def demo(args, image_path):
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load image
image = cv2.imread(image_path)
# 4. detect
_labels, _scores, _coords = object_detector.predict(image)
# 5. draw bounding box on the image
for labels, scores, coords in zip(_labels, _scores, _coords):
cv2.rectangle(image, (int(coords[0]), int(coords[1])), (int(coords[2]), int(coords[3])), COLORS[labels % 3], 2)
cv2.putText(image, '{label}: {score:.3f}'.format(label=VOC_CLASSES[labels], score=scores), (int(coords[0]), int(coords[1])), FONT, 0.5, COLORS[labels % 3], 2)
# 6. visualize result
if args.display is True:
cv2.imshow('result', image)
cv2.waitKey(0)
# 7. write result
if args.save is True:
os.path.makedirs(args.output_dir, exists_ok=True)
path, _ = os.path.splitext(image_path)
cv2.imwrite(os.path.join(args.output_dir, path + '_result.jpg'), image)
def demo_file(args, imagelist,imagefile):
# 1. load the configure file
cfg_from_file(args.confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
args = parse_args()
for image_name in imagelist:
# 3. load image
image_path = os.path.join(imagefile,image_name)
image = cv2.imread(image_path)
# 4. detect
_labels, _scores, _coords = object_detector.predict(image)
# 5. draw bounding box on the image
for labels, scores, coords in zip(_labels, _scores, _coords):
cv2.rectangle(image, (int(coords[0]), int(coords[1])), (int(coords[2]), int(coords[3])), COLORS[labels % 3], 2)
cv2.putText(image, '{label}: {score:.3f}'.format(label=VOC_CLASSES[labels], score=scores), (int(coords[0]), int(coords[1])), FONT, 0.5, COLORS[labels % 3], 2)
# 6. visualize result
if args.display is True:
cv2.imshow('result', image)
cv2.waitKey(800)
'''
# 7. write result
# if args.save is True:
path = './'
path = os.path.join(path,image_name)
print(path)
#path, _ = os.path.splitext(image_path)
#print(path)
cv2.imwrite(path, image)
'''
'''
def time_benchmark(args, image_path):
# 1. load the configure file
cfg_from_file(args.confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load imagedemo
image = cv2.imread(image_path)
# 4. time test
warmup = 20
time_iter = 100
print('Warmup the detector...')
_t = list()
for i in range(warmup+time_iter):
_, _, _, (total_time, preprocess_time, net_forward_time, detect_time, output_time) \
= object_detector.predict(image, check_time=True)
if i > warmup:
_t.append([total_time, preprocess_time, net_forward_time, detect_time, output_time])
if i % 20 == 0:
print('In {}\{}, total time: {} \n preprocess: {} \n net_forward: {} \n detect: {} \n output: {}'.format(
i-warmup, time_iter, total_time, preprocess_time, net_forward_time, detect_time, output_time
))
total_time, preprocess_time, net_forward_time, detect_time, output_time = np.sum(_t, axis=0)/time_iter
print('In average, total time: {} \n preprocess: {} \n net_forward: {} \n detect: {} \n output: {}'.format(
total_time, preprocess_time, net_forward_time, detect_time, output_time
))
def demo(args, image_path):
# 1. load the configure file
cfg_from_file(args.confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load image
image = cv2.imread(image_path)
image256 = image[300:556]
# 4. detect
_labels, _scores, _coords = object_detector.predict(image256)
# 5. draw bounding box on the image
for labels, scores, coords in zip(_labels, _scores, _coords):
