def draw_anchor(ImgPath, AnnoPath, save_path):
# load data
testset = VOCDetection(args.voc_root, [('2007', 'test')], None,
VOCAnnotationTransform())
imagelist = os.listdir(ImgPath)
cnt = 5
#for image in imagelist:
for i in range(cnt):
image, annotation = testset.pull_anno(i)
#image_pre, ext = os.path.splitext(image)
imgfile = ImgPath + image + '.png'
xmlfile = AnnoPath + 'test' + image + '.xml'
#xmlfile = AnnoPath + image + '.xml'
#xmlfile = AnnoPath +image + '.xml'
# print(image)
# 打开xml文档
DOMTree = xml.dom.minidom.parse(xmlfile)
# 得到文档元素对象
collection = DOMTree.documentElement
# 读取图片
img = cv.imread(imgfile)
filenamelist = collection.getElementsByTagName("filename")
filename = filenamelist[0].childNodes[0].data
print(filename)
# 得到标签名为object的信息
objectlist = collection.getElementsByTagName("object")
for objects in objectlist:
# 每个object中得到子标签名为name的信息
namelist = objects.getElementsByTagName('name')
name_idx = 0
bndbox = objects.getElementsByTagName('bndbox')
# print(bndbox)
for box in bndbox:
x1_list = box.getElementsByTagName('xmin')
x1 = int(x1_list[0].childNodes[0].data)
y1_list = box.getElementsByTagName('ymin')
y1 = int(y1_list[0].childNodes[0].data)
x2_list = box.getElementsByTagName('xmax') #注意坐标，看是否需要转换
x2 = int(x2_list[0].childNodes[0].data)
y2_list = box.getElementsByTagName('ymax')
y2 = int(y2_list[0].childNodes[0].data)
cv.rectangle(img, (x1, y1), (x2, y2), (0, 165, 255),
thickness=2)
# 通过此语句得到具体的某个name的值
objectname = namelist[name_idx].childNodes[0].data
cv.putText(img,
objectname, (x1, y1),
cv.FONT_HERSHEY_COMPLEX,
0.7, (0, 0, 255),
thickness=1)
name_idx += 1
#cv.imshow(filename, img)#这个要安装Xmanager才可以看
cv.imwrite(save_path + '/' + filename, img) #save picture
def read_gt(voc_dir):
set_type = 'test'
dataset_mean = (104, 117, 123)
dataset = VOCDetection(voc_dir, [('2007', set_type)],
BaseTransform(300, dataset_mean),
VOCAnnotationTransform())
num_images = len(dataset)
gt_bbox = [[[] for _ in range(num_images)]
for _ in range(len(labelmap)+1)]
for i in range(len(dataset)):
im_name, gt = dataset.pull_anno(i)
for box_conf in gt:
gt_bbox[box_conf[4]+1][i].append(box_conf[:4])
return gt_bbox, num_images
if __name__ == '__main__':
dataset = VOCDetection(
args.voc_root,
[('2007', set_type)],
BaseTransform(300, dataset_mean), # resize to 300*300 and - mean
VOCAnnotationTransform(keep_difficult=True))
# cls * id/size
# +1 for total scale division
num_cls = len(labelmap) + 1
dets_id = [[] for i in range(num_cls)]
dets_size = [[] for i in range(num_cls)]
print('pulling annotation...')
for i in range(len(dataset)):
imgid, gt = dataset.pull_anno(i)
for j, det in enumerate(gt):
det_size = (det[2] - det[0]) * (det[3] - det[1])
cls = det[-1]
dets_id[cls].append(imgid)
dets_size[cls].append(det_size)
dets_id[-1].append(imgid)
dets_size[-1].append(det_size)
if i % 100 == 0:
print('\rProgress: {}%'.format(int(100.0 * i / len(dataset))),
end='')
print()
# extra-small (XS: bottom 10%)
# small (S: next 20%)
# medium (M: next 40%)
dataset = COCODataset(data_dir=coco_root,
img_size=size,
transform=BaseTransform([size, size]))
boxes = []
print("The dataset size: ", len(dataset))
print("Loading the dataset ...")
