File size: 14,124 Bytes
aa24fe8 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 | 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 SSDDataset(Dataset):
def __init__(self, annotation_lines, input_shape, anchors, batch_size, num_classes, train, overlap_threshold = 0.5):
super(SSDDataset, self).__init__()
self.annotation_lines = annotation_lines
self.length = len(self.annotation_lines)
self.input_shape = input_shape
self.anchors = anchors
self.num_anchors = len(anchors)
self.batch_size = batch_size
self.num_classes = num_classes
self.train = train
self.overlap_threshold = overlap_threshold
def __len__(self):
return self.length
def __getitem__(self, index):
index = index % self.length
#---------------------------------------------------#
# 训练时进行数据的随机增强
# 验证时不进行数据的随机增强
#---------------------------------------------------#
image, box = self.get_random_data(self.annotation_lines[index], self.input_shape, random = self.train)
image_data = np.transpose(preprocess_input(np.array(image, dtype = np.float32)), (2, 0, 1))
if len(box)!=0:
boxes = np.array(box[:,:4] , dtype=np.float32)
# 进行归一化，调整到0-1之间
boxes[:, [0, 2]] = boxes[:,[0, 2]] / self.input_shape[1]
boxes[:, [1, 3]] = boxes[:,[1, 3]] / self.input_shape[0]
# 对真实框的种类进行one hot处理
one_hot_label = np.eye(self.num_classes - 1)[np.array(box[:,4], np.int32)]
box = np.concatenate([boxes, one_hot_label], axis=-1)
box = self.assign_boxes(box)
return np.array(image_data, np.float32), np.array(box, np.float32)
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()
#------------------------------#
# 读取图像并转换成RGB图像
#------------------------------#
image = Image.open(line[0])
image = cvtColor(image)
#------------------------------#
# 获得图像的高宽与目标高宽
#------------------------------#
iw, ih = image.size
h, w = input_shape
#------------------------------#
# 获得预测框
#------------------------------#
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
#---------------------------------#
# 将图像多余的部分加上灰条
#---------------------------------#
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)
#---------------------------------#
# 对真实框进行调整
#---------------------------------#
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)] # discard invalid box
return image_data, box
#------------------------------------------#
# 对图像进行缩放并且进行长和宽的扭曲
#------------------------------------------#
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)
#------------------------------------------#
# 将图像多余的部分加上灰条
#------------------------------------------#
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
#------------------------------------------#
# 翻转图像
#------------------------------------------#
flip = self.rand()<.5
if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)
image_data = np.array(image, np.uint8)
#---------------------------------#
# 对图像进行色域变换
# 计算色域变换的参数
#---------------------------------#
r = np.random.uniform(-1, 1, 3) * [hue, sat, val] + 1
#---------------------------------#
# 将图像转到HSV上
#---------------------------------#
hue, sat, val = cv2.split(cv2.cvtColor(image_data, cv2.COLOR_RGB2HSV))
dtype = image_data.dtype
#---------------------------------#
# 应用变换
#---------------------------------#
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)
#---------------------------------#
# 对真实框进行调整
#---------------------------------#
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 iou(self, box):
#---------------------------------------------#
# 计算出每个真实框与所有的先验框的iou
# 判断真实框与先验框的重合情况
#---------------------------------------------#
inter_upleft = np.maximum(self.anchors[:, :2], box[:2])
inter_botright = np.minimum(self.anchors[:, 2:4], box[2:])
inter_wh = inter_botright - inter_upleft
inter_wh = np.maximum(inter_wh, 0)
inter = inter_wh[:, 0] * inter_wh[:, 1]
#---------------------------------------------#
# 真实框的面积
#---------------------------------------------#
area_true = (box[2] - box[0]) * (box[3] - box[1])
#---------------------------------------------#
# 先验框的面积
#---------------------------------------------#
area_gt = (self.anchors[:, 2] - self.anchors[:, 0])*(self.anchors[:, 3] - self.anchors[:, 1])
#---------------------------------------------#
# 计算iou
#---------------------------------------------#