cv2.rectangle(image256, (int(coords[0]), int(coords[1])),
(int(coords[2]), int(coords[3])), COLORS[labels % 3], 2)
cv2.putText(
image256, '{label}: {score:.3f}'.format(label=VOC_CLASSES[labels],
score=scores),
(int(coords[0]), int(coords[1])), FONT, 0.5, COLORS[labels % 3], 2)
# 6. visualize result
if args.display is True:
cv2.imshow('result', image)
cv2.waitKey(0)
# 7. write result
if args.save is True:
# path, _ = os.path.splitext(image_path)
img_name = image_path.split("/")[-1]
cv2.imwrite(os.path.join(args.test_out_img_path, img_name), image)
def predict():
args = parse_args()
cfg_from_file(args.cfg)
detector = ObjectDetector()
img = cv2.imread(img_f)
_labels, _scores, _coords = detector.predict(img)
print('labels: {}\nscores: {}\ncoords: {}'.format(_labels, _scores, _coords))
def demo_live(args, video_path):
# 1. load the configure file
cfg_from_file(args.confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load video
video = cv2.VideoCapture(video_path)
index = -1
while (video.isOpened()):
index = index + 1
sys.stdout.write('Process image: {} \r'.format(index))
sys.stdout.flush()
# 4. read image
flag, image = video.read()
if flag == False:
print("Can not read image in Frame : {}".format(index))
break
# 5. detect
_labels, _scores, _coords = object_detector.predict(image,
threshold=0.6)
# 6. draw bounding box on the image
for labels, scores, coords in zip(_labels, _scores, _coords):
cv2.rectangle(image, (int(coords[0]), int(coords[1])),
(int(coords[2]), int(coords[3])), COLORS[labels % 3],
2)
cv2.putText(
image, '{label}: {score:.3f}'.format(label=VOC_CLASSES[labels],
score=scores),
(int(coords[0]), int(coords[1])), FONT, 0.5,
COLORS[labels % 3], 2)
# 7. visualize result
if args.display is True:
cv2.imshow('result', image)
cv2.waitKey(33)
# 8. write result
if args.save is True:
path, _ = os.path.splitext(video_path)
path = path + '_result'
if not os.path.exists(path):
os.mkdir(path)
cv2.imwrite(path + '/{}.jpg'.format(index), image)
def demo_live(args, video_path):
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load video
video = cv2.VideoCapture(video_path)
if args.save:
path = os.path.split(os.path.splitext(video_path)[0])[1]
output_path = os.path.join(cfg.EXP_DIR, args.output_dir, path + '_result')
if not os.path.exists(output_path):
os.makedirs(output_path)
index = -1
import time
total_time = 0
while(video.isOpened()):
index = index + 1
print('Process image: {} \r'.format(index))
# 4. read image
flag, image = video.read()
if flag == False:
print("Can not read image in Frame : {}".format(index))
break
if index < args.skip_count:
continue
# 5. detect
_labels, _scores, _coords, times = object_detector.predict(image, check_time=True)
total_time += times[-1]
# 6. draw bounding box on the image
for labels, scores, coords in zip(_labels, _scores, _coords):
cv2.rectangle(image, (int(coords[0]), int(coords[1])), (int(coords[2]), int(coords[3])), COLORS[labels % 3], 2)
cv2.putText(image, '{label}: {score:.3f}'.format(label=CONE_CLASSES[labels], score=scores), (int(coords[0]), int(coords[1])), FONT, 0.5, COLORS[labels % 3], 2)
# 7. visualize result
if args.display is True:
cv2.imshow('result', image)
cv2.waitKey(33)
# 8. write result
if args.save is True:
cv2.imwrite(output_path + '/{}.jpg'.format(index), image)
