class FaceDetection:
'''
Class for the Face Detection Model.
'''
def __init__(self, model_name, device='CPU', extensions=None):
self.model_weights = model_name + '.bin'
self.model_structure = model_name + '.xml'
self.device = device
self.extensions = extensions
try:
self.model = IENetwork(self.model_structure, self.model_weights)
except Exception as e:
raise ValueError(
"Could not Initialise the network. Have you enterred the correct model path?"
)
self.input_name = next(iter(self.model.inputs))
self.input_shape = self.model.inputs[self.input_name].shape
self.output_name = next(iter(self.model.outputs))
self.output_shape = self.model.outputs[self.output_name].shape
def load_model(self):
self.net = IECore().load_network(network=self.model,
device_name=self.device,
num_requests=1)
def predict(self, image):
self.preprocess_image = self.preprocess_input(np.copy(image))
self.net.start_async(request_id=0,
inputs={self.input_name: self.preprocess_image})
if self.net.requests[0].wait(-1) == 0:
outputs = self.net.requests[0].outputs
face_image = self.preprocess_output(outputs, image)
return face_image
def preprocess_input(self, image):
image = cv2.resize(image, (self.input_shape[3], self.input_shape[2]))
image = image.transpose((2, 0, 1))
image = image.reshape(1, *image.shape)
return image
def preprocess_output(self, outputs, image):
box = outputs[self.output_name][0][0][0]
xmin = int(box[3] * image.shape[1])
ymin = int(box[4] * image.shape[0])
xmax = int(box[5] * image.shape[1])
ymax = int(box[6] * image.shape[0])
return image[ymin:ymax, xmin:xmax]
class HeadPose:
'''
Class for the Head Pose Estimation Model.
'''
def __init__(self, model_name, device='CPU', extensions=None):
self.model_weights = model_name + '.bin'
self.model_structure = model_name + '.xml'
self.device = device
self.extensions = extensions
try:
self.model = IENetwork(self.model_structure, self.model_weights)
except Exception as e:
raise ValueError(
"Could not Initialise the network. Have you enterred the correct model path?"
)
self.input_name = next(iter(self.model.inputs))
self.input_shape = self.model.inputs[self.input_name].shape
self.output_name = next(iter(self.model.outputs))
self.output_shape = self.model.outputs[self.output_name].shape
def load_model(self):
self.net = IECore().load_network(network=self.model,
device_name=self.device,
num_requests=1)
def predict(self, image):
self.preprocess_image = self.preprocess_input(np.copy(image))
self.net.start_async(request_id=0,
inputs={self.input_name: self.preprocess_image})
if self.net.requests[0].wait(-1) == 0:
outputs = self.net.requests[0].outputs
yaw, pitch, roll = self.preprocess_output(outputs)
return [[yaw, pitch, roll]]
def preprocess_input(self, image):
image = cv2.resize(image, (self.input_shape[3], self.input_shape[2]))
image = image.transpose((2, 0, 1))
image = image.reshape(1, *image.shape)
return image
def preprocess_output(self, outputs):
return outputs['angle_y_fc'], outputs['angle_p_fc'], outputs[
'angle_r_fc']
class GazeEstimation:
'''
Class for the Head Pose Estimation Model.
'''
def __init__(self, model_name, device='CPU', extensions=None):
self.model_weights=model_name+'.bin'
self.model_structure=model_name+'.xml'
self.device=device
self.extensions=extensions
try:
self.model=IENetwork(self.model_structure, self.model_weights)
except Exception as e:
raise ValueError("Could not Initialise the network. Have you enterred the correct model path?")
