File size: 4,172 Bytes
34d1f8b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
import numpy as np
import torch
import torch.nn as nn
from PIL import Image
class Grid(object):
def __init__(self,
use_h,
use_w,
rotate=1,
offset=False,
ratio=0.5,
mode=0,
prob=1.):
self.use_h = use_h
self.use_w = use_w
self.rotate = rotate
self.offset = offset
self.ratio = ratio
self.mode = mode
self.st_prob = prob
self.prob = prob
def set_prob(self, epoch, max_epoch):
self.prob = self.st_prob * epoch / max_epoch
def __call__(self, img, label):
if np.random.rand() > self.prob:
return img, label
h = img.size(1)
w = img.size(2)
self.d1 = 2
self.d2 = min(h, w)
hh = int(1.5 * h)
ww = int(1.5 * w)
d = np.random.randint(self.d1, self.d2)
if self.ratio == 1:
self.L = np.random.randint(1, d)
else:
self.L = min(max(int(d * self.ratio + 0.5), 1), d - 1)
mask = np.ones((hh, ww), np.float32)
st_h = np.random.randint(d)
st_w = np.random.randint(d)
if self.use_h:
for i in range(hh // d):
s = d * i + st_h
t = min(s + self.L, hh)
mask[s:t, :] *= 0
if self.use_w:
for i in range(ww // d):
s = d * i + st_w
t = min(s + self.L, ww)
mask[:, s:t] *= 0
r = np.random.randint(self.rotate)
mask = Image.fromarray(np.uint8(mask))
mask = mask.rotate(r)
mask = np.asarray(mask)
mask = mask[(hh - h) // 2:(hh - h) // 2 + h,
(ww - w) // 2:(ww - w) // 2 + w]
mask = torch.from_numpy(mask).float()
if self.mode == 1:
mask = 1 - mask
mask = mask.expand_as(img)
if self.offset:
offset = torch.from_numpy(2 * (np.random.rand(h, w) - 0.5)).float()
offset = (1 - mask) * offset
img = img * mask + offset
else:
img = img * mask
return img, label
class GridMask(nn.Module):
def __init__(self,
use_h,
use_w,
rotate=1,
offset=False,
ratio=0.5,
mode=0,
prob=1.):
super(GridMask, self).__init__()
self.use_h = use_h
self.use_w = use_w
self.rotate = rotate
self.offset = offset
self.ratio = ratio
self.mode = mode
self.st_prob = prob
self.prob = prob
def set_prob(self, epoch, max_epoch):
self.prob = self.st_prob * epoch / max_epoch # + 1.# 0.5
def forward(self, x):
if np.random.rand() > self.prob or not self.training:
return x
n, c, h, w = x.size()
x = x.view(-1, h, w)
hh = int(1.5 * h)
ww = int(1.5 * w)
d = np.random.randint(2, h)
self.L = min(max(int(d * self.ratio + 0.5), 1), d - 1)
mask = np.ones((hh, ww), np.float32)
st_h = np.random.randint(d)
st_w = np.random.randint(d)
if self.use_h:
for i in range(hh // d):
s = d * i + st_h
t = min(s + self.L, hh)
mask[s:t, :] *= 0
if self.use_w:
for i in range(ww // d):
s = d * i + st_w
t = min(s + self.L, ww)
mask[:, s:t] *= 0
r = np.random.randint(self.rotate)
mask = Image.fromarray(np.uint8(mask))
mask = mask.rotate(r)
mask = np.asarray(mask)
mask = mask[(hh - h) // 2:(hh - h) // 2 + h,
(ww - w) // 2:(ww - w) // 2 + w]
mask = torch.from_numpy(mask).to(x)
if self.mode == 1:
mask = 1 - mask
mask = mask.expand_as(x)
if self.offset:
offset = torch.from_numpy(2 * (np.random.rand(h, w) - 0.5)).to(x)
x = x * mask + offset * (1 - mask)
else:
x = x * mask
return x.view(n, c, h, w)
|