def detect(self, img, threshold=0.5, scales=[1.0]):
proposals_list = []
landmarks_list = []
scores_list = []
for im_scale in scales:
if im_scale != 1.0:
im = cv2.resize(img,
None,
None,
fx=im_scale,
fy=im_scale,
interpolation=cv2.INTER_LINEAR)
else:
im = img
im = im.astype(np.float32)
# self.model.bind(data_shapes=[('data', (1, 3, image_size[0], image_size[1]))], for_training=False)
im_info = [im.shape[0], im.shape[1], im_scale]
im_tensor = np.zeros((1, 3, im.shape[0], im.shape[1]))
for i in range(3):
im_tensor[0,
i, :, :] = im[:, :, 2 - i] - self.pixel_means[2 - i]
data = nd.array(im_tensor)
db = mx.io.DataBatch(data=(data, ),
provide_data=[('data', data.shape)])
self.model.forward(db, is_train=False)
net_out = self.model.get_outputs()
pre_nms_topN = self._rpn_pre_nms_top_n
# post_nms_topN = self._rpn_post_nms_top_n
# min_size_dict = self._rpn_min_size_fpn
for s in self._feat_stride_fpn:
if len(scales) > 1 and s == 32 and im_scale == scales[-1]:
continue
_key = 'stride%s' % s
stride = int(s)
idx = 0
if s == 16:
idx = 3
elif s == 8:
idx = 6
# print('getting', im_scale, stride, idx, len(net_out), data.shape, file=sys.stderr)
scores = net_out[idx].asnumpy()
# print(scores.shape)
idx += 1
# print('scores',stride, scores.shape, file=sys.stderr)
scores = scores[:, self._num_anchors['stride%s' % s]:, :, :]
bbox_deltas = net_out[idx].asnumpy()
idx += 1
# if DEBUG:
# print 'im_size: ({}, {})'.format(im_info[0], im_info[1])
# print 'scale: {}'.format(im_info[2])
_height, _width = int(im_info[0] / stride), int(im_info[1] /
stride)
height, width = bbox_deltas.shape[2], bbox_deltas.shape[3]
# kpoint
kpoint_deltas = net_out[idx].asnumpy()
A = self._num_anchors['stride%s' % s]
K = height * width
anchors = anchors_plane(
height, width, stride,
self._anchors_fpn['stride%s' % s].astype(np.float32))
# print((height, width), (_height, _width), anchors.shape, bbox_deltas.shape, scores.shape, file=sys.stderr)
anchors = anchors.reshape((K * A, 4))
# print('pre', bbox_deltas.shape, height, width)
bbox_deltas = self._clip_pad(bbox_deltas, (height, width))
# print('after', bbox_deltas.shape, height, width)
bbox_deltas = bbox_deltas.transpose((0, 2, 3, 1)).reshape(
(-1, 4))
kpoint_deltas = self._clip_pad(kpoint_deltas, (height, width))
kpoint_deltas = kpoint_deltas.transpose((0, 2, 3, 1)).reshape(
(-1, 10))
scores = self._clip_pad(scores, (height, width))
scores = scores.transpose((0, 2, 3, 1)).reshape((-1, 1))
# print(anchors.shape, bbox_deltas.shape, A, K, file=sys.stderr)
proposals = self._bbox_pred(anchors, bbox_deltas)
# proposals = anchors
proposals = clip_boxes(proposals, im_info[:2])
landmarks = landmark_pred(anchors, kpoint_deltas)
landmarks = clip_points(landmarks, im_info[:2])
# keep = self._filter_boxes(proposals, min_size_dict['stride%s'%s] * im_info[2])
# proposals = proposals[keep, :]
# scores = scores[keep]
# print('333', proposals.shape)
scores_ravel = scores.ravel()
order = scores_ravel.argsort()[::-1]
if pre_nms_topN > 0:
order = order[:pre_nms_topN]
proposals = proposals[order, :]
landmarks = landmarks[order, :]
scores = scores[order]
proposals /= im_scale
landmarks /= im_scale
proposals_list.append(proposals)
landmarks_list.append(landmarks)
scores_list.append(scores)
proposals = np.vstack(proposals_list)
landmarks = np.vstack(landmarks_list)
scores = np.vstack(scores_list)
scores_ravel = scores.ravel()
order = scores_ravel.argsort()[::-1]
#if config.TEST.SCORE_THRESH>0.0:
# _count = np.sum(scores_ravel>config.TEST.SCORE_THRESH)
# order = order[:_count]
#if pre_nms_topN > 0:
# order = order[:pre_nms_topN]
proposals = proposals[order, :]
landmarks = landmarks[order, :]
scores = scores[order]
det = np.hstack((proposals, scores, landmarks)).astype(np.float32)
#if np.shape(det)[0] == 0:
# print("Something wrong with the input image(resolution is too low?), generate fake proposals for it.")
# proposals = np.array([[1.0, 1.0, 2.0, 2.0]]*post_nms_topN, dtype=np.float32)
# scores = np.array([[0.9]]*post_nms_topN, dtype=np.float32)
# det = np.array([[1.0, 1.0, 2.0, 2.0, 0.9]]*post_nms_topN, dtype=np.float32)
if self.nms_threshold < 1.0:
keep = self.nms(det)
det = det[keep, :]
if threshold > 0.0:
keep = np.where(det[:, 4] >= threshold)[0]
det = det[keep, :]
return det
def detect(self, img, threshold=0.5, scales=[1.0]):
proposals_list = []
proposals_kp_list = []
scores_list = []
for im_scale in scales:
if im_scale != 1.0:
im = cv2.resize(img, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
else:
im = img
im = im.astype(np.float32)
# im_shape = im.shape
# self.model.bind(data_shapes=[('data', (1, 3, im_shape[0], im_shape[1]))], for_training=False)
im_info = [im.shape[0], im.shape[1], im_scale]
im_tensor = np.zeros((1, 3, im.shape[0], im.shape[1]))
for i in range(3):
im_tensor[0, i, :, :] = im[:, :, 2 - i] - self.pixel_means[2 - i] #bgr2rgb mxnet rgb opencv bgr
data = nd.array(im_tensor)
db = mx.io.DataBatch(data=(data,), provide_data=[('data', data.shape)])
timea = datetime.datetime.now()
self.model.forward(db, is_train=False)
timeb = datetime.datetime.now()
diff = timeb - timea
print('forward uses', diff.total_seconds(), 'seconds')
net_out = self.model.get_outputs() #网络的输出为len=9的list,针对三个不同的stride,分为三大块的list,其中每个list分别代表score,bbox,kpoint三个维度的结果，
pre_nms_topN = self._rpn_pre_nms_top_n
#post_nms_topN = self._rpn_post_nms_top_n
#min_size_dict = self._rpn_min_size_fpn
for s in self.feat_strides:
_key = 'stride%s' % s
# print(_key)
stride = int(s)
if s == self.feat_strides[0]:
idx = 0
if s == self.feat_strides[1]:
idx = 3
elif s == self.feat_strides[2]:
idx = 6
# print('getting', im_scale, stride, idx, len(net_out), data.shape, file=sys.stderr)
scores = net_out[idx].asnumpy() #获取每个stride下的分类得分
idx += 1
# print('scores',stride, scores.shape, file=sys.stderr)
scores = scores[:, self._num_anchors['stride%s'%s]:, :, :] #去掉了其中lable的值？？？
bbox_deltas = net_out[idx].asnumpy()
idx += 1
_height, _width = int(im_info[0] / stride), int(im_info[1] / stride)
height, width = bbox_deltas.shape[2], bbox_deltas.shape[3]
# kpoint
kpoint_deltas = net_out[idx].asnumpy()
A = self._num_anchors['stride%s' % s]
K = height * width
anchors = anchors_plane(height, width, stride, self._anchors_fpn['stride%s' % s].astype(np.float32)) #RP映射回原图中的坐标位置
# print((height, width), (_height, _width), anchors.shape, bbox_deltas.shape, scores.shape, file=sys.stderr)
anchors = anchors.reshape((K * A, 4))
# print('predict bbox_deltas', bbox_deltas.shape, height, width)
bbox_deltas = self._clip_pad(bbox_deltas, (height, width))
# print('after clip pad', bbox_deltas.shape, height, width)
bbox_deltas = bbox_deltas.transpose((0, 2, 3, 1)).reshape((-1, 4))
kpoint_deltas = self._clip_pad(kpoint_deltas, (height, width))
kpoint_deltas = kpoint_deltas.transpose((0, 2, 3, 1)).reshape((-1, 10))
scores = self._clip_pad(scores, (height, width))
scores = scores.transpose((0, 2, 3, 1)).reshape((-1, 1))
# print(anchors.shape, bbox_deltas.shape, A, K, file=sys.stderr)
proposals = self._bbox_pred(anchors, bbox_deltas)
proposals = clip_boxes(proposals, im_info[:2]) #将超出图像的坐标去除掉
proposals_kp = kpoint_pred(anchors, kpoint_deltas)
proposals_kp = clip_points(proposals_kp, im_info[:2])
#取出score的top N
scores_ravel = scores.ravel()
order = scores_ravel.argsort()[::-1]
if pre_nms_topN > 0:
order = order[:pre_nms_topN]
proposals = proposals[order, :]
proposals_kp = proposals_kp[order, :]
scores = scores[order]
proposals /= im_scale
proposals_kp /= im_scale
proposals_list.append(proposals)
proposals_kp_list.append(proposals_kp)
scores_list.append(scores)
proposals = np.vstack(proposals_list)
proposals_kp = np.vstack(proposals_kp_list)
scores = np.vstack(scores_list)
scores_ravel = scores.ravel()
order = scores_ravel.argsort()[::-1]
#if config.TEST.SCORE_THRESH>0.0:
# _count = np.sum(scores_ravel>config.TEST.SCORE_THRESH)
# order = order[:_count]
#if pre_nms_topN > 0:
# order = order[:pre_nms_topN]
proposals = proposals[order, :]
proposals_kp = proposals_kp[order, :]
scores = scores[order]
det = np.hstack((proposals, scores, proposals_kp)).astype(np.float32)
#if np.shape(det)[0] == 0:
# print("Something wrong with the input image(resolution is too low?), generate fake proposals for it.")
# proposals = np.array([[1.0, 1.0, 2.0, 2.0]]*post_nms_topN, dtype=np.float32)
# scores = np.array([[0.9]]*post_nms_topN, dtype=np.float32)
# det = np.array([[1.0, 1.0, 2.0, 2.0, 0.9]]*post_nms_topN, dtype=np.float32)
if self.nms_threshold < 1.0:
keep = self.nms(det)
det = det[keep, :]
if threshold > 0.0:
keep = np.where(det[:, 4] >= threshold)[0]
det = det[keep, :]
return det