print("Post-process time", total_time / (index+1))
if args.save:
print("Images saved to", output_path)
def demo_video(args, video_path):
# 1. load the configure file
cfg_from_file(args.confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load video
video = cv2.VideoCapture(video_path)
index = -1
frametime10 = np.zeros((10,1))
while(video.isOpened()):
#sys.stdout.write('Process image: {} \r'.format(index))
#sys.stdout.flush()
# 4. read image
flag, image = video.read()
t0 = timeit.default_timer()
if flag == False:
#print("Can not read image in Frame : {}".format(index))
break
# 5. detect
_labels, _scores, _coords,elapsed = object_detector.predict(image)
# 6. draw bounding box on the image
for labels, scores, coords in zip(_labels, _scores, _coords):
cv2.rectangle(image, (int(coords[0]), int(coords[1])), (int(coords[2]), int(coords[3])), COLORS[labels % 3], 5)
cv2.putText(image, '{label}: {score:.3f}'.format(label=VOC_CLASSES[labels], score=scores), (int(coords[0]), int(coords[1])), FONT, 0.5, COLORS[labels % 3], 2)
#print(elapsed)
index = index + 1
index = index%10
#frametime10[index] = elapsed
#fps = 1/np.average(frametime10)
fps = 1/elapsed
cv2.putText(image, '{fps:%.5s}'%(fps), (int(50), int(50)), FONT, 2,COLORS[1])
#print(fps)
# 7. visualize result
if args.display is True:
image = cv2.resize(image,(540,960))
cv2.imshow('result', image)
key = cv2.waitKey(1) & 0xFF
if key==ord("q"):
break
video.close()
if key==ord("s"):
key2 = cv2.waitKey(0)
def demo_live(args, video_path):
# 1. load the configure file
cfg_from_file(args.confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load video
cam = cv2.VideoCapture(0)
#cam.set(cv2.CAP_PROP_FRAME_HEIGHT,1080)
#cam.set(cv2.CAP_PROP_FRAME_WIDTH,1920)frametime10
index = -1
frametime20 = np.zeros((100,1))
index = 0
while True:
#index = index + 1
#sys.stdout.write('Process image: {} \r'.format(index))
#sys.stdout.flush()
# 4. read image
#flag, image = video.read()
retval,image = cam.read()
#
#image = cv2.resize(image,(192,108))
#image = image[270:270+540,480:480+540,:]
print(image.shape)
if retval == False:
print("Can not read image in Frame : {}".format(index))
break
t0 = timeit.default_timer()
# 5. detect
_labels, _scores, _coords = object_detector.predict(image)
# 6. draw bounding box on the image
for labels, scores, coords in zip(_labels, _scores, _coords):
cv2.rectangle(image, (int(coords[0]), int(coords[1])), (int(coords[2]), int(coords[3])), COLORS[labels % 3], 2)
cv2.putText(image, '{label}: {score:.3f}'.format(label=VOC_frametime10CLASSES[labels], score=scores), (int(coords[0]), int(coords[1])), FONT, 0.5, COLORS[labels % 3], 2)
elapsed = timeit.default_timer() - t0
frametime20[index] = elapsed
index = index+1
index = index%100
print(elapsed)
# 7. visualize result
cv2.imshow('result', image)
cv2.waitKey(1)
'''
def demo_live(confg_file, index):
# 1. load the configure file
cfg_from_file(confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
# 3. load video
state = "init"
cam = cv2.VideoCapture(0)
points = []
record_points = []
count_frames = 0
all_count = 0
success_count = 0
circle_radius = 20
line_thickness = 16
close_distance = 20
wait_frames = 10
font_scale = 1
font_thickness = 2
middle_state = False
middle_frame = 0
bias = 50
t = 0
