def draw_result(out, im_scale, clss, bbox, nms_thresh, conf):
CV_AA = 16
for cls_id in range(1, 21):
_cls = clss[:, cls_id][:, np.newaxis]
_bbx = bbox[:, cls_id * 4: (cls_id + 1) * 4]
dets = np.hstack((_bbx, _cls))
keep = nms(dets, nms_thresh)
dets = dets[keep, :]
inds = np.where(dets[:, -1] >= conf)[0]
for i in inds:
x1, y1, x2, y2 = map(int, dets[i, :4])
cv.rectangle(out, (x1, y1), (x2, y2), (0, 0, 255), 2, CV_AA)
ret, baseline = cv.getTextSize(
CLASSES[cls_id], cv.FONT_HERSHEY_SIMPLEX, 0.8, 1)
cv.rectangle(out, (x1, y2 - ret[1] - baseline),
(x1 + ret[0], y2), (0, 0, 255), -1)
cv.putText(out, CLASSES[cls_id], (x1, y2 - baseline),
cv.FONT_HERSHEY_SIMPLEX, 0.8, (255, 255, 255), 1, CV_AA)
return out
def draw_result(out, im_scale, clss, bbox, nms_thresh, conf):
CV_AA = 16
for cls_id in range(1,2):
_cls = clss[:, cls_id][:, np.newaxis]
_bbx = bbox[:, cls_id * 4: (cls_id + 1) * 4]
dets = np.hstack((_bbx, _cls))
keep = nms(dets, nms_thresh)
dets = dets[keep, :]
inds = np.where(dets[:, -1] >= conf)[0]
result = []
for i in inds:
x1, y1, x2, y2 = map(int, dets[i, :4])
score = dets[i][-1]
cv.rectangle(out, (x1, y1), (x2, y2), (0, 0, 255), 2, CV_AA)
ret, baseline = cv.getTextSize(
CLASSES[cls_id], cv.FONT_HERSHEY_SIMPLEX, 0.8, 1)
cv.putText(out, "%s:%.2f"%(CLASSES[cls_id], score), (x1, y1 - baseline),
cv.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 1, CV_AA)
result.append([x1, y1, x2, y2, score])
return out, result
def get_dictionary(self, out, im_scale, clss, bbox, nms_thresh, conf):
dictionary = {}
width = out.shape[1]
height = out.shape[0]
for cls_id in range(1, 21):
_cls = clss[:, cls_id][:, np.newaxis]
_bbx = bbox[:, cls_id * 4: (cls_id + 1) * 4]
dets = np.hstack((_bbx, _cls))
keep = nms(dets, nms_thresh)
dets = dets[keep, :]
inds = np.where(dets[:, -1] >= conf)[0]
for i in inds:
x1, y1, x2, y2 = map(int, dets[i, :4])
if x2 > width:
x2 = width
if y2 > height:
y2 = height
name = CLASSES[cls_id] + "_" + str(i)
dictionary[name] = (x1, y1, x2, y2)
return dictionary
def draw_result(self, out, im_scale, clss, bbox, nms_thresh, conf):
CV_AA = 16
for cls_id in range(1, 21):
_cls = clss[:, cls_id][:, np.newaxis]
_bbx = bbox[:, cls_id * 4: (cls_id + 1) * 4]
dets = np.hstack((_bbx, _cls))
keep = nms(dets, nms_thresh)
dets = dets[keep, :]
inds = np.where(dets[:, -1] >= conf)[0]
for i in inds:
x1, y1, x2, y2 = map(int, dets[i, :4])
cv.rectangle(out, (x1, y1), (x2, y2), (0, 0, 255), 2, CV_AA)
ret, baseline = cv.getTextSize(
CLASSES[cls_id], cv.FONT_HERSHEY_SIMPLEX, 0.8, 1)
cv.rectangle(out, (x1, y2 - ret[1] - baseline),
(x1 + ret[0], y2), (0, 0, 255), -1)
cv.putText(out, CLASSES[cls_id], (x1, y2 - baseline),
cv.FONT_HERSHEY_SIMPLEX,
0.8, (255, 255, 255), 1, CV_AA)
return out
def __call__(self, rpn_cls_prob, rpn_bbox_pred, im_info, train):
# Algorithm:
#
# for each (H, W) location i
# generate A anchor boxes centered on cell i
# apply predicted bbox deltas at cell i to each of the A anchors
# clip predicted boxes to image
# remove predicted boxes with either height or width < threshold
# sort all (proposal, score) pairs by score from highest to lowest
# take top pre_nms_topN proposals before NMS
# apply NMS with threshold 0.7 to remaining proposals
# take after_nms_topN proposals after NMS
# return the top proposals (-> RoIs top, scores top)
pre_nms_topN = self.TRAIN_RPN_PRE_NMS_TOP_N \
