterContour(name="pillike.FilterContour"), iaa.pillike.FilterEmboss(name="pillike.FilterEmboss"), iaa.pillike.FilterSharpen(name="pillike.FilterSharpen"), iaa.pillike.FilterDetail(name="pillike.FilterDetail"), iaa.pillike.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10), shear=(-10, 10), fillcolor=(0, 255), name="pillike.Affine"), ] augmenters_segmentation = [ iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=64, interpolation="cubic", name="Superpixels_max_size_64_cubic"), iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=64, interpolation="linear", name="Superpixels_max_size_64_linear"), iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=128, interpolation="linear", name="Superpixels_max_size_128_linear"), iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=224, interpolation="linear", name="Superpixels_max_size_224_linear"), iaa.UniformVoronoi(n_points=(250, 1000), name="UniformVoronoi"), iaa.RegularGridVoronoi(n_rows=(16, 31), n_cols=(16, 31), name="RegularGridVoronoi"), iaa.RelativeRegularGridVoronoi(n_rows_frac=(0.07, 0.14), n_cols_frac=(0.07, 0.14), name="RelativeRegularGridVoronoi"), ] augmenters_size = [ iaa.Resize((0.8, 1.2), interpolation="nearest", name="Resize_nearest"), iaa.Resize((0.8, 1.2), interpolation="linear", name="Resize_linear"), iaa.Resize((0.8, 1.2), interpolation="cubic", name="Resize_cubic"), iaa.CropAndPad(percent=(-0.2, 0.2), pad_mode="constant", pad_cval=(0, 255), keep_size=False, name="CropAndPad"), iaa.CropAndPad(percent=(-0.2, 0.2), pad_mode="edge", pad_cval=(0, 255), keep_size=False, name="CropAndPad_edge"), iaa.CropAndPad(percent=(-0.2, 0.2), pad_mode="constant", pad_cval=(0, 255), name="CropAndPad_keep_size"), iaa.Pad(percent=(0.05, 0.2), pad_mode="constant", pad_cval=(0, 255), keep_size=False, name="Pad"), iaa.Pad(percent=(0.05, 0.2), pad_mode="edge", pad_cval=(0, 255), keep_size=False, name="Pad_edge"), iaa.Pad(percent=(0.05, 0.2), pad_mode="constant", pad_cval=(0, 255), name="Pad_keep_size"), iaa.Crop(percent=(0.05, 0.2), keep_size=False, name="Crop"), iaa.Crop(percent=(0.05, 0.2), name="Crop_keep_size"), iaa.PadToFixedSize(width=width+10, height=height+10, pad_mode="constant", pad_cval=(0, 255), name="PadToFixedSize"), iaa.CropToFixedSize(width=width-10, height=height-10, name="CropToFixedSize"), iaa.KeepSizeByResize(iaa.CropToFixedSize(height=height-10, width=width-10), interpolation="nearest", name="KeepSizeByResize_CropToFixedSize_nearest"), iaa.KeepSizeByResize(iaa.CropToFixedSize(height=height-10, width=width-10), interpolation="linear", name="KeepSizeByResize_CropToFixedSize_linear"), iaa.KeepSizeByResize(iaa.CropToFixedSize(height=height-10, width=width-10), interpolation="cubic", name="KeepSizeByResize_CropToFixedSize_cubic"), ] augmenters_weather = [ iaa.FastSnowyLandscape(lightness_threshold=(100, 255), lightness_multiplier=(1.0, 4.0), name="FastSnowyLandscape"), iaa.Clouds(name="Clouds"), iaa.Fog(name="Fog"), iaa.CloudLayer(intensity_mean=(196, 255), intensity_freq_exponent=(-2.5, -2.0), intensity_coarse_scale=10, alpha_min=0, alpha_multiplier=(0.25, 0.75), alpha_size_px_max=(2, 8), alpha_freq_exponent=(-2.5, -2.0), sparsity=(0.8, 1.0), density_multiplier=(0.5, 1.0), name="CloudLayer"), iaa.Snowflakes(name="Snowflakes"), iaa.SnowflakesLayer(density=(0.005, 0.075), density_uniformity=(0.3, 0.9), flake_size=(0.2, 0.7), flake_size_uniformity=(0.4, 0.8), angle=(-30, 30), speed=(0.007, 0.03), blur_sigma_fraction=(0.0001, 0.001), name="SnowflakesLayer"), iaa.Rain(name="Rain"), iaa.RainLayer(density=(0.03, 0.14), density_uniformity=(0.8, 1.0), drop_size=(0.01, 0.02), drop_size_uniformity=(0.2, 0.5), angle=(-15, 15), speed=(0.04, 0.20), blur_sigma_fraction=(0.001, 