while True:
retval, frame = cam.read()
img_h, img_w, c = frame.shape
s_y = int((1080 - img_h) / 2)
s_x = int((1920 - img_w) / 2)
bg_image = np.full((1080, 1920, 3), 127, np.uint8)
bg_image[s_y:s_y + img_h, s_x:s_x + img_w] = frame
frame = bg_image[:,
int(1920 * (1 - CROP_RATE) /
2):int(1920 * (1 + CROP_RATE) / 2)]
frame = cv2.flip(frame, 1)
show_img = np.copy(frame)
if state == "init":
points = random_point(
s_x - int(1920 * (1 - CROP_RATE) / 2) + bias,
s_x + img_w - int(1920 * (1 - CROP_RATE) / 2) - bias,
s_y + bias, s_y + img_h - bias)
print("points:", points)
# input()
state = "waiting"
for i in range(len(points) - 1):
cv2.line(show_img, (points[i][0], points[i][1]),
(points[i + 1][0], points[i + 1][1]), (255, 0, 0),
line_thickness)
cv2.circle(show_img, tuple(points[0]), circle_radius, (0, 255, 0), -1)
cv2.circle(show_img, tuple(points[-1]), circle_radius, (0, 0, 255), -1)
for i in range(1, len(points) - 1):
cv2.circle(show_img, tuple(points[i]), circle_radius,
(255, 0, 255), -1)
_labels, _scores, _coords = object_detector.predict(frame)
hands_points = []
for labels, scores, coords in zip(_labels, _scores, _coords):
tmp_x = int((coords[0] + coords[2]) / 2)
tmp_y = int((coords[1] + coords[3]) / 2)
cv2.circle(show_img, (tmp_x, tmp_y), circle_radius, (0, 255, 255),
-1)
hands_points.append([tmp_x, tmp_y])
if state == "waiting":
if count_frames > wait_frames:
state = "Recording"
t = time.time()
count_frames = 0
has_found = False
for h_point in hands_points:
if np.sqrt((h_point[0] - points[0][0])**2 +
(h_point[1] - points[0][1])**2) < close_distance:
has_found = True
count_frames += 1
if has_found == False:
count_frames = 0
if state == "Recording":
record_points.append(hands_points)
cv2.putText(show_img, "Recording", (10, 150),
cv2.FONT_HERSHEY_COMPLEX, font_scale, (0, 0, 255),
font_thickness)
if middle_frame > wait_frames:
middle_state = True
record_points.append("Middle")
middle_frame = 0
if middle_state:
cv2.circle(show_img, tuple(points[1]), circle_radius,
(0, 255, 0), -1)
if count_frames > wait_frames:
state = "init"
print("----------------")
if len(points) == 3:
if judge(record_points, points) and middle_state:
success_count += 1
print("yes")
else:
print("no")
else:
if judge(record_points, points):
success_count += 1
print("yes")
else:
print("no")
all_count += 1
count_frames = 0
middle_frame = 0
middle_state = False
print("{}:{}".format("time", time.time() - t))
record_points = []
has_found = False
middle_found = False
for h_point in hands_points:
if np.sqrt((h_point[0] - points[-1][0])**2 +
(h_point[1] - points[-1][1])**2) < close_distance:
has_found = True
count_frames += 1
if len(points) > 2 and middle_state is False and np.sqrt(
(h_point[0] - points[1][0])**2 +
(h_point[1] - points[1][1])**2) < close_distance:
middle_frame += 1
middle_found = True
if not has_found:
count_frames = 0
if not middle_found:
middle_frame = 0
cv2.putText(show_img, "Result:{}/{}".format(success_count, all_count),
(10, 50), cv2.FONT_HERSHEY_COMPLEX, font_scale,
(0, 0, 255), font_thickness)
cv2.putText(show_img, "{} {}".format(state, count_frames), (10, 100),
cv2.FONT_HERSHEY_COMPLEX, font_scale, (0, 0, 255),
font_thickness)
cv2.imshow("Frame", show_img)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
def inference_img_dir(args, imgs_dir):
