def im_detect(self, im):
cls_prob = self.cls_prob
bbox_pred = self.bbox_pred
rois = self.rois
if isinstance(rois, tuple):
rois = rois[0]
cls_prob = np.reshape(cls_prob,
[-1, cfg.ZLRM.N_CLASSES + 1]) # (R, C+1)
bbox_pred = np.reshape(bbox_pred,
[-1,
(cfg.ZLRM.N_CLASSES + 1) * 4]) # (R, (C+1)x4)
rois = np.array(rois)
boxes = rois[:, 1:5] / self.im_scale
scores = cls_prob
# Apply bounding-box regression deltas
box_deltas = bbox_pred
pred_boxes = bbox_transform_inv(boxes, box_deltas)
pred_boxes = clip_boxes(pred_boxes, im.shape)
return scores, pred_boxes
def im_detect(sess, net, im):
blobs, im_scales = _get_blobs(im)
im_blob = blobs['data']
blobs['im_info'] = np.array(
[[im_blob.shape[1], im_blob.shape[2], im_scales[0]]], dtype=np.float32)
# forward pass
feed_dict = {net.data: blobs['data'], net.im_info: blobs['im_info']}
cls_prob, bbox_pred, rois = \
sess.run([net.get_output('cls_prob'), net.get_output('ave_bbox_pred_rois'),
net.get_output('rois')], \
feed_dict=feed_dict)
if isinstance(rois, tuple):
rois = rois[0]
cls_prob = np.reshape(cls_prob, [-1, cfg.ZLRM.N_CLASSES + 1]) # (R, C+1)
bbox_pred = np.reshape(bbox_pred,
[-1, (cfg.ZLRM.N_CLASSES + 1) * 4]) # (R, (C+1)x4)
rois = np.array(rois)
assert len(im_scales) == 1, "Only single-image batch implemented"
boxes = rois[:, 1:5] / im_scales[0]
scores = cls_prob
if cfg.ZLRM.TEST.BBOX_REG:
# Apply bounding-box regression deltas
box_deltas = bbox_pred
pred_boxes = bbox_transform_inv(boxes, box_deltas)
pred_boxes = clip_boxes(pred_boxes, im.shape)
return scores, pred_boxes
def _process_boxes_scores(cls_prob, bbox_pred, rois, im_scale, im_shape):
"""
process the output tensors, to get the boxes and scores
"""
assert rois.shape[0] == bbox_pred.shape[0],\
'rois and bbox_pred must have the same shape'
boxes = rois[:, 1:5]
scores = cls_prob
if cfg.ZLRM.TEST.BBOX_REG:
pred_boxes = bbox_transform_inv(boxes, deltas=bbox_pred)
pred_boxes = clip_boxes(pred_boxes, im_shape)
else:
# Simply repeat the boxes, once for each class
# boxes = np.tile(boxes, (1, scores.shape[1]))
pred_boxes = clip_boxes(boxes, im_shape)
return pred_boxes, scores
def proposal_layer(rpn_cls_prob_reshape_P2, rpn_bbox_pred_P2, \
rpn_cls_prob_reshape_P3, rpn_bbox_pred_P3, \
rpn_cls_prob_reshape_P4, rpn_bbox_pred_P4, \
rpn_cls_prob_reshape_P5, rpn_bbox_pred_P5, \
rpn_cls_prob_reshape_P6, rpn_bbox_pred_P6, \
im_info, cfg_train_key = True, _feat_strides = cfg.ZLRM.FPN_FEAT_STRIDE[2:], \
anchor_sizes = cfg.ZLRM.FPN_ANCHOR_SIZE[2:]): # anchor_scales = [8, 8, 8, 8, 8]
"""
Parameters
----------
rpn_cls_prob_reshape_P: (1 , H(P), W(P), A(P)x2) outputs of RPN, prob of bg or fg on pyramid layer P
rpn_bbox_pred_P: (1 , H(P), W(P), A(P)x4), rgs boxes output of RPN on pyramid layer P
im_info: a list of [image_height, image_width, scale_ratios]
cfg_key: 'TRAIN' or 'TEST'
_feat_strides: the downsampling ratio of feature map to the original input image on each pyramid layer
