Spaces:
Runtime error
Runtime error
File size: 11,800 Bytes
5b93456 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 |
from random import sample, shuffle
import cv2
import numpy as np
import torch
from PIL import Image
from torch.utils.data.dataset import Dataset
from utils.utils import cvtColor, preprocess_input
class YoloDataset(Dataset):
def __init__(self, annotation_lines, input_shape, num_classes, epoch_length, \
mosaic, mixup, mosaic_prob, mixup_prob, train, special_aug_ratio = 0.7):
super(YoloDataset, self).__init__()
self.annotation_lines = annotation_lines
self.input_shape = input_shape
self.num_classes = num_classes
self.epoch_length = epoch_length
self.mosaic = mosaic
self.mosaic_prob = mosaic_prob
self.mixup = mixup
self.mixup_prob = mixup_prob
self.train = train
self.special_aug_ratio = special_aug_ratio
self.epoch_now = -1
self.length = len(self.annotation_lines)
def __len__(self):
return self.length
def __getitem__(self, index):
index = index % self.length
if self.mosaic and self.rand() < self.mosaic_prob and self.epoch_now < self.epoch_length * self.special_aug_ratio:
lines = sample(self.annotation_lines, 3)
lines.append(self.annotation_lines[index])
shuffle(lines)
image, box = self.get_random_data_with_Mosaic(lines, self.input_shape)
if self.mixup and self.rand() < self.mixup_prob:
lines = sample(self.annotation_lines, 1)
image_2, box_2 = self.get_random_data(lines[0], self.input_shape, random = self.train)
image, box = self.get_random_data_with_MixUp(image, box, image_2, box_2)
else:
image, box = self.get_random_data(self.annotation_lines[index], self.input_shape, random = self.train)
image = np.transpose(preprocess_input(np.array(image, dtype=np.float32)), (2, 0, 1))
box = np.array(box, dtype=np.float32)
if len(box) != 0:
box[:, [0, 2]] = box[:, [0, 2]] / self.input_shape[1]
box[:, [1, 3]] = box[:, [1, 3]] / self.input_shape[0]
box[:, 2:4] = box[:, 2:4] - box[:, 0:2]
box[:, 0:2] = box[:, 0:2] + box[:, 2:4] / 2
return image, box
def rand(self, a=0, b=1):
return np.random.rand()*(b-a) + a
def get_random_data(self, annotation_line, input_shape, jitter=.3, hue=.1, sat=0.7, val=0.4, random=True):
line = annotation_line.split()
image = Image.open(line[0])
image = cvtColor(image)
iw, ih = image.size
h, w = input_shape
box = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])
if not random:
scale = min(w/iw, h/ih)
nw = int(iw*scale)
nh = int(ih*scale)
dx = (w-nw)//2
dy = (h-nh)//2
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image_data = np.array(new_image, np.float32)
if len(box)>0:
np.random.shuffle(box)
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w>1, box_h>1)]
return image_data, box
new_ar = iw/ih * self.rand(1-jitter,1+jitter) / self.rand(1-jitter,1+jitter)
scale = self.rand(.25, 2)
if new_ar < 1:
nh = int(scale*h)
nw = int(nh*new_ar)
else:
nw = int(scale*w)
nh = int(nw/new_ar)
image = image.resize((nw,nh), Image.BICUBIC)
dx = int(self.rand(0, w-nw))
dy = int(self.rand(0, h-nh))
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image = new_image
flip = self.rand()<.5
if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)
image_data = np.array(image, np.uint8)
r = np.random.uniform(-1, 1, 3) * [hue, sat, val] + 1
hue, sat, val = cv2.split(cv2.cvtColor(image_data, cv2.COLOR_RGB2HSV))
dtype = image_data.dtype
x = np.arange(0, 256, dtype=r.dtype)
lut_hue = ((x * r[0]) % 180).astype(dtype)
lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
image_data = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
image_data = cv2.cvtColor(image_data, cv2.COLOR_HSV2RGB)
if len(box)>0:
np.random.shuffle(box)
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
if flip: box[:, [0,2]] = w - box[:, [2,0]]
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w>1, box_h>1)]