union = area_true + area_gt - inter
iou = inter / union
return iou
def encode_box(self, box, return_iou=True, variances = [0.1, 0.1, 0.2, 0.2]):
#---------------------------------------------#
# 计算当前真实框和先验框的重合情况
# iou [self.num_anchors]
# encoded_box [self.num_anchors, 5]
#---------------------------------------------#
iou = self.iou(box)
encoded_box = np.zeros((self.num_anchors, 4 + return_iou))
#---------------------------------------------#
# 找到每一个真实框，重合程度较高的先验框
# 真实框可以由这个先验框来负责预测
#---------------------------------------------#
assign_mask = iou > self.overlap_threshold
#---------------------------------------------#
# 如果没有一个先验框重合度大于self.overlap_threshold
# 则选择重合度最大的为正样本
#---------------------------------------------#
if not assign_mask.any():
assign_mask[iou.argmax()] = True
#---------------------------------------------#
# 利用iou进行赋值
#---------------------------------------------#
if return_iou:
encoded_box[:, -1][assign_mask] = iou[assign_mask]
#---------------------------------------------#
# 找到对应的先验框
#---------------------------------------------#
assigned_anchors = self.anchors[assign_mask]
#---------------------------------------------#
# 逆向编码，将真实框转化为ssd预测结果的格式
# 先计算真实框的中心与长宽
#---------------------------------------------#
box_center = 0.5 * (box[:2] + box[2:])
box_wh = box[2:] - box[:2]
#---------------------------------------------#
# 再计算重合度较高的先验框的中心与长宽
#---------------------------------------------#
assigned_anchors_center = (assigned_anchors[:, 0:2] + assigned_anchors[:, 2:4]) * 0.5
assigned_anchors_wh = (assigned_anchors[:, 2:4] - assigned_anchors[:, 0:2])
#------------------------------------------------#
# 逆向求取ssd应该有的预测结果
# 先求取中心的预测结果，再求取宽高的预测结果
# 存在改变数量级的参数，默认为[0.1,0.1,0.2,0.2]
#------------------------------------------------#
encoded_box[:, :2][assign_mask] = box_center - assigned_anchors_center
encoded_box[:, :2][assign_mask] /= assigned_anchors_wh
encoded_box[:, :2][assign_mask] /= np.array(variances)[:2]
encoded_box[:, 2:4][assign_mask] = np.log(box_wh / assigned_anchors_wh)
encoded_box[:, 2:4][assign_mask] /= np.array(variances)[2:4]
return encoded_box.ravel()
def assign_boxes(self, boxes):
#---------------------------------------------------#
# assignment分为3个部分
# :4 的内容为网络应该有的回归预测结果
# 4:-1 的内容为先验框所对应的种类，默认为背景
# -1 的内容为当前先验框是否包含目标
#---------------------------------------------------#
assignment = np.zeros((self.num_anchors, 4 + self.num_classes + 1))
assignment[:, 4] = 1.0
if len(boxes) == 0:
return assignment
# 对每一个真实框都进行iou计算
encoded_boxes = np.apply_along_axis(self.encode_box, 1, boxes[:, :4])
#---------------------------------------------------#
# 在reshape后，获得的encoded_boxes的shape为：
# [num_true_box, num_anchors, 4 + 1]
# 4是编码后的结果，1为iou
#---------------------------------------------------#
encoded_boxes = encoded_boxes.reshape(-1, self.num_anchors, 5)
#---------------------------------------------------#
# [num_anchors]求取每一个先验框重合度最大的真实框
#---------------------------------------------------#
best_iou = encoded_boxes[:, :, -1].max(axis=0)
best_iou_idx = encoded_boxes[:, :, -1].argmax(axis=0)
best_iou_mask = best_iou > 0
best_iou_idx = best_iou_idx[best_iou_mask]
#---------------------------------------------------#
# 计算一共有多少先验框满足需求
#---------------------------------------------------#
assign_num = len(best_iou_idx)
# 将编码后的真实框取出
encoded_boxes = encoded_boxes[:, best_iou_mask, :]
#---------------------------------------------------#
# 编码后的真实框的赋值
#---------------------------------------------------#
assignment[:, :4][best_iou_mask] = encoded_boxes[best_iou_idx, np.arange(assign_num), :4]
#----------------------------------------------------------#
# 4代表为背景的概率，设定为0，因为这些先验框有对应的物体
#----------------------------------------------------------#
assignment[:, 4][best_iou_mask] = 0
assignment[:, 5:-1][best_iou_mask] = boxes[best_iou_idx, 4:]
#----------------------------------------------------------#
# -1表示先验框是否有对应的物体
#----------------------------------------------------------#
assignment[:, -1][best_iou_mask] = 1
# 通过assign_boxes我们就获得了，输入进来的这张图片，应该有的预测结果是什么样子的
return assignment
# DataLoader中collate_fn使用
def ssd_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(np.array(bboxes)).type(torch.FloatTensor)
return images, bboxes
|