|
|
import random |
|
|
|
|
|
import numpy as np |
|
|
from skimage.filters import gaussian |
|
|
import torch |
|
|
from PIL import Image, ImageFilter |
|
|
|
|
|
|
|
|
class RandomVerticalFlip(object): |
|
|
def __call__(self, img): |
|
|
if random.random() < 0.5: |
|
|
return img.transpose(Image.FLIP_TOP_BOTTOM) |
|
|
return img |
|
|
|
|
|
|
|
|
class DeNormalize(object): |
|
|
def __init__(self, mean, std): |
|
|
self.mean = mean |
|
|
self.std = std |
|
|
|
|
|
def __call__(self, tensor): |
|
|
for t, m, s in zip(tensor, self.mean, self.std): |
|
|
t.mul_(s).add_(m) |
|
|
return tensor |
|
|
|
|
|
|
|
|
class MaskToTensor(object): |
|
|
def __call__(self, img): |
|
|
return torch.from_numpy(np.array(img, dtype=np.int32)).long() |
|
|
|
|
|
|
|
|
class FreeScale(object): |
|
|
def __init__(self, size, interpolation=Image.BILINEAR): |
|
|
self.size = tuple(reversed(size)) |
|
|
self.interpolation = interpolation |
|
|
|
|
|
def __call__(self, img): |
|
|
return img.resize(self.size, self.interpolation) |
|
|
|
|
|
|
|
|
class FlipChannels(object): |
|
|
def __call__(self, img): |
|
|
img = np.array(img)[:, :, ::-1] |
|
|
return Image.fromarray(img.astype(np.uint8)) |
|
|
|
|
|
|
|
|
class RandomGaussianBlur(object): |
|
|
def __call__(self, img): |
|
|
sigma = 0.15 + random.random() * 1.15 |
|
|
blurred_img = gaussian(np.array(img), sigma=sigma, multichannel=True) |
|
|
blurred_img *= 255 |
|
|
return Image.fromarray(blurred_img.astype(np.uint8)) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class Lighting(object): |
|
|
"""Lighting noise(AlexNet - style PCA - based noise)""" |
|
|
|
|
|
def __init__(self, alphastd, |
|
|
eigval=(0.2175, 0.0188, 0.0045), |
|
|
eigvec=((-0.5675, 0.7192, 0.4009), |
|
|
(-0.5808, -0.0045, -0.8140), |
|
|
(-0.5836, -0.6948, 0.4203))): |
|
|
self.alphastd = alphastd |
|
|
self.eigval = torch.Tensor(eigval) |
|
|
self.eigvec = torch.Tensor(eigvec) |
|
|
|
|
|
def __call__(self, img): |
|
|
if self.alphastd == 0: |
|
|
return img |
|
|
|
|
|
alpha = img.new().resize_(3).normal_(0, self.alphastd) |
|
|
rgb = self.eigvec.type_as(img).clone()\ |
|
|
.mul(alpha.view(1, 3).expand(3, 3))\ |
|
|
.mul(self.eigval.view(1, 3).expand(3, 3))\ |
|
|
.sum(1).squeeze() |
|
|
return img.add(rgb.view(3, 1, 1).expand_as(img)) |
|
|
|