anchor_sizes: the absolute anchor sizes on each pyramid layer
----------
Returns
----------
rpn_rois : (sum(H x W x A), 5) e.g. [0, x1, y1, x2, y2]
# 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)
#layer_params = yaml.load(self.param_str_)
"""
anchor_scales = np.array(anchor_sizes) / np.array(_feat_strides)
# _anchors = [generate_anchors(base_size=_feat_stride, scales=[anchor_scale]) for _feat_stride, anchor_scale in zip(_feat_strides, anchor_scales)]
_anchors = [[], [], [], [], []]
_anchors[0] = generate_anchors(base_size=_feat_strides[0], ratios=cfg.ZLRM.ANCHOR_RATIO, scales=np.array([anchor_scales[0]]))
_anchors[1] = generate_anchors(base_size=_feat_strides[1], ratios=cfg.ZLRM.ANCHOR_RATIO, scales=np.array([anchor_scales[1]]))
_anchors[2] = generate_anchors(base_size=_feat_strides[2], ratios=cfg.ZLRM.ANCHOR_RATIO, scales=np.array([anchor_scales[2]]))
_anchors[3] = generate_anchors(base_size=_feat_strides[3], ratios=cfg.ZLRM.ANCHOR_RATIO, scales=np.array([anchor_scales[3]]))
_anchors[4] = generate_anchors(base_size=_feat_strides[4], ratios=cfg.ZLRM.ANCHOR_RATIO, scales=np.array([anchor_scales[4]]))
_num_anchors = [anchor.shape[0] for anchor in _anchors]
im_info = im_info[0]
#assert rpn_cls_prob_reshape.shape[0] == 1, \
# 'Only single item batches are supported'
# cfg_key = str(self.phase) # either 'TRAIN' or 'TEST'
#cfg_key = 'TEST'
if cfg_train_key==True:
# print('使用TEST')
pre_nms_topN = cfg.ZLRM.TRAIN.RPN_PRE_NMS_TOP_N # 12000
post_nms_topN = cfg.ZLRM.TRAIN.RPN_POST_NMS_TOP_N # 2000
nms_thresh = cfg.ZLRM.TRAIN.RPN_NMS_THRESH # 0.7
min_size = cfg.ZLRM.TRAIN.RPN_MIN_SIZE # 16
else:
pre_nms_topN = cfg.ZLRM.TEST.RPN_PRE_NMS_TOP_N # 6000
post_nms_topN = cfg.ZLRM.TEST.RPN_POST_NMS_TOP_N # 300
nms_thresh = cfg.ZLRM.TEST.RPN_NMS_THRESH # 0.7
min_size = cfg.ZLRM.TEST.RPN_MIN_SIZE # 16
rpn_cls_prob_reshapes = [rpn_cls_prob_reshape_P2, rpn_cls_prob_reshape_P3, rpn_cls_prob_reshape_P4, rpn_cls_prob_reshape_P5, rpn_cls_prob_reshape_P6]
bbox_deltas = [rpn_bbox_pred_P2, rpn_bbox_pred_P3, rpn_bbox_pred_P4, rpn_bbox_pred_P5, rpn_bbox_pred_P6]
heights = [rpn_cls_prob_reshape.shape[1] for rpn_cls_prob_reshape in rpn_cls_prob_reshapes]
widths = [rpn_cls_prob_reshape.shape[2] for rpn_cls_prob_reshape in rpn_cls_prob_reshapes]
# the first set of _num_anchors channels are bg probs
# the second set are the fg probs, which we want
# (4, 1, H, W, A(x)) --> (1, H, W, stack(A))
scores = [np.reshape(np.reshape(rpn_cls_prob_reshape, [1, height, width, _num_anchor, 2])[:,:,:,:,1],
[-1, 1])
for height, width, rpn_cls_prob_reshape, _num_anchor in
zip(heights, widths, rpn_cls_prob_reshapes, _num_anchors)]
# scores are (1 * H(P) * W(P) * A(P), 1) format
# reshape to (sum(1 * H * W * A), 1) where rows are ordered by (h, w, a)
scores = np.concatenate(scores, axis=0)
if DEBUG:
print('im_size: ({}, {})'.format(im_info[0], im_info[1]))
print('scale: {}'.format(im_info[2]))
# 1. Generate proposals from bbox deltas and shifted anchors
if DEBUG:
print('score map size: {}'.format(scores.shape))
def gen_shift(height, width, _feat_stride):
# Enumerate all shifts
shift_x = np.arange(0, width) * _feat_stride
shift_y = np.arange(0, height) * _feat_stride
shift_x, shift_y = np.meshgrid(shift_x, shift_y)
shift = np.vstack((shift_x.ravel(), shift_y.ravel(),
shift_x.ravel(), shift_y.ravel())).transpose()
return shift
shifts = [gen_shift(height, width, _feat_stride)
for height, width, _feat_stride in zip(heights, widths, _feat_strides)]
# Enumerate all shifted anchors:
#
# add A anchors (4, 1, A(x), 4) to
# cell K shifts (4, K, 1, 4) to get
# shift anchors (4, K, A(x), 4)
# reshape to (K*stack(A), 4) shifted anchors
As = _num_anchors
Ks = [shift.shape[0] for shift in shifts]
anchors = [_anchor.reshape((1, A, 4)) +
shift.reshape((1, K, 4)).transpose((1, 0, 2))
for A, K, _anchor, shift in zip(As, Ks, _anchors, shifts)]
anchors = [anchor.reshape((K * A, 4))
for anchor, A, K in zip(anchors, As, Ks)]
anchors = np.concatenate(anchors, axis=0)
# Transpose and reshape predicted bbox transformations to get them
# into the same order as the anchors:
#
# bbox deltas will be (1, 4 * A(x), H, W) format
# transpose to (1, H, W, 4 * A(x))
# reshape to (1 * H * W * A(x), 4) where rows are ordered by (h, w, a)
# in slowest to fastest order
#bbox_deltas = bbox_deltas.reshape((-1, 4)) #(HxWxA, 4)
bbox_deltas = [bbox_delta.reshape((-1, 4)) for bbox_delta in bbox_deltas]
bbox_deltas = np.concatenate(bbox_deltas, axis=0)
# Convert anchors into proposals via bbox transformations
proposals = bbox_transform_inv(anchors, bbox_deltas)
# 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)
blob = np.hstack((batch_inds, proposals.astype(np.float32, copy=False)))
rpn_rois = blob
if cfg_train_key == False:
# assign rois to level Pk (P2 ~ P6)
def calc_level(width, height):
return min(6, max(2, int(4 + np.log2(np.sqrt(width * height) / 224))))
level = lambda roi : calc_level(roi[3] - roi[1], roi[4] - roi[2]) # roi: [0, x0, y0, x1, y1]
leveled_rois = [None] * 5
leveled_idxs = [[], [], [], [], []]
for idx, roi in enumerate(rpn_rois):
level_idx = level(roi) - 2
leveled_idxs[level_idx].append(idx)
for level_idx in range(0, 5):
leveled_rois[level_idx] = rpn_rois[leveled_idxs[level_idx]]
rpn_rois = np.concatenate(leveled_rois, axis=0)
return leveled_rois[0], leveled_rois[1], leveled_rois[2], leveled_rois[3], leveled_rois[4], rpn_rois
return rpn_rois
def proposal_layer(rpn_cls_prob_reshape,
rpn_bbox_pred,
im_info,
cfg_key=True,
_feat_stride=cfg.ZLRM.RESNET_50_FEAT_STRIDE,
anchor_scales=cfg.ZLRM.ANCHOR_SCALE):
"""
Parameters
----------
rpn_cls_prob_reshape: (1 , H , W , Ax2) outputs of RPN, prob of bg or fg
NOTICE: the old version is ordered by (1, H, W, 2, A) !!!!
