def transform(self, image, mask): H, W = image.shape[0], image.shape[1] new_h, new_w = self.input_shape[0], self.input_shape[1] if H > self.input_shape[0] and W > self.input_shape[1]: y_min, x_min = random.randint(0, H - self.input_shape[0]), random.randint( 0, W - self.input_shape[1]) compose = Compose([ transforms.Crop(x_min=x_min, y_min=y_min, x_max=x_min + self.input_shape[1], y_max=y_min + self.input_shape[0]), ToTensorV2() ]) new_image = compose(image=image)['image'] new_mask = compose(image=mask)['image'] else: resize_ratio = int( math.ceil(max([new_h / float(H), new_w / float(W)]))) h, w = H * resize_ratio, W * resize_ratio y_min, x_min = random.randint(0, h - self.input_shape[0]), random.randint( 0, w - self.input_shape[1]) compose = Compose([ transforms.Resize(h, w), transforms.Crop(x_min=x_min, y_min=y_min, x_max=x_min + self.input_shape[1], y_max=y_min + self.input_shape[0]), ToTensorV2() ]) new_image = compose(image=image)['image'] new_mask = compose(image=mask)['image'] assert new_image.shape[0] == 3 and new_mask.shape[0] == 2 return new_image, new_mask
def standard_tencrop_batch(im, crop_prop=0.9): """ Returns an ordered ten crop batch of images from an original image (corners, center + mirrors). Parameters ---------- im : numpy array, type np.uint8 crop_prop: float, [0, 1] Size of the crop with respect to the whole image Returns ------- List of 10 numpy arrays """ batch = [] min_side = np.amin(im.shape[:2]) im = resize_im(im, height=min_side, width=min_side) # resize to shorter border h, w = min_side, min_side # height, width (square) crop_size = int(crop_prop * min_side) # Crops c1 = transforms.Crop(x_min=0, y_min=0, x_max=crop_size, y_max=crop_size)(image=im)['image'] # top-left c2 = transforms.Crop(x_min=0, y_min=h - crop_size, x_max=crop_size, y_max=h)(image=im)['image'] # bottom-left c3 = transforms.Crop(x_min=w - crop_size, y_min=0, x_max=w, y_max=crop_size)(image=im)['image'] # top-right c4 = transforms.Crop(x_min=w - crop_size, y_min=h - crop_size, x_max=w, y_max=h)(image=im)['image'] # bottom-right c5 = transforms.Crop( x_min=np.round((w - crop_size) / 2).astype(int), y_min=np.round((h - crop_size) / 2).astype(int), x_max=np.round((w + crop_size) / 2).astype(int), y_max=np.round( (h + crop_size) / 2).astype(int))(image=im)['image'] # center # Save crop and its mirror lr_aug = albumentations.HorizontalFlip(p=1) for image in [c1, c2, c3, c4, c5]: batch.append(image) batch.append(lr_aug(image=image)['image']) return batch
def augment(im, params=None): """ Perform data augmentation on some image using the albumentations package. Parameters ---------- im : Numpy array params : dict or None Contains the data augmentation parameters Mandatory keys: - h_flip ([0,1] float): probability of performing an horizontal left-right mirroring. - v_flip ([0,1] float): probability of performing an vertical up-down mirroring. - rot ([0,1] float): probability of performing a rotation to the image. - rot_lim (int): max degrees of rotation. - stretch ([0,1] float): probability of randomly stretching an image. - crop ([0,1] float): randomly take an image crop. - zoom ([0,1] float): random zoom applied to crop_size. --> Therefore the effective crop size at each iteration will be a random number between 1 and crop*(1-zoom). For example: * crop=1, zoom=0: no crop of the image * crop=1, zoom=0.1: random crop of random size between 100% image and 90% of the image * crop=0.9, zoom=0.1: random crop of random size between 90% image and 80% of the image * crop=0.9, zoom=0: random crop of always 90% of the image Image size refers to the size of the shortest side. - blur ([0,1] float): probability of randomly blurring an image. - pixel_noise ([0,1] float): probability of randomly adding pixel noise to an image. - pixel_sat ([0,1] float): probability