self.input_name=list(self.model.inputs.keys())
self.input_shape = self.model.inputs['left_eye_image'].shape
self.output_name=next(iter(self.model.outputs))
self.output_shape=self.model.outputs[self.output_name].shape
def load_model(self):
self.net = IECore().load_network(network = self.model, device_name = self.device,num_requests=1)
def predict(self, left_eye_image,right_eye_image,head_pose_angles):
self.preprocess_left_eye_image = self.preprocess_input(np.copy(left_eye_image))
self.preprocess_right_eye_image = self.preprocess_input(np.copy(right_eye_image))
self.head_pose_angles = head_pose_angles
self.net.start_async(request_id=0, inputs={'head_pose_angles': self.head_pose_angles,\
'left_eye_image': self.preprocess_left_eye_image,\
'right_eye_image': self.preprocess_right_eye_image})
if self.net.requests[0].wait(-1) == 0:
outputs = self.net.requests[0].outputs
outputs = self.preprocess_output(outputs)
return outputs
def preprocess_input(self, image):
image = cv2.resize(image, (self.input_shape[3], self.input_shape[2]))
image = image.transpose((2,0,1))
image = image.reshape(1, *image.shape)
return image
def preprocess_output(self, outputs):
return outputs[self.output_name].squeeze()
def main():
log.basicConfig(format="[ %(levelname)s ] %(message)s",
level=log.INFO,
stream=sys.stdout)
args = build_argparser().parse_args()
model_xml = args.model
model_bin = os.path.splitext(model_xml)[0] + ".bin"
# Plugin initialization for specified device and load extensions library if specified
log.info("Initializing plugin for {} device...".format(args.device))
#plugin = IEPlugin(device=args.device, plugin_dirs=args.plugin_dir)
#if args.cpu_extension and 'CPU' in args.device:
# plugin.add_cpu_extension(args.cpu_extension)
# Read IR
log.info("Reading IR...")
net = IECore().read_network(model=model_xml, weights=model_bin)
if "CPU" in args.device:
supported_layers = IECore().query_network(net, "CPU")
not_supported_layers = [
l for l in net.layers.keys() if l not in supported_layers
]
if len(not_supported_layers) != 0:
log.error(
"Following layers are not supported by the plugin for specified device {}:\n {}"
.format(args.device, ', '.join(not_supported_layers)))
log.error(
"Please try to specify cpu extensions library path in demo's command line parameters using -l "
"or --cpu_extension command line argument")
sys.exit(1)
assert len(
net.inputs.keys()) == 1, "Demo supports only single input topologies"
assert len(net.outputs) == 1, "Demo supports only single output topologies"
input_blob = next(iter(net.inputs))
out_blob = next(iter(net.outputs))
#Added here
input_blob2 = next(iter(net.inputs))
out_blob2 = next(iter(net.outputs))
log.info("Loading IR to the plugin...")
exec_net = IECore().load_network(network=net,
device_name=args.device,
num_requests=2)
# Read and pre-process input image
n, c, h, w = net.inputs[input_blob].shape
#Added here
n2, c2, h2, w2 = net.inputs[input_blob2].shape
del net
#added from here
if args.input == 'cam':
input_stream = 0
elif args.input == 'gstreamer':
#gst rtp sink
input_stream = 'udpsrc port=5000 caps = " application/x-rtp, encoding-name=JPEG,payload=26" ! rtpjpegdepay ! decodebin ! videoconvert ! appsink'
else:
input_stream = args.input
assert os.path.isfile(args.input), "Specified input file doesn't exist"
if args.labels:
with open(args.labels, 'r') as f:
labels_map = [x.strip() for x in f]
else:
labels_map = None
if input_stream == 'gstreamer':
cap = cv2.VideoCapture(input_stream, cv2.CAP_GSTREAMER)
else:
cap = cv2.VideoCapture(input_stream)
if args.input2 == 'cam':
input_stream2 = 0
elif args.input2 == 'gstreamer':
#gst rtp sink
input_stream2 = 'udpsrc port=5001 caps = " application/x-rtp, encoding-name=JPEG,payload=26" ! rtpjpegdepay ! decodebin ! videoconvert ! appsink'
else:
input_stream2 = args.input2
assert os.path.isfile(
args.input2), "Specified input file doesn't exist"
if args.labels:
with open(args.labels, 'r') as f:
labels_map = [x.strip() for x in f]
else:
labels_map = None
if input_stream2 == 'gstreamer':
cap2 = cv2.VideoCapture(input_stream2, cv2.CAP_GSTREAMER)
else:
cap2 = cv2.VideoCapture(input_stream2)
cur_request_id = 0
next_request_id = 1
#Added here
cur_request_id2 = 1
next_request_id2 = 0
log.info("Starting inference in async mode...")
