def _arm_inference(_id):
logits, bboxes = threat_detect_inference(_id, 'arm')
arcs = build_arcs('arm', logits, bboxes, _id)
prediction_strings = []
for i in range(len(arcs)):
arc = arcs[i]
zone = i + 1
predict_proba = ArmCalibrationModel().calibrate(
arc.calibration_featurize('arm'))
prediction_strings.append('{0}_Zone{1},{2}'.format(
_id, zone, predict_proba))
for s in prediction_strings:
print(s)
def _curate_arm_calibration(data_set):
ids = Table().read_table(dp.ids_by_data_set(data_set)).column('Id')
X, y_label, y_zone = [], [], []
for _id in ids:
print(_id)
logits, bboxes = threat_detect_inference(_id, 'arm')
arcs = build_arcs('arm', logits, bboxes, _id)
for i in range(len(arcs)):
arc = arcs[i]
X.append(arc.to_list())
zone = i + 1
y_label.append(_ground_truth_label(_id, zone))
y_zone.append(zone)
X, y_label, y_zone = np.array(X), np.array(y_label), np.array(y_zone)
return X, y_label, y_zone, ids
def _curate_torso_calibration(data_set):
ids = Table().read_table(dp.ids_by_data_set(data_set)).column('Id')
X, y_label, y_zone, example_ids = [], [], [], []
xml_base_zone_path = dp.REPO_HOME_PATH + '/data/bbox/aps_threats/zone_{2}/{0}_{1}.xml'
for _id in ids:
print(_id)
logits, bboxes = threat_detect_inference(_id, 'torso')
_, cropped_bbox = crop_and_pad(_id,
file_format='aps',
region='torso',
slc=0,
keypoint_pad=None)
arcs = build_arcs('torso', logits, bboxes, _id)
for i in range(len(arcs)):
arc = arcs[i]
matched = False
for zone in [5, 6, 7, 17]:
num_matches = 0
original_scale_boxes = arc.original_scale_boxes(cropped_bbox)
for i in range(original_scale_boxes.shape[0]):
gt_xml_path = xml_base_zone_path.format(i, _id, zone)
if os.path.exists(gt_xml_path):
gt_bboxes = np.array(parse_bbox_xml(gt_xml_path))
if gt_bboxes.size > 0:
if np.max(
_iou(gt_bboxes, original_scale_boxes[i][
np.newaxis])) > 0.5:
num_matches += 1
matched = num_matches / np.sum(
np.sum(original_scale_boxes, axis=1) > 0) >= 0.5
if matched:
X.append(arc.to_list())
y_label.append(int(matched))
y_zone.append(zone)
example_ids.append(_id)
break
if not matched:
X.append(arc.to_list())
y_label.append(int(matched))
y_zone.append(zone)
example_ids.append(_id)
X, y_label, y_zone = np.array(X), np.array(y_label), np.array(y_zone)
return X, y_label, y_zone, example_ids
def _thigh_inference(_id):
logits, bboxes = threat_detect_inference(_id, 'thigh')
arcs = build_arcs('thigh', logits, bboxes)
zone_predictions = {i: [] for i in [8, 9, 10, 11, 12]}
for i in range(len(arcs)):
arc = arcs[i]
predict_proba = ThighCalibrationModel().calibrate(
arc.calibration_featurize('thigh'))
zone = ThighCalibrationModel().zone(arc.zone_featurize('thigh'))[0]
zone_predictions[zone].append(predict_proba)
prediction_strings = []
for zone in [8, 9, 10, 11, 12]:
preds = np.array(sorted(zone_predictions[zone])[::-1])
if len(preds) == 0:
predict_proba = MIN_PREDICTION
else:
predict_proba = preds[0] + (1 - preds[0]) * min(
np.sum(preds[1:]), 1)
prediction_strings.append('{0}_Zone{1},{2}'.format(
_id, zone, predict_proba))
for s in prediction_strings:
print(s)