def forward(self, feature_maps, gt_bboxes=None, img_shape=None):
"""
Args:
feature_maps(Variable): [p2, p3, p4, p5, p6] or [c5], feature pyramid or single feature
map.
gt_bboxes(Tensor): [N, M, (x1, y1, x2, y2)].
img_shape(Tensor): [height, width], Image shape.
Returns:
rois(Tensor): [N, M, (idx, x1, y1, x2, y2)] N: batch size, M: number of roi after
nms, idx: bbox index in mini-batch.
rpn_loss_cls(Tensor): Classification loss
rpn_loss_bbo(Tensor)x: Bounding box regression loss
"""
batch_size = feature_maps[0].size(0)
assert batch_size == 1, "batch_size > 1 will add support later."
if self.use_fpn:
if self.training:
post_nms_top_n = int(self.config['FPN']['TRAIN_FPN_POST_NMS_TOP_N'])
nms_thresh = float(self.config['FPN']['TRAIN_FPN_NMS_THRESH'])
else:
post_nms_top_n = int(self.config['FPN']['TEST_FPN_POST_NMS_TOP_N'])
nms_thresh = float(self.config['FPN']['TEST_FPN_NMS_THRESH'])
rois_pre_nms = []
rpn_loss_cls = 0
rpn_loss_bbox = 0
for idx, feature in enumerate(feature_maps):
self.rpn.RPN_anchor_target = self.RPN_anchor_targets[idx]
self.rpn.RPN_proposal = self.RPN_proposals[idx]
rpn_result = self.rpn(feature, img_shape, gt_bboxes, None)
roi_single, loss_cls_single, loss_bbox_single = rpn_result
rpn_loss_cls += loss_cls_single
rpn_loss_bbox += loss_bbox_single
rois_pre_nms.append(roi_single)
rois_pre_nms = torch.cat(rois_pre_nms, 1) # [N, M, (n, score, x1, y1, x2, y2)].
# Apply nms to result of all pyramid rois.
score = rois_pre_nms[0, :, 1]
score.unsqueeze_(-1)
bbox = rois_pre_nms[0, :, 2:]
keep_idx = nms(torch.cat([bbox, score], 1), nms_thresh)
keep_idx = keep_idx[:post_nms_top_n]
rois_per_img = torch.cat([rois_pre_nms[:, idx, :] for idx in keep_idx])
rois = rois_per_img[:, [0, 2, 3, 4, 5]] # remove roi_score
rois = rois.unsqueeze(0)
rpn_loss_cls /= len(feature_maps)
rpn_loss_bbox /= len(feature_maps)
else:
rpn_result = self.rpn(feature_maps[0], img_shape, gt_bboxes, None)
rois_rpn, rpn_loss_cls, rpn_loss_bbox = rpn_result
rois = rois_rpn[:, :, [0, 2, 3, 4, 5]] # remove roi_score
return rois, rpn_loss_cls, rpn_loss_bbox
def forward(self, feature_maps, gt_bboxes=None, img_shape=None):
"""
Args:
feature_maps: [p2, p3, p4, p5, p6] or [c5], feature pyramid or single feature map.
gt_bboxes: [N, M, (x1, y1, x2, y2)].
img_shape: [height, width], Image shape.
Returns:
rois(Tensor): [N, M, (idx, x1, y1, x2, y2)] N: batch size, M: number of roi after nms,
idx: bbox index in mini-batch.
rpn_loss_cls(Tensor): Classification loss
rpn_loss_bbo(Tensor)x: Bounding box regression loss
"""
batch_size = feature_maps[0].size(0)
nms_output_num = cfg.TEST.RPN_POST_NMS_TOP_N
if self.training:
nms_output_num = cfg.TRAIN.RPN_POST_NMS_TOP_N
if self.use_fpn:
rois_pre_nms = []
rpn_loss_cls = 0
rpn_loss_bbox = 0
for idx, feature in enumerate(feature_maps):
self.rpn.RPN_anchor_target = self.RPN_anchor_targets[idx]
self.rpn.RPN_proposal = self.RPN_proposals[idx]
rpn_result = self.rpn(feature, img_shape, gt_bboxes, None)
roi_single, loss_cls_single, loss_bbox_single = rpn_result
rpn_loss_cls += loss_cls_single
rpn_loss_bbox += loss_bbox_single
roi_score = roi_single[:, :, 1]
roi_bbox = roi_single[:, :, 2:]
roi_score.unsqueeze_(-1)
rois_pre_nms.append(torch.cat((roi_bbox, roi_score), 2))
rois_pre_nms = torch.cat(rois_pre_nms,
1) # [N, M, 5], torch.cat() at dim 'M'.
