def prepare_net(self):
inputs = cv2.GInferInputs()
g_inputs = []
for input_name in self.inputs:
if input_name in self.const_inputs:
continue
g_in = cv2.GMat()
inputs.setInput(input_name, g_in)
g_inputs.append(g_in)
outputs = cv2.gapi.infer("net", inputs)
g_outputs = [outputs.at(out_name) for out_name in self.output_names]
self.comp = cv2.GComputation(cv2.GIn(*g_inputs), cv2.GOut(*g_outputs))
args = ['net', str(self.model)]
if self.weights is not None:
args.append(str(self.weights))
args.append(self.device.upper())
if self.backend == 'ie':
pp = cv2.gapi.ie.params(*args)
else:
pp = cv2.gapi.mx.params('net', str(self.model))
for input_name, value in self._const_inputs.items():
pp.constInput(input_name, value)
if self.backend == 'ie':
self.network_args = compile_args(cv2.gapi.networks(pp))
else:
mvcmd_file = os.environ.get('MVCMD_FILE', '')
self.network_args = compile_args(
cv2.gapi.networks(pp), cv2.gapi_mx_mvcmdFile(mvcmd_file)
)
def test_age_gender_infer_roi_list(self):
# NB: Check IE
if not cv.dnn.DNN_TARGET_CPU in cv.dnn.getAvailableTargets(
cv.dnn.DNN_BACKEND_INFERENCE_ENGINE):
return
root_path = '/omz_intel_models/intel/age-gender-recognition-retail-0013/FP32/age-gender-recognition-retail-0013'
model_path = self.find_file(
root_path + '.xml',
[os.environ.get('OPENCV_DNN_TEST_DATA_PATH')])
weights_path = self.find_file(
root_path + '.bin',
[os.environ.get('OPENCV_DNN_TEST_DATA_PATH')])
device_id = 'CPU'
rois = [(10, 15, 62, 62), (23, 50, 62, 62), (14, 100, 62, 62),
(80, 50, 62, 62)]
img_path = self.find_file(
'cv/face/david2.jpg',
[os.environ.get('OPENCV_TEST_DATA_PATH')])
img = cv.imread(img_path)
# OpenCV DNN
dnn_age_list = []
dnn_gender_list = []
for roi in rois:
age, gender = self.infer_reference_network(
model_path, weights_path, self.make_roi(img, roi))
dnn_age_list.append(age)
dnn_gender_list.append(gender)
# OpenCV G-API
g_in = cv.GMat()
g_rois = cv.GArrayT(cv.gapi.CV_RECT)
inputs = cv.GInferInputs()
inputs.setInput('data', g_in)
outputs = cv.gapi.infer("net", g_rois, inputs)
age_g = outputs.at("age_conv3")
gender_g = outputs.at("prob")
comp = cv.GComputation(cv.GIn(g_in, g_rois),
cv.GOut(age_g, gender_g))
pp = cv.gapi.ie.params("net", model_path, weights_path, device_id)
gapi_age_list, gapi_gender_list = comp.apply(
cv.gin(img, rois),
args=cv.gapi.compile_args(cv.gapi.networks(pp)))
# Check
for gapi_age, gapi_gender, dnn_age, dnn_gender in zip(
gapi_age_list, gapi_gender_list, dnn_age_list,
dnn_gender_list):
self.assertEqual(0.0,
cv.norm(dnn_gender, gapi_gender, cv.NORM_INF))
self.assertEqual(0.0, cv.norm(dnn_age, gapi_age, cv.NORM_INF))
def test_age_gender_infer(self):
# NB: Check IE
if not cv.dnn.DNN_TARGET_CPU in cv.dnn.getAvailableTargets(
cv.dnn.DNN_BACKEND_INFERENCE_ENGINE):
return
root_path = '/omz_intel_models/intel/age-gender-recognition-retail-0013/FP32/age-gender-recognition-retail-0013'
model_path = self.find_file(
root_path + '.xml', [os.environ.get('OPENCV_DNN_TEST_DATA_PATH')])
weights_path = self.find_file(
root_path + '.bin', [os.environ.get('OPENCV_DNN_TEST_DATA_PATH')])
img_path = self.find_file('cv/face/david2.jpg',
[os.environ.get('OPENCV_TEST_DATA_PATH')])
device_id = 'CPU'
img = cv.resize(cv.imread(img_path), (62, 62))
# OpenCV DNN
net = cv.dnn.readNetFromModelOptimizer(model_path, weights_path)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_INFERENCE_ENGINE)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
blob = cv.dnn.blobFromImage(img)
net.setInput(blob)