if args.save:
infer_key = imgs_dir.split("/")[-1].replace("/", "")
model_name = args.confg_file.split("/")[-1].replace(".yml", "")
test_img_rdir = os.path.join(args.save, infer_key)
test_model_rdir = os.path.join(args.save, infer_key, model_name)
test_out_img_path = os.path.join(args.save, infer_key, model_name,
"det_imgs")
pred_out_txt = os.path.join(args.save, infer_key, model_name,
"pred_txt")
model_save_path = os.path.join(args.save, infer_key, model_name,
"model")
if not os.path.exists(test_img_rdir):
os.mkdir(test_img_rdir)
if not os.path.exists(test_model_rdir):
os.mkdir(test_model_rdir)
if not os.path.exists(test_out_img_path):
os.mkdir(test_out_img_path)
if not os.path.exists(pred_out_txt):
os.mkdir(pred_out_txt)
if not os.path.exists(model_save_path):
os.mkdir(model_save_path)
# 1. load the configure file
cfg_from_file(args.confg_file)
# 2. load detector based on the configure file
object_detector = ObjectDetector()
for idx, img in enumerate(os.listdir(imgs_dir)):
image_path = os.path.join(imgs_dir, img)
# 3. load image
image = cv2.imread(image_path)
image256 = image[300:556]
# 4. detect
_labels, _scores, _coords = object_detector.predict(image256)
# 5. draw bounding box on the image
cxyl, stl, edl = [], [], []
for label, score, coords in zip(_labels, _scores, _coords):
xmin, ymin, xmax, ymax = [
int(round(i)) for i in coords.cpu().numpy()
]
cx = int(round((xmin + xmax) / 2))
cy = int(round((ymin + ymax) / 2))
min_d = min(xmax - xmin, ymax - ymin)
if score >= 0.45:
if label == 0:
cxyl.append([(cx, cy),
[[xmin, ymin], [xmin, ymax], [xmax, ymax],
[xmax, ymin]]])
cv2.circle(image256, (cx, cy), int(min_d / 4), (0, 0, 255),
2)
# cv2.rectangle(img,(xmin, ymin),(xmax, ymax),(0, 255, 255))
if score >= 0.45:
if label == 1:
stl.append((cx, cy))
# cv2.circle(image256, (cx, cy), 5, (255, 0, 0), 2)
# elif label == 2:
# cv2.circle(image256, (cx, cy), 5, (0, 255, 0), 2)
# cv2.line(img, (xmin, ymin), (xmax, ymax), (155, 155, 155), 2)
# cv2.line(image256, (xmin + 20, ymin + 20), (xmax - 20, ymax - 20), (0, 255, 0), 2)
# elif label == 4:
# # cv2.line(img, (xmin, ymin), (xmax, ymax), (0, 155, 155), 2)
# cv2.line(image256, (xmin + 20, ymin + 20), (xmax - 20, ymax - 20), (0, 155, 155), 2)
# elif label == 5:
# cv2.circle(img256, (cx, cy), 5, (255, 255, 0))
# cv2.rectangle(image256, (int(coords[0]), int(coords[1])), (int(coords[2]), int(coords[3])),
# COLORS[labels % 3], 2)
# cv2.putText(image256, '{label}: {score:.3f}'.format(label=VOC_CLASSES[labels], score=scores),
# (int(coords[0]), int(coords[1])), FONT, 0.5, COLORS[labels % 3], 2)
for idx2, cxyp in enumerate(cxyl):
dis = []
for idx1, stp in enumerate(stl):
tdis = cv2.pointPolygonTest(np.array(cxyp[-1]), stp, True)
tdis = float("inf") if tdis < 0 else tdis
tdis2 = np.linalg.norm(np.array(stp) - np.array(cxyp[0]))
dis.append(tdis + tdis2)
idx = np.argmin(dis)
# if cv2.pointPolygonTest(np.array(cxyp[-1]), stp, True):
cv2.arrowedLine(image256, stl[idx], cxyp[0], (0, 0, 255))
# 6. visualize result
if args.display is True:
cv2.imshow('result', image)
cv2.waitKey(0)
# 7. write result
if args.save is not None:
# path, _ = os.path.splitext(image_path)
img_name = image_path.split("/")[-1]
cv2.imwrite(os.path.join(test_out_img_path, img_name), image)
print("save img:", img_name)