def gen_sim_matrix(x_files, y_files):
# Get a combined list of the skeleton files chosen earlier
combined_files = x_files + y_files
# Initializing the similarity matrix to be used for final comparison
s_matrix = np.zeros(len(combined_files)**2).reshape(
len(combined_files), len(combined_files))
# Populating the similarity matrix with distance outputs from DTW
for i, file_i in enumerate(combined_files):
sk_i = Skeleton(file_i)
sk_i.load()
sk_i.normalize('spine-base')
for j, file_j in enumerate(combined_files):
sk_j = Skeleton(file_j)
sk_j.load()
sk_j.normalize('spine-base')
dist, cost, acc, path = dtw(
sk_i.data, sk_j.data, dist=lambda a, b: np.linalg.norm(a - b))
s_matrix[i, j] = dist
return s_matrix
def main():
service_name = 'GestureRecognizer.Recognition'
log = Logger(name=service_name)
op = load_options()
channel = Channel(op.broker_uri)
log.info('Connected to broker {}', op.broker_uri)
exporter = create_exporter(service_name=service_name, uri=op.zipkin_uri)
subscription = Subscription(channel=channel, name=service_name)
for group_id in list(op.group_ids):
subscription.subscribe(
'SkeletonsGrouper.{}.Localization'.format(group_id))
model = GestureRecognizer("model_gesture1_72.00.pth")
log.info('Initialize the model')
unc = Gauge('uncertainty_total', "Uncertainty about predict")
unc.set(0.0)
start_http_server(8000)
buffer = list()
predict_flag = False
mean = lambda x: (sum(x) / len(x))
while True:
msg = channel.consume()
tracer = Tracer(exporter, span_context=msg.extract_tracing())
span = tracer.start_span(name='detection_and_info')
annotations = msg.unpack(ObjectAnnotations)
skeleton = select_skeletons(annotations=annotations,
min_keypoints=op.skeletons.min_keypoints,
x_range=op.skeletons.x_range,
y_range=op.skeletons.y_range)
if skeleton is None:
tracer.end_span()
continue
skl = Skeleton(skeleton)
skl_normalized = skl.normalize()
pred, prob, uncertainty = model.predict(skl_normalized)
if pred == 0 and predict_flag is False:
pass
elif pred != 0 and predict_flag is False:
initial_time = time.time()
predict_flag = True
buffer.append(uncertainty)
elif pred != 0 and predict_flag is True:
buffer.append(uncertainty)
elif pred == 0 and predict_flag is True:
predict_flag = False
exec_time = time.time() - initial_time
if exec_time >= op.exec_time:
unc.set(mean(buffer))
log.info("execution_ms: {}, buffer_mean: {}",
(exec_time * 1000), mean(buffer))
buffer = []
tracer.end_span()
info = {
'prediction': pred,
'probability': prob,
'uncertainty': uncertainty,
'took_ms': {
'service': round(span_duration_ms(span), 2)
}
}
log.info('{}', str(info).replace("'", '"'))