return image_data, box
def merge_bboxes(self, bboxes, cutx, cuty):
merge_bbox = []
for i in range(len(bboxes)):
for box in bboxes[i]:
tmp_box = []
x1, y1, x2, y2 = box[0], box[1], box[2], box[3]
if i == 0:
if y1 > cuty or x1 > cutx:
continue
if y2 >= cuty and y1 <= cuty:
y2 = cuty
if x2 >= cutx and x1 <= cutx:
x2 = cutx
if i == 1:
if y2 < cuty or x1 > cutx:
continue
if y2 >= cuty and y1 <= cuty:
y1 = cuty
if x2 >= cutx and x1 <= cutx:
x2 = cutx
if i == 2:
if y2 < cuty or x2 < cutx:
continue
if y2 >= cuty and y1 <= cuty:
y1 = cuty
if x2 >= cutx and x1 <= cutx:
x1 = cutx
if i == 3:
if y1 > cuty or x2 < cutx:
continue
if y2 >= cuty and y1 <= cuty:
y2 = cuty
if x2 >= cutx and x1 <= cutx:
x1 = cutx
tmp_box.append(x1)
tmp_box.append(y1)
tmp_box.append(x2)
tmp_box.append(y2)
tmp_box.append(box[-1])
merge_bbox.append(tmp_box)
return merge_bbox
def get_random_data_with_Mosaic(self, annotation_line, input_shape, jitter=0.3, hue=.1, sat=0.7, val=0.4):
h, w = input_shape
min_offset_x = self.rand(0.3, 0.7)
min_offset_y = self.rand(0.3, 0.7)
image_datas = []
box_datas = []
index = 0
for line in annotation_line:
line_content = line.split()
image = Image.open(line_content[0])
image = cvtColor(image)
iw, ih = image.size
box = np.array([np.array(list(map(int,box.split(',')))) for box in line_content[1:]])
flip = self.rand()<.5
if flip and len(box)>0:
image = image.transpose(Image.FLIP_LEFT_RIGHT)
box[:, [0,2]] = iw - box[:, [2,0]]
new_ar = iw/ih * self.rand(1-jitter,1+jitter) / self.rand(1-jitter,1+jitter)
scale = self.rand(.4, 1)
if new_ar < 1:
nh = int(scale*h)
nw = int(nh*new_ar)
else:
nw = int(scale*w)
nh = int(nw/new_ar)
image = image.resize((nw, nh), Image.BICUBIC)
if index == 0:
dx = int(w*min_offset_x) - nw
dy = int(h*min_offset_y) - nh
elif index == 1:
dx = int(w*min_offset_x) - nw
dy = int(h*min_offset_y)
elif index == 2:
dx = int(w*min_offset_x)
dy = int(h*min_offset_y)
elif index == 3:
dx = int(w*min_offset_x)
dy = int(h*min_offset_y) - nh
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image_data = np.array(new_image)
index = index + 1
box_data = []
if len(box)>0:
np.random.shuffle(box)
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w>1, box_h>1)]
box_data = np.zeros((len(box),5))
box_data[:len(box)] = box
image_datas.append(image_data)
box_datas.append(box_data)
cutx = int(w * min_offset_x)
cuty = int(h * min_offset_y)
new_image = np.zeros([h, w, 3])
new_image[:cuty, :cutx, :] = image_datas[0][:cuty, :cutx, :]
new_image[cuty:, :cutx, :] = image_datas[1][cuty:, :cutx, :]
new_image[cuty:, cutx:, :] = image_datas[2][cuty:, cutx:, :]
new_image[:cuty, cutx:, :] = image_datas[3][:cuty, cutx:, :]
new_image = np.array(new_image, np.uint8)
r = np.random.uniform(-1, 1, 3) * [hue, sat, val] + 1
hue, sat, val = cv2.split(cv2.cvtColor(new_image, cv2.COLOR_RGB2HSV))
dtype = new_image.dtype
x = np.arange(0, 256, dtype=r.dtype)
lut_hue = ((x * r[0]) % 180).astype(dtype)
lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
new_image = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
new_image = cv2.cvtColor(new_image, cv2.COLOR_HSV2RGB)
new_boxes = self.merge_bboxes(box_datas, cutx, cuty)
return new_image, new_boxes
def get_random_data_with_MixUp(self, image_1, box_1, image_2, box_2):
new_image = np.array(image_1, np.float32) * 0.5 + np.array(image_2, np.float32) * 0.5
if len(box_1) == 0:
new_boxes = box_2
elif len(box_2) == 0:
new_boxes = box_1
else:
new_boxes = np.concatenate([box_1, box_2], axis=0)
return new_image, new_boxes
def yolo_dataset_collate(batch):
images = []
bboxes = []
for img, box in batch:
images.append(img)
bboxes.append(box)
images = torch.from_numpy(np.array(images)).type(torch.FloatTensor)
bboxes = [torch.from_numpy(ann).type(torch.FloatTensor) for ann in bboxes]
return images, bboxes
|