0.001), name="RainLayer") ] augmenters = ( augmenters_meta + augmenters_arithmetic + augmenters_artistic + augmenters_blend + augmenters_blur + augmenters_collections + augmenters_color + augmenters_contrast + augmenters_convolutional + augmenters_edges + augmenters_flip + augmenters_geometric + augmenters_pooling + augmenters_imgcorruptlike + augmenters_pillike + augmenters_segmentation + augmenters_size + augmenters_weather ) if only_augmenters is not None: augmenters_reduced = [] for augmenter in augmenters: if any([re.search(pattern, augmenter.name) for pattern in only_augmenters]): augmenters_reduced.append(augmenter) augmenters = augmenters_reduced return augmenters
iaa.GammaContrast((0.5, 2.0), per_channel=True), iaa.Affine(rotate=(-15, 15)), iaa.Affine(translate_percent={"x": -0.20}, mode=ia.ALL, cval=(0, 255)), iaa.Affine(translate_percent={"y": -0.20}, mode=ia.ALL, cval=(0, 255)), iaa.Affine(translate_percent={"x": +0.20}, mode=ia.ALL, cval=(0, 255)), iaa.Affine(translate_percent={"y": +0.20}, mode=ia.ALL, cval=(0, 255)), iaa.BlendAlpha( (0.0, 1.0), iaa.Affine(rotate=(-20, 20)), per_channel=0.5), iaa.BlendAlpha([0.25, 0.75], iaa.MedianBlur(13)), iaa.BlendAlphaElementwise( (0.0, 1.0), foreground=iaa.Add(100), background=iaa.Multiply(0.2)), iaa.BlendAlphaSimplexNoise(iaa.EdgeDetect(1.0)), iaa.BlendAlphaSimplexNoise( iaa.EdgeDetect(1.0), upscale_method="nearest"), iaa.BlendAlphaSimplexNoise( iaa.EdgeDetect(1.0), upscale_method="linear"), iaa.BlendAlphaSomeColors(iaa.TotalDropout(1.0)), iaa.BlendAlphaSomeColors( iaa.AveragePooling(7), alpha=[0.0, 1.0], smoothness=0.0), iaa.FastSnowyLandscape( lightness_threshold=140, lightness_multiplier=2.5), iaa.Clouds(), iaa.Fog(), iaa.Rain(speed=(0.1, 0.3)),
iaa.InvertMaskGen(0.5, iaa.VerticalLinearGradientMaskGen()), iaa.Clouds() ) aug26 = iaa.BlendAlphaElementwise( (0.0, 0.5), iaa.Affine(rotate=(-0, 0)), per_channel=0.5) aug27 = iaa.BlendAlphaElementwise( (0.0, 0.2), foreground=iaa.Add(20), background=iaa.Multiply(0.4)) aug28 = iaa.BlendAlphaElementwise([0.25, 0.75], iaa.MedianBlur(13)) aug29 = iaa.BlendAlphaSimplexNoise(iaa.EdgeDetect(0.6)) aug30 = iaa.BlendAlphaSimplexNoise( iaa.EdgeDetect(0.2), upscale_method="nearest") aug31 = iaa.Cutout(fill_mode="constant", cval=(0, 255), fill_per_channel=0.5) # aug32 = iaa.BlendAlphaHorizontalLinearGradient( # iaa.TotalDropout(0.3), # min_value=0.1, max_value=0.3) # aug33 = iaa.BlendAlphaHorizontalLinearGradient( # iaa.AveragePooling(3), # start_at=(0.0, 0.2), end_at=(0.0, 0.2)) # aug34 = iaa.BlendAlphaVerticalLinearGradient( # iaa.TotalDropout(0.6),
def chapter_alpha_masks_simplex(): # ----------------------------------------- # example 1 (basic) # ----------------------------------------- import imgaug as ia from imgaug import augmenters as iaa ia.seed(1) # Example batch of images. # The array has shape (8, 128, 128, 3) and dtype uint8. images = np.array([ia.quokka(size=(128, 128)) for _ in range(8)], dtype=np.uint8) seq = iaa.BlendAlphaSimplexNoise( foreground=iaa.Multiply(iap.Choice([0.5, 1.5]), per_channel=True)) images_aug = seq(images=images) # ------------ save("alpha", "alpha_simplex_example_basic.jpg", grid(images_aug, cols=4, rows=2)) # ----------------------------------------- # example 1 (per_channel) # ----------------------------------------- import imgaug as ia from imgaug import augmenters as iaa ia.seed(1) # Example batch of images. # The array has shape (8, 128, 128, 3) and dtype uint8. images = np.array([ia.quokka(size=(128, 128)) for _ in range(8)], dtype=np.uint8) seq = iaa.BlendAlphaSimplexNoise(foreground=iaa.EdgeDetect(1.0), per_channel=True) images_aug = seq(images=images) # ------------ save("alpha", "alpha_simplex_example_per_channel.jpg", grid(images_aug, cols=4, rows=2)) # ----------------------------------------- # noise masks # ----------------------------------------- import imgaug as ia from imgaug import augmenters as iaa seed = 1 ia.seed(seed) seq = iaa.BlendAlphaSimplexNoise( foreground=iaa.Multiply(iap.Choice([0.5, 1.5]), per_channel=True)) masks = [ seq.factor.draw_samples((64, 64), random_state=ia.new_random_state(seed + 1 + i)) for i in range(16) ] masks = np.hstack(masks) masks = np.tile(masks[:, :, np.newaxis], (1, 1, 1, 3)) masks = (masks * 255).astype(np.uint8) # ------------ save("alpha", "alpha_simplex_noise_masks.jpg", grid(masks, cols=16, rows=1)) # ----------------------------------------- # noise masks, upscale=nearest # ----------------------------------------- import imgaug as ia from imgaug import augmenters as iaa seed = 1 ia.seed(seed) seq = iaa.SimplexNoiseAlpha(first=iaa.Multiply(iap.Choice([0.5, 1.5]), per_channel=True), upscale_method="nearest") masks = [ seq.factor.draw_samples((64, 64), random_state=ia.new_random_state(seed + 1 + i)) for i in range(16) ] masks = np.hstack(masks) masks = np.tile(masks[:, :, np.newaxis], (1, 1, 1, 3)) masks = (masks * 255).astype(np.uint8) # ------------ save("alpha", "alpha_simplex_noise_masks_nearest.jpg", grid(masks, cols=16, rows=1)) # ----------------------------------------- # noise masks linear # ----------------------------------------- import imgaug as ia from imgaug import augmenters as iaa seed = 1 ia.seed(seed) seq = iaa.BlendAlphaSimplexNoise(foreground=iaa.Multiply(iap.Choice( [0.5, 1.5]), per_channel=True), upscale_method="linear") masks = [ seq.factor.draw_samples((64, 64), random_state=ia.new_random_state(seed + 1 + i)) for i in range(16) ] masks = np.hstack(masks) masks = np.tile(masks[:, :, np.newaxis], (1, 1, 1, 3)) masks = (masks * 255).astype(np.uint8) # ------------ save("alpha", "alpha_simplex_noise_masks_linear.jpg", grid(masks, cols=16, rows=1))
def __init__(self, args): if args.inference: logger.info( f"`args.inference` is set, so switching off all augmentations") self.seq = self.shift_seq = None return sometimes = lambda aug: iaa.Sometimes(0.5, aug) logger.info(f"Pixelwise augmentation: {args.use_pixelwise_augs}") logger.info(f"Affine scale augmentation: {args.use_affine_scale}") logger.info(f"Affine shift augmentation: {args.use_affine_shift}") total_augs = [] if args.use_pixelwise_augs: pixelwise_augs = [ iaa.SomeOf( (0, 5), [ # sometimes(iaa.Superpixels(p_replace=(0, 0.25), n_segments=(150, 200))), iaa.OneOf([ iaa.GaussianBlur( (0, 1.0) ), # blur images with a sigma between 0 and 3.0 iaa.AverageBlur(k=(1, 3)), # blur image using local means with kernel sizes between 2 and 7 iaa.MedianBlur(k=(1, 3)), # blur image using local medians with kernel sizes between 2 and 7 ]), iaa.Sharpen(alpha=(0, 1.0), lightness=(1.0, 1.5)), # sharpen images iaa.Emboss(alpha=(0, 1.0), strength=(0, 0.5)), # emboss images # search either for all edges or for directed edges, # blend the result with the original image using a blobby mask iaa.BlendAlphaSimplexNoise( iaa.EdgeDetect(alpha=(0.0, 0.15)), ), iaa.AdditiveGaussianNoise( loc=0, scale=(0.0, 0.05 * 255), per_channel=False), # add gaussian noise to images iaa.Add((-10, 10), per_channel=0.5), # change brightness of images (by -10 to 10 of original value) iaa.AddToSaturation( (-20, 20)), # change hue and saturation iaa.JpegCompression((70, 99)), iaa.Multiply((0.5, 1.5), per_channel=False), iaa.OneOf([ iaa.LinearContrast( (0.75, 1.25), per_channel=False), iaa.SigmoidContrast(cutoff=0.5, gain=(3.0, 11.0)) ]), sometimes( iaa.ElasticTransformation(alpha=(0.5, 3.5), sigma=0.15)), # move pixels locally around (with random strengths) ], random_order=True) ] total_augs.extend(pixelwise_augs) if