def predict(self, **inputs):
"""
Args:
val_func(callable): model inference function
Returns:
results boxes: detection model output
"""
box_cls, box_delta = self.pred_func(**inputs)
# box_cls, box_delta = self.model(**inputs)
box_cls, box_delta = box_cls.numpy(), box_delta.numpy()
dtboxes_all = list()
all_inds = np.where(box_cls > self.model.cfg.test_cls_threshold)
for c in range(self.model.cfg.num_classes):
inds = np.where(all_inds[1] == c)[0]
inds = all_inds[0][inds]
scores = box_cls[inds, c]
if self.model.cfg.class_aware_box:
bboxes = box_delta[inds, c, :]
else:
bboxes = box_delta[inds, :]
dtboxes = np.hstack(
(bboxes, scores[:, np.newaxis])).astype(np.float32)
if dtboxes.size > 0:
if self.model.cfg.test_nms == -1:
keep = dtboxes[:, 4].argsort()[::-1]
else:
assert 0 < self.model.cfg.test_nms <= 1.0
keep = py_cpu_nms(dtboxes, self.model.cfg.test_nms)
dtboxes = np.hstack(
(dtboxes[keep], np.full(
(len(keep), 1), c,
dtype=np.float32))).astype(np.float32)
dtboxes_all.extend(dtboxes)
if len(dtboxes_all) > self.model.cfg.test_max_boxes_per_image:
dtboxes_all = sorted(
dtboxes_all, reverse=True,
key=lambda i: i[4])[:self.model.cfg.test_max_boxes_per_image]
dtboxes_all = np.array(dtboxes_all, dtype=np.float)
return dtboxes_all
def predict(self, val_func):
"""
Args:
val_func(callable): model inference function
Returns:
results boxes: detection model output
"""
model = self.model
box_cls, box_delta = val_func()
box_cls, box_delta = box_cls.numpy(), box_delta.numpy()
dtboxes_all = list()
all_inds = np.where(box_cls > model.cfg.test_cls_threshold)
for c in range(0, model.cfg.num_classes):
inds = np.where(all_inds[1] == c)[0]
inds = all_inds[0][inds]
scores = box_cls[inds, c]
if model.cfg.class_aware_box:
bboxes = box_delta[inds, c, :]
else:
bboxes = box_delta[inds, :]
dtboxes = np.hstack(
(bboxes, scores[:, np.newaxis])).astype(np.float32)
if dtboxes.size > 0:
keep = py_cpu_nms(dtboxes, model.cfg.test_nms)
dtboxes = np.hstack(
(dtboxes[keep], np.ones(
(len(keep), 1), np.float32) * c)).astype(np.float32)
dtboxes_all.extend(dtboxes)
if len(dtboxes_all) > model.cfg.test_max_boxes_per_image:
dtboxes_all = sorted(
dtboxes_all, reverse=True,
key=lambda i: i[4])[:model.cfg.test_max_boxes_per_image]
dtboxes_all = np.array(dtboxes_all, dtype=np.float)
return dtboxes_all
def detect_persons(self, image):
data, im_info = DetEvaluator.process_inputs(
image.copy(),
self.detector.cfg.test_image_short_size,
self.detector.cfg.test_image_max_size,
)
evaluator = DetEvaluator(self.detector)
det_res = evaluator.predict(image=mge.tensor(data),
im_info=mge.tensor(im_info))
persons = []
for d in det_res:
cls_id = int(d[5] + 1)
if cls_id == 1:
bbox = d[:5]
persons.append(bbox)
persons = np.array(persons).reshape(-1, 5)
keep = py_cpu_nms(persons, cfg.nms_thr)
return persons[keep]