dnn_age, dnn_gender = net.forward(net.getUnconnectedOutLayersNames())
# OpenCV G-API
g_in = cv.GMat()
inputs = cv.GInferInputs()
inputs.setInput('data', g_in)
outputs = cv.gapi.infer("net", inputs)
age_g = outputs.at("age_conv3")
gender_g = outputs.at("prob")
comp = cv.GComputation(cv.GIn(g_in), cv.GOut(age_g, gender_g))
pp = cv.gapi.ie.params("net", model_path, weights_path, device_id)
nets = cv.gapi.networks(pp)
args = cv.compile_args(nets)
gapi_age, gapi_gender = comp.apply(cv.gin(img),
args=cv.compile_args(
cv.gapi.networks(pp)))
# Check
self.assertEqual(0.0, cv.norm(dnn_gender, gapi_gender, cv.NORM_INF))
self.assertEqual(0.0, cv.norm(dnn_age, gapi_age, cv.NORM_INF))
def test_person_detection_retail_0013(self):
# NB: Check IE
if not cv.dnn.DNN_TARGET_CPU in cv.dnn.getAvailableTargets(
cv.dnn.DNN_BACKEND_INFERENCE_ENGINE):
return
root_path = '/omz_intel_models/intel/person-detection-retail-0013/FP32/person-detection-retail-0013'
model_path = self.find_file(
root_path + '.xml', [os.environ.get('OPENCV_DNN_TEST_DATA_PATH')])
weights_path = self.find_file(
root_path + '.bin', [os.environ.get('OPENCV_DNN_TEST_DATA_PATH')])
img_path = self.find_file('gpu/lbpcascade/er.png',
[os.environ.get('OPENCV_TEST_DATA_PATH')])
device_id = 'CPU'
img = cv.resize(cv.imread(img_path), (544, 320))
# OpenCV DNN
net = cv.dnn.readNetFromModelOptimizer(model_path, weights_path)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_INFERENCE_ENGINE)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
blob = cv.dnn.blobFromImage(img)
def parseSSD(detections, size):
h, w = size
bboxes = []
detections = detections.reshape(-1, 7)
for sample_id, class_id, confidence, xmin, ymin, xmax, ymax in detections:
if confidence >= 0.5:
x = int(xmin * w)
y = int(ymin * h)
width = int(xmax * w - x)
height = int(ymax * h - y)
bboxes.append((x, y, width, height))
return bboxes
net.setInput(blob)
dnn_detections = net.forward()
dnn_boxes = parseSSD(np.array(dnn_detections), img.shape[:2])
# OpenCV G-API
g_in = cv.GMat()
inputs = cv.GInferInputs()
inputs.setInput('data', g_in)
g_sz = cv.gapi.streaming.size(g_in)
outputs = cv.gapi.infer("net", inputs)
detections = outputs.at("detection_out")
bboxes = cv.gapi.parseSSD(detections, g_sz, 0.5, False, False)
comp = cv.GComputation(cv.GIn(g_in), cv.GOut(bboxes))
pp = cv.gapi.ie.params("net", model_path, weights_path, device_id)
gapi_boxes = comp.apply(cv.gin(img.astype(np.float32)),
args=cv.compile_args(cv.gapi.networks(pp)))
# Comparison
self.assertEqual(
0.0,
cv.norm(
np.array(dnn_boxes).flatten(),
np.array(gapi_boxes).flatten(), cv.NORM_INF))
for i in range(size):
for st in eyesl[i]:
out_l_st += [1 if st[0] < st[1] else 0]
for st in eyesr[i]:
out_r_st += [1 if st[0] < st[1] else 0]
return out_l_st, out_r_st
if __name__ == '__main__':
ARGUMENTS = build_argparser().parse_args()
# ------------------------Demo's graph------------------------
g_in = cv.GMat()
# Detect faces
face_inputs = cv.GInferInputs()
face_inputs.setInput('data', g_in)
face_outputs = cv.gapi.infer('face-detection', face_inputs)
faces = face_outputs.at('detection_out')
# Parse faces
sz = cv.gapi.streaming.size(g_in)
faces_rc = cv.gapi.parseSSD(faces, sz, 0.5, False, False)
# Detect poses
head_inputs = cv.GInferInputs()
head_inputs.setInput('data', g_in)
face_outputs = cv.gapi.infer('head-pose', faces_rc, head_inputs)
angles_y = face_outputs.at('angle_y_fc')
angles_p = face_outputs.at('angle_p_fc')
angles_r = face_outputs.at('angle_r_fc')