def __getitem__(self, idx):
img_name = self.img_name[idx]
#new work
img_path = os.path.join(self.datadir, img_name)
if not os.path.exists(img_path):
img_path = os.path.join(self.datadir2, img_name)
lim = img_name.split('_')[0]
if lim not in ["img", "image", "tainchi"]:
xml_path = os.path.join(self.labelsdir,
img_name.replace('.png', '.xml'))
else:
self.labelsdir2 = "/home/like/data/VOC/VOC2007/Annotations2"
xml_path = os.path.join(self.labelsdir2,
img_name.replace('.jpg', '.xml'))
img = cv2.imread(img_path)
gtbox, _ = readxml(xml_path)
h, w, c = img.shape
if np.random.randint(2) == 1 and len(gtbox) > 3:
img = img[:, ::-1, :]
newx1 = w - gtbox[:, 2] - 1
newx2 = w - gtbox[:, 0] - 1
gtbox[:, 0] = newx1
gtbox[:, 2] = newx2
[cls, regr], _ = cal_rpn(
(h, w), (math.ceil(h / 16), math.ceil(w / 16)), 16, gtbox)
m_img = img - IMAGE_MEAN
regr = np.hstack([cls.reshape(cls.shape[0], 1), regr])
cls = np.expand_dims(cls, axis=0)
m_img = torch.from_numpy(m_img.transpose([2, 0, 1])).float()
cls = torch.from_numpy(cls).float()
regr = torch.from_numpy(regr).float()
"""使用新/8的策略"""
"""得到新的gtbox"""
newgtbox = []
for box in gtbox:
x1 = box[0]
y1 = box[1]
x2 = box[2]
y2 = box[3]
newgtbox.append([x1, y1, x1 + 8, y2])
newgtbox.append([x1 + 8, y1, x2, y2])
newgtbox = np.array(newgtbox)
[cls_8, regr_8], _ = cal_rpn(
(h, w), (math.ceil(h / 8), math.ceil(w / 8)), 8, newgtbox)
regr_8 = np.hstack([cls_8.reshape(cls_8.shape[0], 1), regr_8])
cls_8 = np.expand_dims(cls_8, axis=0)
cls_8 = torch.from_numpy(cls_8).float()
regr_8 = torch.from_numpy(regr_8).float()
return m_img, cls, regr, cls_8, regr_8
def __getitem__(self, idx):
img_name = self.img_names[idx]
img_path = os.path.join(self.datadir, img_name)
print(img_path)
xml_path = os.path.join(self.labelsdir,
img_name.replace('.jpg', '.xml'))
gtbox, _ = readxml(xml_path)
img = cv2.imread(img_path)
h, w, c = img.shape
# clip image
if np.random.randint(2) == 1:
img = img[:, ::-1, :]
newx1 = w - gtbox[:, 2] - 1
newx2 = w - gtbox[:, 0] - 1
gtbox[:, 0] = newx1
gtbox[:, 2] = newx2
[cls, regr], _ = cal_rpn((h, w), (int(h / 16), int(w / 16)), 16, gtbox)
m_img = img - IMAGE_MEAN
regr = np.hstack([cls.reshape(cls.shape[0], 1), regr])
cls = np.expand_dims(cls, axis=0)
# transform to torch tensor
m_img = torch.from_numpy(m_img.transpose([2, 0, 1])).float()
cls = torch.from_numpy(cls).float()
regr = torch.from_numpy(regr).float()
return m_img, cls, regr
def __getitem__(self, index):
img = self.imgs[index]
xml_file = os.path.join(self.voc_dir, "Annotations", (img + ".xml"))
gt_boxes, labels, image_name = self.read_xml(xml_file)
image_name = os.path.join(self.voc_dir, "JPEGImages", image_name)
# 读取图片，如果尺寸不是ctpn_params.IMAGE_HEIGHT*ctpn_params.IMAGE_HEIGHT，等比例缩放至该尺寸
image = cv2.imread(image_name)
if image.shape[0] != ctpn_params.IMAGE_HEIGHT or image.shape[1] != ctpn_params.IMAGE_HEIGHT:
image, rescale_fac, padding = resize_image2square(image, ctpn_params.IMAGE_HEIGHT)
gt_boxes = adj_gtboxes(gt_boxes, rescale_fac, padding)
# 将大标定框分割成宽度是ctpn_params.ANCHORS_WIDTH的小框
gt_boxes, class_ids = gen_gt_from_quadrilaterals(gt_boxes, labels, image.shape, ctpn_params.ANCHORS_WIDTH)
h, w, c = image.shape
if self.is_debug == False:
image = image - ctpn_params.IMAGE_MEAN
image = torch.from_numpy(image.transpose([2, 0, 1])).float()
# 计算rpn
[clss, regr], base_anchors = cal_rpn((h, w), (int(h / 16), int(w / 16)), 16, gt_boxes)
# 数据按[(label, Vc, Vh)]存放
regr = np.hstack([clss.reshape(clss.shape[0], 1), regr])