of randomly using HueSaturationValue in the image. - cutout ([0,1] float): probability of using cutout in the image. Returns ------- Numpy array """ ## 1) Crop the image effective_zoom = np.random.rand() * params['zoom'] crop = params['crop'] - effective_zoom ly, lx, channels = im.shape crop_size = int(crop * min([ly, lx])) rand_x = np.random.randint(low=0, high=lx - crop_size + 1) rand_y = np.random.randint(low=0, high=ly - crop_size + 1) crop = transforms.Crop(x_min=rand_x, y_min=rand_y, x_max=rand_x + crop_size, y_max=rand_y + crop_size) im = crop(image=im)['image'] ## 2) Now add the transformations for augmenting the image pixels transform_list = [] # Add random stretching if params['stretch']: transform_list.append( imgaug_transforms.IAAPerspective(scale=0.1, p=params['stretch'])) # Add random rotation if params['rot']: transform_list.append( transforms.Rotate(limit=params['rot_lim'], p=params['rot'])) # Add horizontal flip if params['h_flip']: transform_list.append(transforms.HorizontalFlip(p=params['h_flip'])) # Add vertical flip if params['v_flip']: transform_list.append(transforms.VerticalFlip(p=params['v_flip'])) # Add some blur to the image if params['blur']: transform_list.append( albumentations.OneOf([ transforms.MotionBlur(blur_limit=7, p=1.), transforms.MedianBlur(blur_limit=7, p=1.), transforms.Blur(blur_limit=7, p=1.), ], p=params['blur'])) # Add pixel noise if params['pixel_noise']: transform_list.append( albumentations.OneOf( [ transforms.CLAHE(clip_limit=2, p=1.), imgaug_transforms.IAASharpen(p=1.), imgaug_transforms.IAAEmboss(p=1.), transforms.RandomBrightnessContrast(contrast_limit=0, p=1.), transforms.RandomBrightnessContrast(brightness_limit=0, p=1.), transforms.RGBShift(p=1.), transforms.RandomGamma(p=1.) #, # transforms.JpegCompression(), # transforms.ChannelShuffle(), # transforms.ToGray() ], p=params['pixel_noise'])) # Add pixel saturation if params['pixel_sat']: transform_list.append( transforms.HueSaturationValue(p=params['pixel_sat'])) # Remove randomly remove some regions from the image if params['cutout']: ly, lx, channels = im.shape scale_low, scale_high = 0.05, 0.25 # min and max size of the squares wrt the full image scale = np.random.uniform(scale_low, scale_high) transform_list.append( transforms.Cutout(num_holes=8, max_h_size=int(scale * ly), max_w_size=int(scale * lx), p=params['cutout'])) # Compose all image transformations and augment the image augmentation_fn = albumentations.Compose(transform_list) im = augmentation_fn(image=im)['image'] return im
def augment(im, params=None): """ Perform data augmentation on some image using the albumentations package. Parameters ---------- im : Numpy array params : dict or None Contains the data augmentation parameters Mandatory keys: - h_flip ([0,1] float): probability of performing an horizontal left-right mirroring. - v_flip ([0,1] float): probability of performing an vertical up-down mirroring. - rot ([0,1] float): probability of performing a rotation to the image. - rot_lim (int): max degrees of rotation. - stretch ([0,1] float): probability of randomly stretching an image. - expand ([True, False] bool): whether to pad the image to a square shape with background color canvas. - crop ([0,1] float): randomly take an image crop. - invert_col ([0, 1] float): randomly invert the colors of the image. p=1 -> invert colors (VPR) - zoom ([0,1] float): random zoom applied to crop_size. --> Therefore the effective crop size at each iteration will be a random number between 1 and crop*(1-zoom). For example: * crop=1, zoom=0: no crop of the image * crop=1, zoom=0.1: random crop of random size between 100% image and 90% of the image * crop=0.9, zoom=0.1: random crop of random size between 90% image and 80% of the image * crop=0.9, zoom=0: random crop of