def demo(net, image_name, gt_boxes, result_dir, conf=0.75):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = image_name
im = cv2.imread(im_file)
im_height = im.shape[0]
im_width = im.shape[1]
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = r_im_detect(net, im)
# print "gt_margin: ", cfg.TEST.GT_MARGIN, cfg.TRAIN.GT_MARGIN
# print "img_padding: ", cfg.IMG_PADDING
timer.toc()
print('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = conf
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 5 * cls_ind:5 * (cls_ind + 1)] # D
cls_scores = scores[:, cls_ind]
dets = np.hstack(
(cls_boxes, cls_scores[:, np.newaxis])).astype(np.float32)
keep = rotate_gpu_nms(dets, NMS_THRESH) # D
dets = dets[keep, :]
#dets = dets[0:20]
#dets[:, 4] = dets[:, 4] * 0.45
dets[:, 2] = dets[:, 2] / cfg.TEST.GT_MARGIN
dets[:, 3] = dets[:, 3] / cfg.TEST.GT_MARGIN
#if imdb_name == "icdar13":
#write_result_ICDAR2013(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
#result_file = write_result_ICDAR2013(im_file, dets, CONF_THRESH, result_dir, im_height, im_width)
#print dets
#if imdb_name == "icdar15":
# write_result_ICDAR(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
results = write_result_ICDAR(im_file, dets, CONF_THRESH, result_dir,
im_height, im_width)
# write_result(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
# result_file = write_result(im_file, dets, CONF_THRESH, result_dir, im_height, im_width)
# print "write done"
# post_merge(result_file)
# print "merge done"
#
#print "merge done"
# vis_detections(im, cls, dets, gt_boxes, thresh=CONF_THRESH)
return results
def detect(self, image_file, thresh=0.5):
"""
return format: [ label score x1 y1 x2 y2 x3 y3 x4 y4 ]
"""
# Load the demo image
im = cv2.imread(image_file)
im_height = im.shape[0]
im_width = im.shape[1]
# Detect all object classes and regress object bounds
scores, boxes = r_im_detect(self.net, im)
NMS_THRESH = 0.3
####################################
### formate: [x_ctr y_ctr w h an score class]
predections = np.empty((0, 7)) # the last all classes result
#######################################
for cls_ind, cls in enumerate(self.classnames[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 5 * cls_ind:5 * (cls_ind + 1)] # D (300,5)
cls_scores = scores[:,
cls_ind] # (300,) cls_scores[:, np.newaxis] ===> (300,1)
dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])).astype(
np.float32) # (300,5) + (300,1) ===> (300,6)
keep = rotate_gpu_nms(dets, NMS_THRESH) # D
dets = dets[keep, :] # only one class
############################ add the other axis to contain the class label ####################
############### (n,6) ===> (n,7) [ box(5) , score ] ===> [ box(5) , score , class ]
label = np.ones_like(keep)
dets = np.hstack((dets, label[:, np.newaxis] * cls_ind))
########################### contact with different class #######################################
############## (n1,7) + (n2,7) + (n3,7) + (n4,7) ===> (n1+n2+n3+n4,7)
predections = np.vstack((predections, dets))
order = predections[:, 5] > thresh
predections = predections[order] # get score > 0.5
dets[:, 2] = dets[:, 2] / 1.4
dets[:, 3] = dets[:, 3] / 1.4
predections[:, 2] = predections[:, 2] / 1.4
predections[:, 3] = predections[:, 3] / 1.4
pre = predections[:, 0:6]
results = self.formatResult(predections, thresh, im_height, im_width)
# [ label score x1 y1 x2 y2 x3 y3 x4 y4 ]
return results
def demo(net, image_name, output_name):#, result_dir, ori_result_dir):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = image_name
im = cv2.imread(im_file)
im_height = im.shape[0]
im_width = im.shape[1]
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = r_im_detect(net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.9
NMS_THRESH = 0.3
file_ret = ""
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 5*cls_ind:5*(cls_ind + 1)] # D
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = rotate_gpu_nms(dets, NMS_THRESH) # D
dets = dets[keep, :]