regr = torch.from_numpy(regr).float()
clss = np.expand_dims(clss, axis=0)
clss = torch.from_numpy(clss).float()
if self.is_debug:
return image, gt_boxes, clss, index
else:
return image, regr, clss, index
def __getitem__(self, idx):
img_name = self.img_names[idx]
img_path = os.path.join(self.datadir, img_name)
#print(img_path)
img = cv2.imread(img_path)
#cv2.imwrite('original.jpg', img)
#####for read error, use default image#####
if img is None:
# print(img_path)
with open('error_imgs.txt', 'a') as f:
f.write('{}\n'.format(img_path))
img_name = 'img_2647.jpg'
img_path = os.path.join(self.datadir, img_name)
img = cv2.imread(img_path)
#####for read error, use default image#####
h, w, c = img.shape
rescale_fac = max(h, w) / 1600
if rescale_fac > 1.0:
h = int(h / rescale_fac)
w = int(w / rescale_fac)
img = cv2.resize(img, (w, h))
gt_path = os.path.join(self.labelsdir,
'gt_' + img_name.split('.')[0] + '.txt')
gtbox = self.parse_gtfile(gt_path, rescale_fac)
# print('gtbox shape: ', gtbox.shape)
# clip image
if np.random.randint(2) == 1:
img = img[:, ::-1, :]
newx1 = w - gtbox[:, 2] - 1
newx2 = w - gtbox[:, 0] - 1
gtbox[:, 0] = newx1
gtbox[:, 2] = newx2
[cls, regr], base_anchors = cal_rpn((h, w), (int(h / 16), int(w / 16)),
16, gtbox)
# print('class', cls, f"{cls.shape}")
debug_img = self.draw_boxes(img.copy(), cls, base_anchors, gtbox)
os.makedirs('debug', exist_ok=True)
cv2.imwrite('debug/{}'.format(img_name), debug_img)
m_img = img - IMAGE_MEAN
regr = np.hstack([cls.reshape(cls.shape[0], 1), regr])
cls = np.expand_dims(cls, axis=0)
# transform to torch tensor
m_img = torch.from_numpy(m_img.transpose([2, 0, 1])).float()
cls = torch.from_numpy(cls).float()
regr = torch.from_numpy(regr).float()
return m_img, cls, regr
def __getitem__(self, idx):
img_name = self.img_names[idx]
img_path = os.path.join(self.datadir, img_name)
# print(img_path)
txt_path = os.path.join(self.labelsdir,
img_name.replace('.jpg', '.txt'))
gtboxes = readtxt(txt_path)
if len(gtboxes) < 2:
return self.__getitem__((idx + 1) % len(self))
gtbox = np.array(gtboxes)
img = cv2.imread(img_path)
h, w, c = img.shape
if w < 32:
img = cv2.resize(img, (h * 5, w * 5), cv2.INTER_NEAREST)
gtbox = gtbox * 5
# clip image
if np.random.randint(2) == 1:
img = img[:, ::-1, :]
newx1 = w - gtbox[:, 2] - 1
newx2 = w - gtbox[:, 0] - 1
gtbox[:, 0] = newx1
gtbox[:, 2] = newx2
[cls, regr], _ = cal_rpn((h, w), (int(h / 16), int(w / 16)), 16, gtbox)
if cls is None or max(cls) == -1:
return self.__getitem__((idx + 1) % len(self))
m_img = img - IMAGE_MEAN
regr = np.hstack([cls.reshape(cls.shape[0], 1), regr])
cls = np.expand_dims(cls, axis=0)
# transform to torch tensor
m_img = torch.from_numpy(m_img.transpose([2, 0, 1])).float()
cls = torch.from_numpy(cls).float()
regr = torch.from_numpy(regr).float()
return m_img, cls, regr
model = CTPN_Model()
clsp, regrp = model(img)
import cv2
import numpy as np
from ctpn_utils import cal_rpn
path = "./detection_test/205531101_00590.jpg"
img = cv2.imread(path)
gtboxes = [(40, 40, 140, 140), (56, 40, 140, 140)]
gtbox = np.array(gtboxes)
h, w, c = img.shape
[cls, regr], _ = cal_rpn((h, w), (int(h / 16), int(w / 16)), 16, gtbox)
regr = np.hstack([cls.reshape(cls.shape[0], 1), regr])
regr = torch.from_numpy(regr)
regr = regr.unsqueeze(0)
cls = np.expand_dims(cls, axis=0)
cls = torch.from_numpy(cls)
cls = cls.unsqueeze(0)
# loss = RPN_CLS_Loss("cpu")
# print(loss(clsp,cls))
regrp = regrp.double()
regr = regr.double()