always 90% of the image Image size refers to the size of the shortest side. - blur ([0,1] float): probability of randomly blurring an image. - pixel_noise ([0,1] float): probability of randomly adding pixel noise to an image. - pixel_sat ([0,1] float): probability of randomly using HueSaturationValue in the image. - cutout ([0,1] float): probability of using cutout in the image. Returns ------- Numpy array """ ## 1) Expand the image by padding it with bg-color canvas if params["expand"]: desired_size = max(im.shape) # check bg if np.argmax(im.shape) > 0: bgcol = tuple(np.repeat(int(np.mean(im[[0, -1], :, :])), 3)) else: bgcol = tuple(np.repeat(int(np.mean(im[:, [0, -1], :])), 3)) im = Image.fromarray(im) old_size = im.size # old_size[0] is in (width, height) format ratio = float(desired_size) / max(old_size) new_size = tuple([int(x * ratio) for x in old_size]) im = im.resize(new_size, Image.ANTIALIAS) # create a new image and paste the resized on it new_im = Image.new("RGB", (desired_size, desired_size), color=bgcol) new_im.paste(im, ((desired_size - new_size[0]) // 2, (desired_size - new_size[1]) // 2)) im = np.array(new_im) ## 2) Crop the image if params["crop"] and params["crop"] != 1: effective_zoom = np.random.rand() * params['zoom'] crop = params['crop'] - effective_zoom ly, lx, channels = im.shape crop_size = int(crop * min([ly, lx])) rand_x = np.random.randint(low=0, high=lx - crop_size + 1) rand_y = np.random.randint(low=0, high=ly - crop_size + 1) crop = transforms.Crop(x_min=rand_x, y_min=rand_y, x_max=rand_x + crop_size, y_max=rand_y + crop_size) im = crop(image=im)['image'] if params["enhance"]: im = Image.fromarray(im) enhancer = ImageEnhance.Contrast(im) im = np.array(enhancer.enhance(params["enhance"])) ## 3) Now add the transformations for augmenting the image pixels transform_list = [] if params['invert_col']: transform_list.append(transforms.InvertImg(p=params['invert_col'])) # Add random stretching if params['stretch']: transform_list.append( imgaug_transforms.IAAPerspective(scale=0.1, p=params['stretch'])) # Add random rotation if params['rot']: transform_list.append( transforms.Rotate(limit=params['rot_lim'], p=params['rot'])) # Add horizontal flip if params['h_flip']: transform_list.append(transforms.HorizontalFlip(p=params['h_flip'])) # Add vertical flip if params['v_flip']: transform_list.append(transforms.VerticalFlip(p=params['v_flip'])) # Add some blur to the image if params['blur']: transform_list.append( albumentations.OneOf([ transforms.MotionBlur(blur_limit=7, p=1.), transforms.MedianBlur(blur_limit=7, p=1.), transforms.Blur(blur_limit=7, p=1.), ], p=params['blur'])) # Add pixel noise if params['pixel_noise']: transform_list.append( albumentations.OneOf( [ transforms.CLAHE(clip_limit=2, p=1.), imgaug_transforms.IAASharpen(p=1.), imgaug_transforms.IAAEmboss(p=1.), transforms.RandomBrightnessContrast(contrast_limit=0, p=1.), transforms.RandomBrightnessContrast(brightness_limit=0, p=1.), transforms.RGBShift(p=1.), transforms.RandomGamma(p=1.) #, # transforms.JpegCompression(), # transforms.ChannelShuffle(), # transforms.ToGray() ], p=params['pixel_noise'])) # Add pixel saturation if params['pixel_sat']: transform_list.append( transforms.HueSaturationValue(p=params['pixel_sat'])) # Remove randomly remove some regions from the image if params['cutout']: ly, lx, channels = im.shape scale_low, scale_high = 0.05, 0.25 # min and max size of the squares wrt the full image scale = np.random.uniform(scale_low, scale_high) transform_list.append( transforms.Cutout(num_holes=8, max_h_size=int(scale * ly), max_w_size=int(scale * lx), p=params['cutout'])) # Compose all image transformations and augment the image augmentation_fn = albumentations.Compose(transform_list) im = augmentation_fn(image=im)['image'] return im