log.info("To switch between sync and async modes press Tab button")
log.info("To stop the demo execution press Esc button")
#Async doesn't work if True
#Request issues = Runtime Error: [REQUEST BUSY]
is_async_mode = False
render_time = 0
ret, frame = cap.read()
ret2, frame2 = cap2.read()
#Montage width and height
#In this case means 2x1 boxes
mW = 2
mH = 1
frameList = []
print(
"To close the application, press 'CTRL+C' or any key with focus on the output window"
)
while cap.isOpened() or cap2.isOpened():
if is_async_mode:
ret, next_frame = cap.read()
ret2, next_frame2 = cap2.read()
else:
ret, frame = cap.read()
ret2, frame2 = cap2.read()
if (not (ret and ret2)):
break
initial_w = cap.get(3)
initial_h = cap.get(4)
initial_w2 = cap2.get(3)
initial_h2 = cap2.get(4)
# Main sync point:
# in the truly Async mode we start the NEXT infer request, while waiting for the CURRENT to complete
# in the regular mode we start the CURRENT request and immediately wait for it's completion
inf_start = time.time()
if is_async_mode:
if (ret and ret2):
in_frame = cv2.resize(next_frame, (w, h))
in_frame = in_frame.transpose(
(2, 0, 1)) # Change data layout from HWC to CHW
in_frame = in_frame.reshape((n, c, h, w))
exec_net.start_async(request_id=next_request_id,
inputs={input_blob: in_frame})
in_frame2 = cv2.resize(next_frame2, (w2, h2))
in_frame2 = in_frame2.transpose(
(2, 0, 1)) # Change data layout from HWC to CHW
in_frame2 = in_frame2.reshape((n2, c2, h2, w2))
exec_net.start_async(request_id=next_request_id2,
inputs={input_blob2: in_frame2})
else:
if (ret and ret2):
in_frame = cv2.resize(frame, (w, h))
in_frame = in_frame.transpose(
(2, 0, 1)) # Change data layout from HWC to CHW
in_frame = in_frame.reshape((n, c, h, w))
exec_net.start_async(request_id=cur_request_id,
inputs={input_blob: in_frame})
in_frame2 = cv2.resize(frame2, (w2, h2))
in_frame2 = in_frame2.transpose(
(2, 0, 1)) # Change data layout from HWC to CHW
in_frame2 = in_frame2.reshape((n2, c2, h2, w2))
exec_net.start_async(request_id=cur_request_id2,
inputs={input_blob2: in_frame2})
if exec_net.requests[cur_request_id].wait(
-1) == 0 and exec_net.requests[cur_request_id2].wait(-1) == 0:
inf_end = time.time()
det_time = inf_end - inf_start
# Parse detection results of the current request
res = exec_net.requests[cur_request_id].outputs[out_blob]
res2 = exec_net.requests[cur_request_id2].outputs[out_blob2]
for obj in res[0][0]:
# Draw only objects when probability more than specified threshold
if obj[2] > args.prob_threshold:
xmin = int(obj[3] * initial_w)
ymin = int(obj[4] * initial_h)
xmax = int(obj[5] * initial_w)
ymax = int(obj[6] * initial_h)
class_id = int(obj[1])
# Draw box and label\class_id
color = (min(class_id * 12.5,
255), min(class_id * 7,
255), min(class_id * 5, 255))
cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), color, 2)
det_label = labels_map[class_id] if labels_map else str(
class_id)
cv2.putText(
frame,
det_label + ' ' + str(round(obj[2] * 100, 1)) + ' %',
(xmin, ymin - 7), cv2.FONT_HERSHEY_COMPLEX, 0.6, color,
1)
for obj in res2[0][0]:
# Draw only objects when probability more than specified threshold
if obj[2] > args.prob_threshold:
xmin = int(obj[3] * initial_w2)
ymin = int(obj[4] * initial_h2)
xmax = int(obj[5] * initial_w2)
ymax = int(obj[6] * initial_h2)
class_id = int(obj[1])
# Draw box and label\class_id
color = (min(class_id * 12.5,
255), min(class_id * 7,
255), min(class_id * 5, 255))
cv2.rectangle(frame2, (xmin, ymin), (xmax, ymax), color, 2)
det_label = labels_map[class_id] if labels_map else str(
class_id)
cv2.putText(
frame2,
det_label + ' ' + str(round(obj[2] * 100, 1)) + ' %',
(xmin, ymin - 7), cv2.FONT_HERSHEY_COMPLEX, 0.6, color,