if train else self.TEST_RPN_PRE_NMS_TOP_N
post_nms_topN = self.TRAIN_RPN_POST_NMS_TOP_N \
if train else self.TEST_RPN_POST_NMS_TOP_N
nms_thresh = self.RPN_NMS_THRESH
min_size = self.RPN_MIN_SIZE
# the first set of _num_anchors channels are bg probs
# the second set are the fg probs, which we want
scores = to_cpu(rpn_cls_prob.data[:, self._num_anchors:, :, :])
bbox_deltas = to_cpu(rpn_bbox_pred.data)
im_info = im_info[0, :]
# 1. Generate proposals from bbox deltas and shifted anchors
height, width = scores.shape[-2:]
# Enumerate all shifts
shift_x = np.arange(0, width) * self._feat_stride
shift_y = np.arange(0, height) * self._feat_stride
shift_x, shift_y = np.asarray(np.meshgrid(shift_x, shift_y))
shifts = np.vstack((shift_x.ravel(), shift_y.ravel(),
shift_x.ravel(), shift_y.ravel())).transpose()
# Enumerate all shifted anchors:
#
# add A anchors (1, A, 4) to
# cell K shifts (K, 1, 4) to get
# shift anchors (K, A, 4)
# reshape to (K*A, 4) shifted anchors
A = self._num_anchors
K = shifts.shape[0]
anchors = self._anchors.reshape((1, A, 4)) + \
shifts.reshape((1, K, 4)).transpose((1, 0, 2))
anchors = anchors.reshape((K * A, 4))
# Transpose and reshape predicted bbox transformations to get them
# into the same order as the anchors:
#
# bbox deltas will be (1, 4 * A, H, W) format
# transpose to (1, H, W, 4 * A)
# reshape to (1 * H * W * A, 4) where rows are ordered by (h, w, a)
# in slowest to fastest order
bbox_deltas = bbox_deltas.transpose((0, 2, 3, 1)).reshape((-1, 4))
# Same story for the scores:
#
# scores are (1, A, H, W) format
# transpose to (1, H, W, A)
# reshape to (1 * H * W * A, 1) where rows are ordered by (h, w, a)
scores = scores.transpose((0, 2, 3, 1)).reshape((-1, 1))
# Convert anchors into proposals via bbox transformations
proposals = bbox_transform_inv(anchors, bbox_deltas, -1)
# 2. clip predicted boxes to image
proposals = clip_boxes(proposals, im_info[:2])
# 3. remove predicted boxes with either height or width < threshold
# (NOTE: convert min_size to input image scale stored in im_info[2])
keep = _filter_boxes(proposals, min_size * im_info[2])
proposals = proposals[keep, :]
scores = scores[keep]
# 4. sort all (proposal, score) pairs by score from highest to lowest
# 5. take top pre_nms_topN (e.g. 6000)
order = scores.ravel().argsort()[::-1]
if pre_nms_topN > 0:
order = order[:pre_nms_topN]
proposals = proposals[order, :]
scores = scores[order]
# 6. apply nms (e.g. threshold = 0.7)
# 7. take after_nms_topN (e.g. 300)
# 8. return the top proposals (-> RoIs top)
keep = nms(np.hstack((proposals, scores)), nms_thresh)
if post_nms_topN > 0:
keep = keep[:post_nms_topN]
proposals = proposals[keep, :]
scores = scores[keep]
# Output rois blob
# Our RPN implementation only supports a single input image, so all
# batch inds are 0
batch_inds = np.zeros((proposals.shape[0], 1), dtype=np.float32)
rois = np.asarray(np.hstack((batch_inds, proposals)), dtype=np.float32)
return rois
def __call__(self, rpn_cls_prob, rpn_bbox_pred, im_info, train):
