def forward(self, bottom, top):
# Text Quad
# Proposal ROIS(0, x1, y1, x2, y2, x3, y3, x4, y4)
all_rois = bottom[0].data
# GT boxes (x1, y1, x2, y2, x3, y3, x4, y4, label)
gt_boxes = bottom[1].data
# Include ground-truth boxes in the set of candidate rois
zeros = np.zeros((gt_boxes.shape[0], 1), dtype=gt_boxes.dtype)
all_rois = np.vstack((all_rois, np.hstack((zeros, gt_boxes[:, :-1]))))
# Sanity check: single batch only
assert np.all(
all_rois[:, 0] == 0), 'Only single item batches are supported'
num_images = 1
rois_per_image = cfg.TRAIN.BATCH_SIZE / num_images
fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)
# Sample rois with classification labels and bounding box regression targets
labels, quads, bbox_targets, bbox_inside_weights = _sample_rois(
all_rois, gt_boxes, fg_rois_per_image, rois_per_image,
self._num_classes, self._num_weights)
# dual rois pooling module
if cfg.DUAL_ROI:
rois = quad_2_obb(np.array(quads[:, 1:9], dtype=np.float32))
rois = dual_roi(rois)
else:
rois = quad_2_obb(quads[:, 1:9])
batch_inds = np.zeros((rois.shape[0], 1), dtype=np.float32)
rois = np.hstack((batch_inds, rois.astype(np.float32, copy=False)))
if DEBUG:
print '#num fg: {}'.format((labels == 1).sum())
print '%num bg: {}'.format((labels == 0).sum())
# sampled rois
top[0].reshape(*rois.shape)
top[0].data[...] = rois
# classification labels
top[1].reshape(*labels.shape)
top[1].data[...] = labels
# bbox_targets
top[2].reshape(*bbox_targets.shape)
top[2].data[...] = bbox_targets
# bbox_inside_weights
top[3].reshape(*bbox_inside_weights.shape)
top[3].data[...] = bbox_inside_weights
# bbox_outside_weights
top[4].reshape(*bbox_inside_weights.shape)
top[4].data[...] = np.array(bbox_inside_weights > 0).astype(np.float32)
def forward(self, bottom, top):
# params
cfg_key = self.phase # either 'TRAIN' or 'TEST'
if cfg_key == 0:
cfg_ = cfg.TRAIN
else:
cfg_ = cfg.TEST
# corner params
pt_thres = cfg_.PT_THRESH
pt_max_num = cfg.PT_MAX_NUM
pt_nms_range = cfg.PT_NMS_RANGE
pt_nms_thres = cfg.PT_NMS_THRESH
# proposal params
ld_interval = cfg.LD_INTERVAL
ld_um_thres = cfg.LD_UM_THRESH
# rpn params
# min_size = cfg_.RPN_MIN_SIZE
nms_thresh = cfg_.RPN_NMS_THRESH
pre_nms_topN = cfg_.RPN_PRE_NMS_TOP_N
post_nms_topN = cfg_.RPN_POST_NMS_TOP_N
im_info = bottom[0].data[0, :]
score_tl = bottom[1].data[0, :].transpose((1, 2, 0))
score_tr = bottom[2].data[0, :].transpose((1, 2, 0))
score_br = bottom[3].data[0, :].transpose((1, 2, 0))
score_bl = bottom[4].data[0, :].transpose((1, 2, 0))
scores = np.concatenate([
score_tl[:, :, :, np.newaxis], score_tr[:, :, :, np.newaxis],
score_br[:, :, :, np.newaxis], score_bl[:, :, :, np.newaxis]
],
axis=3)
map_info = scores.shape[:2]
# 1. sample corner candidates from prob maps
tl, tr, br, bl = _corner_sampling(scores, pt_thres, pt_max_num,
pt_nms_range, pt_nms_thres)
# 2. assemble corner candidates into proposals
proposals = _proposal_sampling(tl, tr, br, bl, map_info, ld_interval,
ld_um_thres)
# 3. filter
proposals = filter_quads(proposals)
scores = proposals[:, 8]
proposals = proposals[:, :8]
# 3. rescale quads into raw image space
proposals = proposals * self._feat_stride
# 4. quadrilateral non-max surpression
order = scores.ravel().argsort()[::-1]
if pre_nms_topN > 0:
order = order[:pre_nms_topN]
proposals = proposals[order, :]
scores = scores[order]
keep = nms(
np.hstack((proposals, scores[:, np.newaxis])).astype(np.float32,
copy=False),
nms_thresh)
proposals = proposals[keep, :]
scores = scores[keep]
if post_nms_topN > 0:
proposals = proposals[:post_nms_topN, :]
scores = scores[:post_nms_topN]
if proposals.shape[0] == 0:
# add whole image to avoid error
print('NO PROPOSALS!')
proposals = np.array(
[[0, 0, im_info[1], 0, im_info[1], im_info[0], 0, im_info[0]]])
scores = np.array([0.0])
# output
# top[0]: quads(x1, y1, x2, y2, x3, y3, x4, y4)
# top[1]: rois(xmin, ymin, xmax, ymax, theta)
# top[2]: scores
batch_inds = np.zeros((proposals.shape[0], 1), dtype=np.float32)
blob = np.hstack((batch_inds, proposals.astype(np.float32,
copy=False)))
top[0].reshape(*blob.shape)
top[0].data[...] = blob
if len(top) > 1:
if cfg.DUAL_ROI:
rois = quad_2_obb(np.array(proposals, dtype=np.float32))
rois = dual_roi(rois)
else:
rois = quad_2_obb(np.array(proposals, dtype=np.float32))
batch_inds = np.zeros((rois.shape[0], 1), dtype=np.float32)
blob = np.hstack((batch_inds, rois.astype(np.float32, copy=False)))
top[1].reshape(*blob.shape)
top[1].data[...] = blob
if len(top) > 2:
scores = np.vstack((scores, scores)).transpose()
top[2].reshape(*scores.shape)
top[2].data[...] = scores