rpn_bbox_pred: (1 , H , W , Ax4), rgs boxes output of RPN
im_info: a list of [image_height, image_width, scale_ratios]
cfg_key: 'TRAIN' or 'TEST'
_feat_stride: the downsampling ratio of feature map to the original input image
anchor_scales: the scales to the basic_anchor (basic anchor is [16, 16])
----------
Returns
----------
rpn_rois : (1 x H x W x A, 5) e.g. [0, x1, y1, x2, y2]
# 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)
#layer_params = yaml.load(self.param_str_)
"""
_anchors = generate_anchors(scales=np.array(anchor_scales))
_num_anchors = _anchors.shape[0]
# rpn_cls_prob_reshape = np.transpose(rpn_cls_prob_reshape,[0,3,1,2]) #-> (1 , 2xA, H , W)
# rpn_bbox_pred = np.transpose(rpn_bbox_pred,[0,3,1,2]) # -> (1 , Ax4, H , W)
#rpn_cls_prob_reshape = np.transpose(np.reshape(rpn_cls_prob_reshape,[1,rpn_cls_prob_reshape.shape[0],rpn_cls_prob_reshape.shape[1],rpn_cls_prob_reshape.shape[2]]),[0,3,2,1])
#rpn_bbox_pred = np.transpose(rpn_bbox_pred,[0,3,2,1])
im_info = im_info[0]
assert rpn_cls_prob_reshape.shape[0] == 1, \
'Only single item batches are supported'
# cfg_key = str(self.phase) # either 'TRAIN' or 'TEST'
#cfg_key = 'TEST'
# print('========================', cfg.ZLRM.TRAIN.RPN_PRE_NMS_TOP_N)
# print('===================', cfg_key)
if cfg_key == True:
# print('使用TEST')
pre_nms_topN = cfg.ZLRM.TRAIN.RPN_PRE_NMS_TOP_N # 12000
post_nms_topN = cfg.ZLRM.TRAIN.RPN_POST_NMS_TOP_N # 2000
nms_thresh = cfg.ZLRM.TRAIN.RPN_NMS_THRESH # 0.7
min_size = cfg.ZLRM.TRAIN.RPN_MIN_SIZE # 16
else:
pre_nms_topN = cfg.ZLRM.TEST.RPN_PRE_NMS_TOP_N # 6000
post_nms_topN = cfg.ZLRM.TEST.RPN_POST_NMS_TOP_N # 300
nms_thresh = cfg.ZLRM.TEST.RPN_NMS_THRESH # 0.7
min_size = cfg.ZLRM.TEST.RPN_MIN_SIZE # 16
height, width = rpn_cls_prob_reshape.shape[1:3]
# the first set of _num_anchors channels are bg probs
# the second set are the fg probs, which we want
# (1, H, W, A)
scores = np.reshape(
np.reshape(rpn_cls_prob_reshape,
[1, height, width, _num_anchors, 2])[:, :, :, :, 1],
[1, height, width, _num_anchors])
# TODO: NOTICE: the old version is ordered by (1, H, W, 2, A) !!!!
# TODO: if you use the old trained model, VGGnet_fast_rcnn_iter_70000.ckpt, uncomment this line
# scores = rpn_cls_prob_reshape[:,:,:,_num_anchors:]
bbox_deltas = rpn_bbox_pred
#im_info = bottom[2].data[0, :]
if DEBUG:
print('im_size: ({}, {})'.format(im_info[0], im_info[1]))
print('scale: {}'.format(im_info[2]))
# 1. Generate proposals from bbox deltas and shifted anchors
if DEBUG:
print('score map size: {}'.format(scores.shape))
# Enumerate all shifts
shift_x = np.arange(0, width) * _feat_stride
shift_y = np.arange(0, height) * _feat_stride
shift_x, shift_y = 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 = _num_anchors
K = shifts.shape[0]
anchors = _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.reshape((-1, 4)) #(HxWxA, 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.reshape((-1, 1))
# Convert anchors into proposals via bbox transformations
proposals = bbox_transform_inv(anchors, bbox_deltas)
# 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]
# # remove irregular boxes, too fat too tall
# keep = _filter_irregular_boxes(proposals)
# 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)
blob = np.hstack((batch_inds, proposals.astype(np.float32, copy=False)))
# dets = np.hstack((blob, scores)).astype(np.float32)
# print(dets.shape)
# print('jjjjj=============', dets[:, -1])
return blob, scores