for i in range(len(dataset)):
if i % 5000 == 0:
print('Loading datat [%d / %d]' % (i + 1, len(dataset)))
if dataset == 'coco':
# For COCO
img, _ = dataset.pull_image(i)
w, h = img.shape[1], img.shape[0]
annotation = dataset.pull_anno(i)
elif dataset == 'voc':
# For VOC
img = dataset.pull_image(i)
w, h = img.shape[1], img.shape[0]
_, annotation = dataset.pull_anno(i)
# prepare bbox datas
for box_and_label in annotation:
box = box_and_label[:-1]
xmin, ymin, xmax, ymax = box
bw = (xmax - xmin) / w * size
bh = (ymax - ymin) / h * size
# check bbox
if bw < 1.0 or bh < 1.0:
show_threshold = 0.05
net = build_ssd('test', 300, 2)
net.load_state_dict(torch.load('weights/ssd300_0712_115000.pth'))
testset = VOCDetection(VOCroot, [('2007', 'test')], None,
AnnotationTransform())
transform = BaseTransform(net.size, (104, 117, 123))
net.eval()
net.cuda()
cudnn.benchmark = True
print('Finished loading model!')
num_images = len(testset)
for i in range(num_images):
img = testset.pull_image(i)
img_id, annotation = testset.pull_anno(i)
gtloc = tuple(np.array(annotation[0][:-1]).astype('int32'))
x = torch.from_numpy(transform(img)[0]).permute(2, 0, 1)
x = Variable(x.unsqueeze(0))
x = x.cuda()
y = net(x)
detections = y.data
scale = torch.Tensor(
[img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
im2show = np.copy(img)
for i in range(1, detections.size(1)):
j = 0
while detections[0, i, j, 0] >= show_threshold:
score = detections[0, i, j, 0]
label_name = labelmap[i - 1]
pt = (detections[0, i, j, 1:] *
def ssd_detect(limit_detection, dataset):
# image = cv2.imread('./data/example.jpg', cv2.IMREAD_COLOR) # uncomment if dataset not downloaded
# here we specify year (07 or 12) and dataset ('test', 'val', 'train')
testset = VOCDetection(VOC_ROOT, [('2007', dataset)], None,
VOCAnnotationTransform())
for img_id in range(len(testset)):
if img_id % 100 == 1:
print(img_id, '/', len(testset))
image = testset.pull_image(img_id)
rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
x = cv2.resize(image, (300, 300)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0)) # wrap tensor in Variable
if torch.cuda.is_available():
xx = xx.cuda()
y = net(xx)
from data import VOC_CLASSES as labels
top_k = 10
plt.figure(figsize=(10, 10))
colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()
# plot the image for matplotlib
currentAxis = plt.gca()
detections = y.data
# scale each detection back up to the image
scale = torch.Tensor(rgb_image.shape[1::-1]).repeat(2)
for i in range(detections.size(1)):
j = 0
while detections[0, i, j, 0] >= limit_detection:
score = detections[0, i, j, 0]
label_name = labels[i - 1]
display_txt = '%s: %.2f' % (label_name, score)
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
coords = (pt[0], pt[1]), pt[2] - pt[0] + 1, pt[3] - pt[1] + 1
color = colors[i]
currentAxis.add_patch(
plt.Rectangle(*coords,
fill=False,
edgecolor=color,
linewidth=2))
currentAxis.text(pt[0],
pt[1],
display_txt,
bbox={
'facecolor': color,
'alpha': 0.5
})
j += 1
#显示正确的检测框
[imageid, gts] = testset.pull_anno(img_id)
for gt in gts:
coords = (gt[0], gt[1]), gt[2] - gt[0] + 1, gt[3] - gt[1] + 1
currentAxis.add_patch(
plt.Rectangle(*coords,
fill=False,
edgecolor=colors[15],
linewidth=2))
plt.imshow(rgb_image)
plt.savefig('result/data/' + str(img_id) + '.jpg')
plt.close()