#dets = dets[0:20]
#dets[:, 4] = dets[:, 4] * 0.45
dets[:, 2] = dets[:, 2] / 1.4
dets[:, 3] = dets[:, 3] / 1.4
file_ret = vis_detections(im, cls, dets, output_name, thresh=CONF_THRESH)
return file_ret
def demo(net, image_name, conf=0.1):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = image_name
im = cv2.imread(im_file)
#print(type(im),im.shape)
im.resize((400, 300, 3))
#print(type(im),im.shape)
im_height = im.shape[0]
im_width = im.shape[1]
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = r_im_detect(net, im)
timer.toc()
# print ('Detection took {:.3f}s for '
# '{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = conf
NMS_THRESH = 0.3
####################################
### formate: [x_ctr y_ctr w h an score class]
predections = np.empty((0, 7)) # the last all classes result
#######################################
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 5 * cls_ind:5 * (cls_ind + 1)] # D (300,5)
cls_scores = scores[:,
cls_ind] # (300,) cls_scores[:, np.newaxis] ===> (300,1)
dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])).astype(
np.float32) # (300,5) + (300,1) ===> (300,6)
keep = rotate_gpu_nms(dets, NMS_THRESH) # D
dets = dets[keep, :] # only one class
############################ add the other axis to contain the class label ####################
############### (n,6) ===> (n,7) [ box(5) , score ] ===> [ box(5) , score , class ]
label = np.ones_like(keep)
dets = np.hstack((dets, label[:, np.newaxis] * cls_ind))
########################### contact with different class #######################################
############## (n1,7) + (n2,7) + (n3,7) + (n4,7) ===> (n1+n2+n3+n4,7)
predections = np.vstack((predections, dets))
order = predections[:, 5] > 0.5
predections = predections[order] # get score > 0.5
dets[:, 2] = dets[:, 2] / cfg.TEST.GT_MARGIN
dets[:, 3] = dets[:, 3] / cfg.TEST.GT_MARGIN
predections[:, 2] = predections[:, 2] / cfg.TEST.GT_MARGIN
predections[:, 3] = predections[:, 3] / cfg.TEST.GT_MARGIN
pre = predections[:, 0:6]
return timer.total_time
if args.cpu_mode:
caffe.set_mode_cpu()
else:
caffe.set_mode_gpu()
caffe.set_device(args.gpu_id)
cfg.GPU_ID = args.gpu_id
net = caffe.Net(prototxt, caffemodel, caffe.TEST)
print '\n\nLoaded network {:s}'.format(caffemodel)
# Warmup on a dummy image
im = 128 * np.ones((300, 500, 3), dtype=np.uint8)
for i in xrange(2):
_, _ = r_im_detect(net, im)
im_names = []
gt_boxes = []
demo_dir = './data'
for img in os.listdir(demo_dir):
im_names.append(os.path.join(demo_dir, img))
gt_boxes.append([0, 0, 0, 0, 0])
# The detection results will save in cood_dir in txt
cood_dir = "./result"
# for im_idx in range(len(im_names)):
# print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
# print 'Demo for data/demo/{}'.format(im_names[im_idx])
def demo(net, image_name, gt_boxes, result_dir, conf=0.1):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = image_name
im = cv2.imread(im_file)
im_height = im.shape[0]
im_width = im.shape[1]
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = r_im_detect(net, im)
# print "gt_margin: ", cfg.TEST.GT_MARGIN, cfg.TRAIN.GT_MARGIN
# print "img_padding: ", cfg.IMG_PADDING
#print("score'size:",scores.shape) # (300,5) class_num is 5
#print("\n\n\nboxes'size:",boxes.shape) # (300,25) each box has 5 info to locate the box,so 5 * class_num = 25
timer.toc()
print('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = conf
NMS_THRESH = 0.3
####################################
### formate: [x_ctr y_ctr w h an score class]
predections = np.empty((0, 7)) # the last all classes result
#######################################
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 5 * cls_ind:5 * (cls_ind + 1)] # D (300,5)
cls_scores = scores[:,
cls_ind] # (300,) cls_scores[:, np.newaxis] ===> (300,1)
dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])).astype(
np.float32) # (300,5) + (300,1) ===> (300,6)
#print("dets111:",dets)
keep = rotate_gpu_nms(dets, NMS_THRESH) # D