1)
# Draw performance stats
inf_time_message = "Inference time: N\A for async mode" if is_async_mode else \
"Inference time: {:.3f} ms".format(det_time * 1000)
render_time_message = "OpenCV rendering time: {:.3f} ms".format(
render_time * 1000)
async_mode_message = "Async mode is on. Processing request {}".format(cur_request_id) if is_async_mode else \
"Async mode is off. Processing request {}".format(cur_request_id)
cv2.putText(frame, inf_time_message, (15, 15),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (200, 10, 10), 1)
cv2.putText(frame, render_time_message, (15, 30),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
cv2.putText(frame, async_mode_message, (10, int(initial_h - 20)),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
cv2.putText(frame2, inf_time_message, (15, 15),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (200, 10, 10), 1)
cv2.putText(frame2, render_time_message, (15, 30),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
cv2.putText(frame2, async_mode_message, (10, int(initial_h - 20)),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
render_start = time.time()
#Added here
#Add the frame into a list
if (ret and ret2):
frameList.append(frame)
frameList.append(frame2)
#build_montages function from imutils to display 2 cameras on a single dashboard
montages = build_montages(frameList, (640, 480), (mW, mH))
for montage in montages:
cv2.imshow("Detection results", montage)
#cv2.imshow("Detection Results", frame)
render_end = time.time()
render_time = render_end - render_start
if is_async_mode:
cur_request_id, next_request_id = next_request_id, cur_request_id
frame = next_frame
frame2 = next_frame2
key = cv2.waitKey(1)
if key == 27:
break
if (9 == key):
is_async_mode = not is_async_mode
log.info("Switched to {} mode".format(
"async" if is_async_mode else "sync"))
cap.release()
cap2.release()
cv2.destroyAllWindows()
class PersonDetect:
'''
Class for the Person Detection Model.
'''
def __init__(self, model_name, device, threshold=0.60):
self.model_weights = model_name + '.bin'
self.model_structure = model_name + '.xml'
self.device = device
self.threshold = threshold
try:
self.model = IENetwork(self.model_structure, self.model_weights)
except Exception as e:
raise ValueError(
"Could not Initialise the network. Have you enterred the correct model path?"
)
self.input_name = next(iter(self.model.inputs))
self.input_shape = self.model.inputs[self.input_name].shape
self.output_name = next(iter(self.model.outputs))
self.output_shape = self.model.outputs[self.output_name].shape
def load_model(self):
self.net = IECore().load_network(network=self.model,
device_name=self.device)
def predict(self, image):
processed_image = self.preprocess_inputs(image)
self.net.start_async(0, inputs={self.input_name: processed_image})
if self.net.requests[0].wait() == 0:
result = self.net.requests[0].outputs[self.output_name]
outputs = self.preprocess_outputs(result, image)
image = self.draw_outputs(outputs, image)
return outputs, image
def draw_outputs(self, coords, image):
frame = image.copy()
for data in coords:
cv2.rectangle(frame, data[:2], data[2:], (0, 255, 0), 2)
return frame
def preprocess_outputs(self, outputs, image):
h, w = image.shape[0:2]
coords = []
for data in outputs[0][0]:
# Draw bounding box for object
if data[2] >= self.threshold:
xmin = int(data[3] * w)
ymin = int(data[4] * h)
xmax = int(data[5] * w)
ymax = int(data[6] * h)
coords.append((xmin, ymin, xmax, ymax))
return coords
def preprocess_inputs(self, image):
p_frame = cv2.resize(image, (self.input_shape[3], self.input_shape[2]))
p_frame = p_frame.transpose(2, 0, 1)
p_frame = p_frame.reshape(1, *p_frame.shape)
return p_frame