rois = feature_maps[0].data.new(batch_size, nms_output_num,
5).zero_()
# Apply nms to result of all pyramid rois.
for i in range(batch_size):
keep_idx = nms(rois_pre_nms[i], cfg.TRAIN.RPN_NMS_THRESH)
keep_idx = keep_idx[:nms_output_num]
rois_per_img = torch.cat(
[rois_pre_nms[i, idx, :].unsqueeze(0) for idx in keep_idx])
rois[i, :, 0] = i
rois[i, :rois_per_img.size(0),
1:] = rois_per_img[:, :4] # remove roi_score
else:
rpn_result = self.rpn(feature_maps[0], img_shape, gt_bboxes, None)
rois_rpn, rpn_loss_cls, rpn_loss_bbox = rpn_result
rois = feature_maps[0].data.new(batch_size, nms_output_num,
5).zero_()
rois[:, :, 0] = 0
rois[:, :, 1:] = rois_rpn[:, :, 2:] # remove roi_score
return rois, rpn_loss_cls, rpn_loss_bbox
def forward(self, input):
# 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)
# the first set of _num_anchors channels are bg probs
# the second set are the fg probs
scores = input[0][:, self._num_anchors:, :, :]
bbox_deltas = input[1]
im_info = input[2]
cfg_key = input[3]
pre_nms_topN = cfg[cfg_key].RPN_PRE_NMS_TOP_N
post_nms_topN = cfg[cfg_key].RPN_POST_NMS_TOP_N
nms_thresh = cfg[cfg_key].RPN_NMS_THRESH
min_size = cfg[cfg_key].RPN_MIN_SIZE
batch_size = bbox_deltas.size(0)
feat_height, feat_width = scores.size(2), scores.size(3)
shift_x = np.arange(0, feat_width) * self._feat_stride
shift_y = np.arange(0, feat_height) * self._feat_stride
shift_x, shift_y = np.meshgrid(shift_x, shift_y)
shifts = torch.from_numpy(
np.vstack((shift_x.ravel(), shift_y.ravel(), shift_x.ravel(),
shift_y.ravel())).transpose())
shifts = shifts.contiguous().type_as(scores).float()
A = self._num_anchors
K = shifts.size(0)
self._anchors = self._anchors.type_as(scores)
# anchors = self._anchors.view(1, A, 4) + shifts.view(1, K, 4).permute(1, 0, 2).contiguous()
anchors = self._anchors.view(1, A, 4) + shifts.view(K, 1, 4)
anchors = anchors.view(1, K * A, 4).expand(batch_size, K * A, 4)
# Transpose and reshape predicted bbox transformations to get them
# into the same order as the anchors:
bbox_deltas = bbox_deltas.permute(0, 2, 3, 1).contiguous()
bbox_deltas = bbox_deltas.view(batch_size, -1, 4)
# Same story for the scores:
scores = scores.permute(0, 2, 3, 1).contiguous()
scores = scores.view(batch_size, -1)
# Convert anchors into proposals via bbox transformations
proposals = bbox_transform_inv(anchors, bbox_deltas, batch_size)
# 2. clip predicted boxes to image
proposals = clip_boxes(proposals, im_info, batch_size)
# proposals = clip_boxes_batch(proposals, im_info, batch_size)
# assign the score to 0 if it's non keep.
# keep = self._filter_boxes(proposals, min_size * im_info[:, 2])
# trim keep index to make it euqal over batch
# keep_idx = torch.cat(tuple(keep_idx), 0)
# scores_keep = scores.view(-1)[keep_idx].view(batch_size, trim_size)
# proposals_keep = proposals.view(-1, 4)[keep_idx, :].contiguous().view(batch_size, trim_size, 4)
# _, order = torch.sort(scores_keep, 1, True)
scores_keep = scores
proposals_keep = proposals
if not self.training:
# filter out score below threshold
assert batch_size == 1
scores_keep_idx = torch.nonzero(scores_keep > 0.5).view(-1)
if scores_keep_idx.numel() != 0:
scores_keep = scores_keep[:, scores_keep_idx]
proposals_keep = proposals_keep[:, scores_keep_idx]
_, order = torch.sort(scores_keep, 1, True)
output = scores.new(batch_size, post_nms_topN, 6).zero_()
for i in range(batch_size):
# # 3. remove predicted boxes with either height or width < threshold
# # (NOTE: convert min_size to input image scale stored in im_info[2])
proposals_single = proposals_keep[i]
scores_single = scores_keep[i]
# # 4. sort all (proposal, score) pairs by score from highest to lowest
# # 5. take top pre_nms_topN (e.g. 6000)
order_single = order[i]
if pre_nms_topN > 0 and pre_nms_topN < scores_keep.numel():
order_single = order_single[:pre_nms_topN]
proposals_single = proposals_single[order_single, :]
scores_single = scores_single[order_single].view(-1, 1)
# 6. apply nms (e.g. threshold = 0.7)
# 7. take after_nms_topN (e.g. 300)
# 8. return the top proposals (-> RoIs top)
keep_idx_i = nms(torch.cat((proposals_single, scores_single), 1),
nms_thresh)
keep_idx_i = keep_idx_i.long().view(-1)
if post_nms_topN > 0:
keep_idx_i = keep_idx_i[:post_nms_topN]
proposals_single = proposals_single[keep_idx_i, :]
scores_single = scores_single[keep_idx_i, :]
# padding 0 at the end.
num_proposal = proposals_single.size(0)
output[i, :, 0] = i
output[i, :num_proposal, 1] = scores_single
output[i, :num_proposal, 2:] = proposals_single
return output
def _process_result(self,
batch_size,
features,
proposals,
cls_prob=None,
bbox_reg=None):
"""Get the final result in test stage.