dets = dets[keep, :] # only one class
#print('keep:',keep)
#print("cls_boxes:",cls_boxes.shape)
#print("cls_scores:",cls_scores.shape)
#print("dets:",dets)
#print("dets:",dets.shape)
#print type(cls_boxes)
############################ add the other axis to contain the class label ####################
############### (n,6) ===> (n,7) [ box(5) , score ] ===> [ box(5) , score , class ]
label = np.ones_like(keep)
dets = np.hstack((dets, label[:, np.newaxis] * cls_ind))
#print(dets)
########################### contact with different class #######################################
############## (n1,7) + (n2,7) + (n3,7) + (n4,7) ===> (n1+n2+n3+n4,7)
predections = np.vstack((predections, dets))
#print("predections:",predections)
#print("class %d predections.shape:" % cls_ind,dets.shape)
#dets = dets[0:20]
#dets[:, 4] = dets[:, 4] * 0.45
#dets[:,:] = predections[:,0:6]
#print("all predections.shape:",predections.shape)
order = predections[:, 5] > 0.5
predections = predections[order] # get score > 0.5
# print("score > 0.5 predections.shape:",predections.shape)
# print("result0:",predections)
# print("confidence : ",predections[:,5])
dets[:, 2] = dets[:, 2] / cfg.TEST.GT_MARGIN
dets[:, 3] = dets[:, 3] / cfg.TEST.GT_MARGIN
predections[:, 2] = predections[:, 2] / cfg.TEST.GT_MARGIN
predections[:, 3] = predections[:, 3] / cfg.TEST.GT_MARGIN
pre = predections[:, 0:6]
lab = predections[:, 6].astype(int).tolist()
#print(type(lab),lab)
# print("classes:",predections[:,6])
# print("labels:",CLASSES[lab[0]])
# print("result1:",predections)
# print("rato h/w : ",predections[:,3]/predections[:,2])
# print("rato w/h : ",predections[:,2]/predections[:,3])
#if imdb_name == "icdar13":
#write_result_ICDAR2013(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
#result_file = write_result_ICDAR2013(im_file, dets, CONF_THRESH, result_dir, im_height, im_width)
#print dets
#if imdb_name == "icdar15":
# write_result_ICDAR(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
results = write_result_ICDAR(im_file, pre, CONF_THRESH, result_dir,
im_height, im_width)
# write_result(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
# result_file = write_result(im_file, dets, CONF_THRESH, result_dir, im_height, im_width)
# print "write done"
# post_merge(result_file)
# print "merge done"
#
#print "merge done"
#vis_detections(im, cls, dets, gt_boxes, thresh=CONF_THRESH)
return results
def demo(net, image_name, gt_boxes, result_dir, ori_result_dir, conf = 0.75):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = image_name
im = cv2.imread(im_file)
im_height = im.shape[0]
im_width = im.shape[1]
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = r_im_detect(net, im)
print "gt_margin: ", cfg.TEST.GT_MARGIN, cfg.TRAIN.GT_MARGIN
print "img_padding: ", cfg.IMG_PADDING
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = conf
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 5*cls_ind:5*(cls_ind + 1)] # D
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = rotate_gpu_nms(dets, NMS_THRESH) # D
dets = dets[keep, :]
#dets = dets[0:20]
#dets[:, 4] = dets[:, 4] * 0.45
dets[:, 2] = dets[:, 2] / cfg.TEST.GT_MARGIN
dets[:, 3] = dets[:, 3] / cfg.TEST.GT_MARGIN
#if imdb_name == "icdar13":
#write_result_ICDAR2013(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
#result_file = write_result_ICDAR2013(im_file, dets, CONF_THRESH, result_dir, im_height, im_width)
#if imdb_name == "icdar15":
write_result_ICDAR(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
result_file = write_result_ICDAR(im_file, dets, CONF_THRESH, result_dir, im_height, im_width)
#write_result(im_file, dets, CONF_THRESH, ori_result_dir, im_height, im_width)
#result_file = write_result(im_file, dets, CONF_THRESH, result_dir, im_height, im_width)
print "write done"
#post_merge(result_file)
print "merge done"
#
#print "merge done"
#vis_detections(im, cls, dets, gt_boxes, thresh=CONF_THRESH)
return result_file