# Algorithm:
#
# for each (H, W) location i
# generate A anchor boxes centered on cell i
# apply predicted bbox deltas at cell i to each of the A anchors
# clip predicted boxes to image
# remove predicted boxes with either height or width < threshold
# sort all (proposal, score) pairs by score from highest to lowest
# take top pre_nms_topN proposals before NMS
# apply NMS with threshold 0.7 to remaining proposals
# take after_nms_topN proposals after NMS
# return the top proposals (-> RoIs top, scores top)
pre_nms_topN = self.RPN_PRE_NMS_TOP_N if train else 6000
post_nms_topN = self.RPN_POST_NMS_TOP_N if train else 300
nms_thresh = self.RPN_NMS_THRESH
min_size = self.RPN_MIN_SIZE
# the first set of _num_anchors channels are bg probs
# the second set are the fg probs, which we want
scores = to_cpu(rpn_cls_prob.data[:, self._num_anchors:, :, :])
bbox_deltas = to_cpu(rpn_bbox_pred.data)
im_info = im_info[0, :]
# 1. Generate proposals from bbox deltas and shifted anchors
height, width = scores.shape[-2:]
# Enumerate all shifts
shift_x = np.arange(0, width) * self._feat_stride
shift_y = np.arange(0, height) * self._feat_stride
shift_x, shift_y = np.asarray(np.meshgrid(shift_x, shift_y))
shifts = np.vstack((shift_x.ravel(), shift_y.ravel(), shift_x.ravel(),
shift_y.ravel())).transpose()
# Enumerate all shifted anchors:
#
# add A anchors (1, A, 4) to
# cell K shifts (K, 1, 4) to get
# shift anchors (K, A, 4)
# reshape to (K*A, 4) shifted anchors
A = self._num_anchors
K = shifts.shape[0]
anchors = self._anchors.reshape((1, A, 4)) + \
shifts.reshape((1, K, 4)).transpose((1, 0, 2))
anchors = anchors.reshape((K * A, 4))
# Transpose and reshape predicted bbox transformations to get them
# into the same order as the anchors:
#
# bbox deltas will be (1, 4 * A, H, W) format
# transpose to (1, H, W, 4 * A)
# reshape to (1 * H * W * A, 4) where rows are ordered by (h, w, a)
# in slowest to fastest order
bbox_deltas = bbox_deltas.transpose((0, 2, 3, 1)).reshape((-1, 4))
# Same story for the scores:
#
# scores are (1, A, H, W) format
# transpose to (1, H, W, A)
# reshape to (1 * H * W * A, 1) where rows are ordered by (h, w, a)
scores = scores.transpose((0, 2, 3, 1)).reshape((-1, 1))
# Convert anchors into proposals via bbox transformations
proposals = bbox_transform_inv(anchors, bbox_deltas, -1)
# 2. clip predicted boxes to image
proposals = clip_boxes(proposals, im_info[:2])
# 3. remove predicted boxes with either height or width < threshold
# (NOTE: convert min_size to input image scale stored in im_info[2])
keep = _filter_boxes(proposals, min_size * im_info[2])
proposals = proposals[keep, :]
scores = scores[keep]
# 4. sort all (proposal, score) pairs by score from highest to lowest
# 5. take top pre_nms_topN (e.g. 6000)
order = scores.ravel().argsort()[::-1]
if pre_nms_topN > 0:
order = order[:pre_nms_topN]
proposals = proposals[order, :]
scores = scores[order]
# 6. apply nms (e.g. threshold = 0.7)
# 7. take after_nms_topN (e.g. 300)
# 8. return the top proposals (-> RoIs top)
keep = nms(np.hstack((proposals, scores)), nms_thresh)
if post_nms_topN > 0:
keep = keep[:post_nms_topN]
proposals = proposals[keep, :]
scores = scores[keep]
# Output rois blob
# Our RPN implementation only supports a single input image, so all
# batch inds are 0
batch_inds = np.zeros((proposals.shape[0], 1), dtype=np.float32)
rois = np.asarray(np.hstack((batch_inds, proposals)), dtype=np.float32)
return rois