args.use_affine_scale: affine_augs_scale = [ 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 order=[1], # use bilinear interpolation (fast) mode=["reflect"])) ] total_augs.extend(affine_augs_scale) if args.use_affine_shift: affine_augs_shift = [ sometimes( iaa.Affine( translate_percent={ "x": (-0.05, 0.05), "y": (-0.05, 0.05) }, order=[1], # use bilinear interpolation (fast) mode=["reflect"])) ] else: affine_augs_shift = [] self.shift_seq = iaa.Sequential(affine_augs_shift) self.seq = iaa.Sequential(total_augs, random_order=True)
def get_aug(self): #sometimes_bg = lambda aug: iaa.Sometimes(0.3, aug) sometimes_contrast = lambda aug: iaa.Sometimes(0.3, aug) sometimes_noise = lambda aug: iaa.Sometimes(0.6, aug) sometimes_blur = lambda aug: iaa.Sometimes(0.6, aug) sometimes_degrade_quality = lambda aug: iaa.Sometimes(0.9, aug) sometimes_blend = lambda aug: iaa.Sometimes(0.2, aug) seq = iaa.Sequential( [ # crop some of the images by 0-30% of their height/width # Execute 0 to 4 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, 4), # [ # change the background color of some of the images chosing any one technique # sometimes_bg(iaa.OneOf([ # iaa.AddToHueAndSaturation((-60, 60)), # iaa.Multiply((0.6, 1), per_channel=True), # ])), #change the contrast of the input images chosing any one technique sometimes_contrast(iaa.OneOf([ iaa.LinearContrast((0.5,1.5)), iaa.SigmoidContrast(gain=(3, 5), cutoff=(0.4, 0.6)), iaa.CLAHE(tile_grid_size_px=(3, 21)), iaa.GammaContrast((0.5,1.0)) ])), #add noise to the input images chosing any one technique sometimes_noise(iaa.OneOf([ iaa.AdditiveGaussianNoise(scale=(3,8)), iaa.CoarseDropout((0.001,0.01), size_percent=0.5), iaa.AdditiveLaplaceNoise(scale=(3,10)), iaa.CoarsePepper((0.001,0.01), size_percent=(0.5)), iaa.AdditivePoissonNoise(lam=(3.0,10.0)), iaa.Pepper((0.001,0.01)), iaa.Snowflakes(), iaa.Dropout(0.01,0.01), ])), #add blurring techniques to the input image sometimes_blur(iaa.OneOf([ iaa.AverageBlur(k=(3)), iaa.GaussianBlur(sigma=(1.0)), ])), # add techniques to degrade the iamge quality sometimes_degrade_quality(iaa.OneOf([ iaa.Emboss(alpha=(0, 1.0), strength=(0, 2.0)), iaa.Sharpen(alpha=(0.5), lightness=(0.75,1.5)), iaa.BlendAlphaSimplexNoise( foreground=iaa.Multiply(iap.Choice([1.5]), per_channel=False) ) ])), # blend some patterns in the background sometimes_blend(iaa.OneOf([ iaa.BlendAlpha( factor=(0.6,0.8), foreground=iaa.Sharpen(1.0, lightness=1), background=iaa.CoarseDropout(p=0.1, size_px=np.random.randint(30))), iaa.BlendAlphaFrequencyNoise(exponent=(-4), foreground=iaa.Multiply(iap.Choice([0.5]), per_channel=False) ), iaa.BlendAlphaSimplexNoise( foreground=iaa.Multiply(iap.Choice([0.5]), per_channel=True) ) ])), ]) return seq
## Artistic elif augmentation == 'cartoon': transform = iaa.Cartoon(blur_ksize=3, segmentation_size=1.0, saturation=2.0, edge_prevalence=1.0) transformed_image = transform(image=image) ## Blend elif augmentation == 'blend_alpha': transform = iaa.BlendAlpha(0.5, iaa.Grayscale(1.0)) transformed_image = transform(image=image) elif augmentation == 'blend_alpha_simplex_noise': transform = iaa.BlendAlphaSimplexNoise(iaa.EdgeDetect(1.0)) transformed_image = transform(image=image) elif augmentation == 'blend_alpha_some_colors': transform = iaa.BlendAlphaSomeColors(iaa.Grayscale(1.0)) transformed_image = transform(image=image) elif augmentation == 'blend_alpha_regular_grid': transform = iaa.BlendAlphaRegularGrid(nb_rows=(4, 6), nb_cols=(1, 4), foreground=iaa.Multiply(0.0)) transformed_image = transform(image=image) elif augmentation == 'blend_alpha_mask': transform = iaa.BlendAlphaMask(iaa.InvertMaskGen(0.5, iaa.VerticalLinearGradientMaskGen()), iaa.Clouds())