Args:
batch_size(int): mini-batch size.
features(list of Variable): extracted features from backbone
proposals(Tensor): [N, M, (idx, score, x1, y1, x2, y2)]
cls_prob(Variable): [(NxM), num_classes]
bbox_reg(Variable): [(NxM), num_classes, (x1, y1, x2, y2)]
Returns:
result: list of lists of dict, outer list is mini-batch, inner list is detected objects,
dict contains stuff below.
dict_key:
'proposal'(Tensor): (x1, y1, x2, y2), course bbox from RPN proposal.
'cls_pred'(int): predicted class id.
'bbox_pred'(Tensor): (x1, y1, x2, y2), refined bbox from prediction head.
'mask_pred'(Tensor): [H, W], predicted mask.
e.g. result[0][0]['mask_pred'] stands for the first object's mask prediction of
the first image of mini-batch.
"""
# Todo: support batch_size > 1.
assert batch_size == 1, "batch_size > 1 will add support later"
proposals = proposals.squeeze(0)
result = []
if self.train_rpn_only:
obj_detected = []
for i in range(proposals.size(0)):
pred_dict = {'proposal': proposals[i, 2:].cpu()}
obj_detected.append(pred_dict)
result.append(obj_detected)
return result
else:
props = []
bboxes = []
cls_ids = []
for idx, roi in enumerate(proposals):
cls_id = torch.max(cls_prob[idx], dim=0)[1]
if int(cls_id) > 0: # remove background
# refine proposal bbox with bbox regression result.
bbox = self._refine_proposal(
roi[2:],
bbox_reg[idx, :, :][cls_id, :].squeeze(0).data)
px1, py1, px2, py2 = bbox
# leave malformed bbox alone
if py1 >= py2 or px1 >= px2:
continue
props.append(roi.unsqueeze(0))
bboxes.append(bbox.unsqueeze(0))
cls_ids.append(int(cls_id))
if len(props) != 0:
props_origin = torch.cat(props)
props_refined = props_origin.clone()
props_refined[:, 2:] = torch.cat(bboxes)
else:
result.append([])
return result
# Apply nms.
if self.use_fpn:
pre_nms_top_n = int(
self.config['FPN']['TEST_FPN_PRE_NMS_TOP_N'])
post_nms_top_n = int(
self.config['FPN']['TEST_FPN_POST_NMS_TOP_N'])
nms_thresh = float(self.config['FPN']['TEST_FPN_NMS_THRESH'])
else:
pre_nms_top_n = int(
self.config['RPN']['TEST_RPN_PRE_NMS_TOP_N'])
post_nms_top_n = int(
self.config['RPN']['TEST_RPN_POST_NMS_TOP_N'])
nms_thresh = float(self.config['RPN']['TEST_RPN_NMS_THRESH'])
score = props_refined[:, 1]
order = torch.sort(score, dim=0, descending=True)[1]
props_origin = props_origin[order, :][:pre_nms_top_n, :]
props_refined = props_refined[order, :][:pre_nms_top_n, :]
score = props_refined[:, 1].unsqueeze(-1)
bbox = props_refined[:, 2:]
keep_idx = nms(torch.cat([bbox, score], 1), nms_thresh)
keep_idx = keep_idx[:post_nms_top_n]
props_origin = torch.cat(
[props_origin[idx, :].unsqueeze(0) for idx in keep_idx])
props_refined = torch.cat(
[props_refined[idx, :].unsqueeze(0) for idx in keep_idx])
if self.use_fpn:
rois_pooling_mask = self._roi_align_fpn(features,
props_refined.clone(),
mode='mask')
mask_prob = self.mask_head(rois_pooling_mask).data
else:
rois_pooling_mask = self.roi_align_mask(
features[0], props_refined.clone(), self.img_height)
mask_prob = self.mask_head(rois_pooling_mask).data
obj_detected = []
for i in range(len(props_origin)):
pred_dict = {
'proposal': props_origin[i, 2:].cpu(),
'cls_pred': cls_ids[i],
'bbox_pred': props_refined[i, 2:].cpu(),
'mask_pred': None
}
px1, py1, px2, py2 = props_refined[i, 2:].int()
mask_height, mask_width = py2 - py1 + 1, px2 - px1 + 1
mask = mask_prob[i, :, :, :][cls_ids[i], :, :]
mask = Variable(mask.unsqueeze(0), requires_grad=False)
mask_resize = F.adaptive_avg_pool2d(
mask, (mask_height, mask_width)).data
mask_threshold = float(self.config['TEST']['MASK_THRESH'])
mask_resize = mask_resize >= mask_threshold
mask_pred = mask_prob.new(self.img_height,
self.img_width).zero_()
mask_pred[py1:py2 + 1, px1:px2 + 1] = mask_resize
pred_dict['mask_pred'] = mask_pred.cpu()
obj_detected.append(pred_dict)
result.append(obj_detected)
return result