def roi_heads(self, image, features, proposals, targets):
image_shape2d = tf.shape(image)[2:] # h,w
featuremap = features[0]
gt_boxes, gt_labels, *_ = targets
if self.training:
# sample proposal boxes in training
proposals = sample_fast_rcnn_targets(proposals.boxes, gt_boxes, gt_labels)
# The boxes to be used to crop RoIs.
# Use all proposal boxes in inference
boxes_on_featuremap = proposals.boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE)
roi_resized = roi_align(featuremap, boxes_on_featuremap, 14)
feature_fastrcnn = resnet_conv5(roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCKS[-1]) # nxcx7x7
# Keep C5 feature to be shared with mask branch
feature_gap = GlobalAvgPooling('gap', feature_fastrcnn, data_format='channels_first')
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_outputs('fastrcnn', feature_gap, cfg.DATA.NUM_CLASS)
fastrcnn_head = FastRCNNHead(proposals, fastrcnn_box_logits, fastrcnn_label_logits, gt_boxes,
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS, dtype=tf.float32))
if self.training:
all_losses = fastrcnn_head.losses()
if cfg.MODE_MASK:
gt_masks = targets[2]
# maskrcnn loss
# In training, mask branch shares the same C5 feature.
fg_feature = tf.gather(feature_fastrcnn, proposals.fg_inds())
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', fg_feature, cfg.DATA.NUM_CATEGORY, num_convs=0) # #fg x #cat x 14x14
target_masks_for_fg = crop_and_resize(
tf.expand_dims(gt_masks, 1),
proposals.fg_boxes(),
proposals.fg_inds_wrt_gt, 14,
pad_border=False) # nfg x 1x14x14
target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1, 'sampled_fg_mask_targets')
all_losses.append(maskrcnn_loss(mask_logits, proposals.fg_labels(), target_masks_for_fg))
return all_losses
else:
decoded_boxes = fastrcnn_head.decoded_output_boxes()
decoded_boxes = clip_boxes(decoded_boxes, image_shape2d, name='fastrcnn_all_boxes')
label_scores = fastrcnn_head.output_scores(name='fastrcnn_all_scores')
final_boxes, final_scores, final_labels = fastrcnn_predictions(
decoded_boxes, label_scores, name_scope='output')
if cfg.MODE_MASK:
roi_resized = roi_align(featuremap, final_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE), 14)
feature_maskrcnn = resnet_conv5(roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCKS[-1])
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', feature_maskrcnn, cfg.DATA.NUM_CATEGORY, 0) # #result x #cat x 14x14
indices = tf.stack([tf.range(tf.size(final_labels)), tf.cast(final_labels, tf.int32) - 1], axis=1)
final_mask_logits = tf.gather_nd(mask_logits, indices) # #resultx14x14
tf.sigmoid(final_mask_logits, name='output/masks')
return []
def build_graph(self, *inputs):
# TODO need to make tensorpack handles dict better
inputs = dict(zip(self.input_names, inputs))
is_training = get_current_tower_context().is_training
image = self.preprocess(inputs['image']) # 1CHW
featuremap = resnet_c4_backbone(image,
cfg.BACKBONE.RESNET_NUM_BLOCK[:3])
rpn_label_logits, rpn_box_logits = rpn_head('rpn', featuremap,
cfg.RPN.HEAD_DIM,
cfg.RPN.NUM_ANCHOR)
anchors = RPNAnchors(get_all_anchors(), inputs['anchor_labels'],
inputs['anchor_boxes'])
anchors = anchors.narrow_to(featuremap)
image_shape2d = tf.shape(image)[2:] # h,w
pred_boxes_decoded = anchors.decode_logits(
rpn_box_logits) # fHxfWxNAx4, floatbox
proposal_boxes, proposal_scores = generate_rpn_proposals(
tf.reshape(pred_boxes_decoded, [-1, 4]),
tf.reshape(rpn_label_logits,
[-1]), image_shape2d, cfg.RPN.TRAIN_PRE_NMS_TOPK
if is_training else cfg.RPN.TEST_PRE_NMS_TOPK,
cfg.RPN.TRAIN_POST_NMS_TOPK
if is_training else cfg.RPN.TEST_POST_NMS_TOPK)
gt_boxes, gt_labels = inputs['gt_boxes'], inputs['gt_labels']
if is_training:
# sample proposal boxes in training
proposals = sample_fast_rcnn_targets(proposal_boxes, gt_boxes,
gt_labels)
else:
# The boxes to be used to crop RoIs.
# Use all proposal boxes in inference
proposals = BoxProposals(proposal_boxes)
boxes_on_featuremap = proposals.boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE)
roi_resized = roi_align(featuremap, boxes_on_featuremap, 14)
feature_fastrcnn = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1]) # nxcx7x7
# Keep C5 feature to be shared with mask branch
feature_gap = GlobalAvgPooling('gap',
feature_fastrcnn,
data_format='channels_first')
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_outputs(
'fastrcnn', feature_gap, cfg.DATA.NUM_CLASS)
fastrcnn_head = FastRCNNHead(
proposals, fastrcnn_box_logits, fastrcnn_label_logits,
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS, dtype=tf.float32))
if is_training:
all_losses = []
# rpn loss
all_losses.extend(
rpn_losses(anchors.gt_labels, anchors.encoded_gt_boxes(),
rpn_label_logits, rpn_box_logits))
# fastrcnn loss
all_losses.extend(fastrcnn_head.losses())
if cfg.MODE_MASK:
# maskrcnn loss
# In training, mask branch shares the same C5 feature.
fg_feature = tf.gather(feature_fastrcnn, proposals.fg_inds())
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', fg_feature, cfg.DATA.NUM_CATEGORY,
num_convs=0) # #fg x #cat x 14x14
target_masks_for_fg = crop_and_resize(
tf.expand_dims(inputs['gt_masks'], 1),
proposals.fg_boxes(),
proposals.fg_inds_wrt_gt,
14,
pad_border=False) # nfg x 1x14x14
target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1,
'sampled_fg_mask_targets')
all_losses.append(
maskrcnn_loss(mask_logits, proposals.fg_labels(),
target_masks_for_fg))
wd_cost = regularize_cost('.*/W',
l2_regularizer(cfg.TRAIN.WEIGHT_DECAY),
name='wd_cost')
all_losses.append(wd_cost)
total_cost = tf.add_n(all_losses, 'total_cost')
add_moving_summary(total_cost, wd_cost)
return total_cost
else:
decoded_boxes = fastrcnn_head.decoded_output_boxes()
decoded_boxes = clip_boxes(decoded_boxes,
image_shape2d,
name='fastrcnn_all_boxes')
label_scores = fastrcnn_head.output_scores(
name='fastrcnn_all_scores')
final_boxes, final_scores, final_labels = fastrcnn_predictions(
decoded_boxes, label_scores, name_scope='output')
if cfg.MODE_MASK:
roi_resized = roi_align(
featuremap, final_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE),
14)
feature_maskrcnn = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', feature_maskrcnn, cfg.DATA.NUM_CATEGORY,
0) # #result x #cat x 14x14
indices = tf.stack([
tf.range(tf.size(final_labels)),
tf.to_int32(final_labels) - 1
],
axis=1)
final_mask_logits = tf.gather_nd(mask_logits,
indices) # #resultx14x14
tf.sigmoid(final_mask_logits, name='output/masks')
def build_graph(self, *inputs):
is_training = get_current_tower_context().is_training
if cfg.MODE_MASK:
image, anchor_labels, anchor_boxes, gt_boxes, gt_labels, gt_masks = inputs
else:
image, anchor_labels, anchor_boxes, gt_boxes, gt_labels = inputs
image = self.preprocess(image) # 1CHW
#with varreplace.freeze_variables(stop_gradient=True, skip_collection=True):
featuremap = resnet_c4_backbone(image, cfg.BACKBONE.RESNET_NUM_BLOCK[:3])
# freeze
# featuremap = tf.stop_gradient(featuremap)
rpn_label_logits, rpn_box_logits = rpn_head('rpn', featuremap, cfg.RPN.HEAD_DIM, cfg.RPN.NUM_ANCHOR)
anchors = RPNAnchors(get_all_anchors(), anchor_labels, anchor_boxes)
anchors = anchors.narrow_to(featuremap)
image_shape2d = tf.shape(image)[2:] # h,w
pred_boxes_decoded = anchors.decode_logits(rpn_box_logits) # fHxfWxNAx4, floatbox
proposal_boxes, proposal_scores = generate_rpn_proposals(
tf.reshape(pred_boxes_decoded, [-1, 4]),
tf.reshape(rpn_label_logits, [-1]),
image_shape2d,
cfg.RPN.TRAIN_PRE_NMS_TOPK if is_training else cfg.RPN.TEST_PRE_NMS_TOPK,
cfg.RPN.TRAIN_POST_NMS_TOPK if is_training else cfg.RPN.TEST_POST_NMS_TOPK)
if is_training:
# sample proposal boxes in training
rcnn_boxes, rcnn_labels, fg_inds_wrt_gt = sample_fast_rcnn_targets(
proposal_boxes, gt_boxes, gt_labels)
else:
# The boxes to be used to crop RoIs.
# Use all proposal boxes in inference
rcnn_boxes = proposal_boxes
featuremap = resnet_conv5(featuremap, cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
rfcn_cls = Conv2D('rfcn_cls', featuremap, cfg.DATA.NUM_CLASS*3*3, (1, 1), data_format='channels_first')
rfcn_reg = Conv2D('rfcn_reg', featuremap, cfg.DATA.NUM_CLASS*4*3*3, (1, 1), data_format='channels_first')
boxes_on_featuremap = rcnn_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE)
classify_vote = VotePooling('votepooling_cls', rfcn_cls, boxes_on_featuremap, 3, 3)
classify_regr = VotePooling('votepooling_regr', rfcn_reg, boxes_on_featuremap, 3, 3, isCls=False)
classify_regr = tf.reshape(classify_regr, [-1, cfg.DATA.NUM_CLASS, 4])
if is_training:
# rpn loss
rpn_label_loss, rpn_box_loss = rpn_losses(
anchors.gt_labels, anchors.encoded_gt_boxes(), rpn_label_logits, rpn_box_logits)
# fastrcnn loss
matched_gt_boxes = tf.gather(gt_boxes, fg_inds_wrt_gt)
fg_inds_wrt_sample = tf.reshape(tf.where(rcnn_labels > 0), [-1]) # fg inds w.r.t all samples
fg_sampled_boxes = tf.gather(rcnn_boxes, fg_inds_wrt_sample)
fg_fastrcnn_box_logits = tf.gather(classify_regr, fg_inds_wrt_sample)
fastrcnn_label_loss, fastrcnn_box_loss = self.fastrcnn_training(
image, rcnn_labels, fg_sampled_boxes,
matched_gt_boxes, classify_vote, fg_fastrcnn_box_logits)
if cfg.MODE_MASK:
# maskrcnn loss
fg_labels = tf.gather(rcnn_labels, fg_inds_wrt_sample)
# In training, mask branch shares the same C5 feature.
fg_feature = tf.gather(feature_fastrcnn, fg_inds_wrt_sample)
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', fg_feature, cfg.DATA.NUM_CATEGORY, num_convs=0) # #fg x #cat x 14x14
target_masks_for_fg = crop_and_resize(
tf.expand_dims(gt_masks, 1),
fg_sampled_boxes,
fg_inds_wrt_gt, 14,
pad_border=False) # nfg x 1x14x14
target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1, 'sampled_fg_mask_targets')
mrcnn_loss = maskrcnn_loss(mask_logits, fg_labels, target_masks_for_fg)
else:
mrcnn_loss = 0.0
wd_cost = regularize_cost(
'.*/W', l2_regularizer(cfg.TRAIN.WEIGHT_DECAY), name='wd_cost')
total_cost = tf.add_n([
rpn_label_loss, rpn_box_loss,
fastrcnn_label_loss, fastrcnn_box_loss,
mrcnn_loss, wd_cost], 'total_cost')
add_moving_summary(total_cost, wd_cost)
return total_cost
else:
final_boxes, final_labels = self.fastrcnn_inference(
image_shape2d, rcnn_boxes, classify_vote, classify_regr)
if cfg.MODE_MASK:
roi_resized = roi_align(featuremap, final_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE), 14)
feature_maskrcnn = resnet_conv5(roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', feature_maskrcnn, cfg.DATA.NUM_CATEGORY, 0) # #result x #cat x 14x14
indices = tf.stack([tf.range(tf.size(final_labels)), tf.to_int32(final_labels) - 1], axis=1)
final_mask_logits = tf.gather_nd(mask_logits, indices) # #resultx14x14
tf.sigmoid(final_mask_logits, name='final_masks')
def build_graph(self, *inputs):
num_fpn_level = len(cfg.FPN.ANCHOR_STRIDES)
assert len(cfg.RPN.ANCHOR_SIZES) == num_fpn_level
is_training = get_current_tower_context().is_training
image = inputs[0]
input_anchors = inputs[1: 1 + 2 * num_fpn_level]
multilevel_anchors = [RPNAnchors(*args) for args in
zip(get_all_anchors_fpn(), input_anchors[0::2], input_anchors[1::2])]
gt_boxes, gt_labels = inputs[11], inputs[12]
if cfg.MODE_MASK:
gt_masks = inputs[-1]
image = self.preprocess(image) # 1CHW
image_shape2d = tf.shape(image)[2:] # h,w
c2345 = resnet_fpn_backbone(image, cfg.BACKBONE.RESNET_NUM_BLOCK)
p23456 = fpn_model('fpn', c2345)
self.slice_feature_and_anchors(image_shape2d, p23456, multilevel_anchors)
# Multi-Level RPN Proposals
rpn_outputs = [rpn_head('rpn', pi, cfg.FPN.NUM_CHANNEL, len(cfg.RPN.ANCHOR_RATIOS))
for pi in p23456]
multilevel_label_logits = [k[0] for k in rpn_outputs]
multilevel_box_logits = [k[1] for k in rpn_outputs]
proposal_boxes, proposal_scores = generate_fpn_proposals(
multilevel_anchors, multilevel_label_logits,
multilevel_box_logits, image_shape2d)
if is_training:
rcnn_boxes, rcnn_labels, fg_inds_wrt_gt = sample_fast_rcnn_targets(
proposal_boxes, gt_boxes, gt_labels)
else:
# The boxes to be used to crop RoIs.
rcnn_boxes = proposal_boxes
roi_feature_fastrcnn = multilevel_roi_align(p23456[:4], rcnn_boxes, 7)
fastrcnn_head_func = getattr(model_frcnn, cfg.FPN.FRCNN_HEAD_FUNC)
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_head_func(
'fastrcnn', roi_feature_fastrcnn, cfg.DATA.NUM_CLASS)
if is_training:
# rpn loss:
rpn_label_loss, rpn_box_loss = multilevel_rpn_losses(
multilevel_anchors, multilevel_label_logits, multilevel_box_logits)
# fastrcnn loss:
matched_gt_boxes = tf.gather(gt_boxes, fg_inds_wrt_gt)
fg_inds_wrt_sample = tf.reshape(tf.where(rcnn_labels > 0), [-1]) # fg inds w.r.t all samples
fg_sampled_boxes = tf.gather(rcnn_boxes, fg_inds_wrt_sample)
fg_fastrcnn_box_logits = tf.gather(fastrcnn_box_logits, fg_inds_wrt_sample)
fastrcnn_label_loss, fastrcnn_box_loss = self.fastrcnn_training(
image, rcnn_labels, fg_sampled_boxes,
matched_gt_boxes, fastrcnn_label_logits, fg_fastrcnn_box_logits)
if cfg.MODE_MASK:
# maskrcnn loss
fg_labels = tf.gather(rcnn_labels, fg_inds_wrt_sample)
roi_feature_maskrcnn = multilevel_roi_align(
p23456[:4], fg_sampled_boxes, 14,
name_scope='multilevel_roi_align_mask')
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', roi_feature_maskrcnn, cfg.DATA.NUM_CATEGORY, 4) # #fg x #cat x 28 x 28
target_masks_for_fg = crop_and_resize(
tf.expand_dims(gt_masks, 1),
fg_sampled_boxes,
fg_inds_wrt_gt, 28,
pad_border=False) # fg x 1x28x28
target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1, 'sampled_fg_mask_targets')
mrcnn_loss = maskrcnn_loss(mask_logits, fg_labels, target_masks_for_fg)
else:
mrcnn_loss = 0.0
wd_cost = regularize_cost(
'(?:group1|group2|group3|rpn|fpn|fastrcnn|maskrcnn)/.*W',
l2_regularizer(cfg.TRAIN.WEIGHT_DECAY), name='wd_cost')
total_cost = tf.add_n([rpn_label_loss, rpn_box_loss,
fastrcnn_label_loss, fastrcnn_box_loss,
mrcnn_loss, wd_cost], 'total_cost')
add_moving_summary(total_cost, wd_cost)
return total_cost * (1. / cfg.TRAIN.NUM_GPUS)
else:
final_boxes, final_labels = self.fastrcnn_inference(
image_shape2d, rcnn_boxes, fastrcnn_label_logits, fastrcnn_box_logits)
if cfg.MODE_MASK:
# Cascade inference needs roi transform with refined boxes.
roi_feature_maskrcnn = multilevel_roi_align(p23456[:4], final_boxes, 14)
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', roi_feature_maskrcnn, cfg.DATA.NUM_CATEGORY, 4) # #fg x #cat x 28 x 28
indices = tf.stack([tf.range(tf.size(final_labels)), tf.to_int32(final_labels) - 1], axis=1)
final_mask_logits = tf.gather_nd(mask_logits, indices) # #resultx28x28
tf.sigmoid(final_mask_logits, name='final_masks')
def build_graph(self, *inputs):
is_training = get_current_tower_context().is_training
# if cfg.MODE_MASK:
# image, anchor_labels, anchor_boxes, gt_boxes, gt_labels, gt_masks = inputs
# else:
# image, anchor_labels, anchor_boxes, gt_boxes, gt_labels, scale_index = inputs
image, anchor_labels, anchor_boxes, gt_boxes, gt_labels = inputs
image = self.preprocess(image) # 1CHW
featuremap = resnet_c4_backbone(image,
cfg.BACKBONE.RESNET_NUM_BLOCK[:3])
rpn_label_logits, rpn_box_logits = rpn_head(
'rpn', featuremap, cfg.RPN.HEAD_DIM, cfg.RPN.NUM_ANCHOR)
anchors = RPNAnchors(get_all_anchors(), anchor_labels, anchor_boxes)
anchors = anchors.narrow_to(featuremap)
image_shape2d = tf.shape(image)[2:] # h,w
pred_boxes_decoded = anchors.decode_logits(
rpn_box_logits) # fHxfWxNAx4, floatbox
proposal_boxes, proposal_scores = generate_rpn_proposals(
tf.reshape(pred_boxes_decoded, [-1, 4]),
tf.reshape(rpn_label_logits,
[-1]), image_shape2d, cfg.RPN.TRAIN_PRE_NMS_TOPK
if is_training else cfg.RPN.TEST_PRE_NMS_TOPK,
cfg.RPN.TRAIN_POST_NMS_TOPK
if is_training else cfg.RPN.TEST_POST_NMS_TOPK)
if is_training:
# sample proposal boxes in training
# rcnn_boxes, rcnn_labels, fg_inds_wrt_gt = sample_sniper_targets(
# proposal_boxes, gt_boxes, gt_labels, scale_index)
rcnn_boxes, rcnn_labels, fg_inds_wrt_gt = sample_sniper_targets(
proposal_boxes, gt_boxes, gt_labels)
else:
# The boxes to be used to crop RoIs.
# Use all proposal boxes in inference
rcnn_boxes = proposal_boxes
boxes_on_featuremap = rcnn_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE)
roi_resized = roi_align(featuremap, boxes_on_featuremap, 14)
feature_fastrcnn = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1]) # nxcx7x7
# Keep C5 feature to be shared with mask branch
feature_gap = GlobalAvgPooling(
'gap', feature_fastrcnn, data_format='channels_first')
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_outputs(
'fastrcnn', feature_gap, cfg.DATA.NUM_CLASS)
if is_training:
# rpn loss
rpn_label_loss, rpn_box_loss = rpn_losses(
anchors.gt_labels, anchors.encoded_gt_boxes(),
rpn_label_logits, rpn_box_logits)
# fastrcnn loss
matched_gt_boxes = tf.gather(gt_boxes, fg_inds_wrt_gt)
fg_inds_wrt_sample = tf.reshape(tf.where(rcnn_labels > 0),
[-1]) # fg inds w.r.t all samples
fg_sampled_boxes = tf.gather(rcnn_boxes, fg_inds_wrt_sample)
fg_fastrcnn_box_logits = tf.gather(fastrcnn_box_logits,
fg_inds_wrt_sample)
fastrcnn_label_loss, fastrcnn_box_loss = self.fastrcnn_training(
image, rcnn_labels, fg_sampled_boxes, matched_gt_boxes,
fastrcnn_label_logits, fg_fastrcnn_box_logits)
if cfg.MODE_MASK:
# maskrcnn loss
fg_labels = tf.gather(rcnn_labels, fg_inds_wrt_sample)
# In training, mask branch shares the same C5 feature.
fg_feature = tf.gather(feature_fastrcnn, fg_inds_wrt_sample)
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', fg_feature, cfg.DATA.NUM_CATEGORY,
num_convs=0) # #fg x #cat x 14x14
target_masks_for_fg = crop_and_resize(
tf.expand_dims(gt_masks, 1),
fg_sampled_boxes,
fg_inds_wrt_gt,
14,
pad_border=False) # nfg x 1x14x14
target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1,
'sampled_fg_mask_targets')
mrcnn_loss = maskrcnn_loss(mask_logits, fg_labels,
target_masks_for_fg)
else:
mrcnn_loss = 0.0
wd_cost = regularize_cost(
'(?:group1|group2|group3|rpn|fastrcnn|maskrcnn)/.*W',
l2_regularizer(cfg.TRAIN.WEIGHT_DECAY),
name='wd_cost')
total_cost = tf.add_n([
rpn_label_loss, rpn_box_loss, fastrcnn_label_loss,
fastrcnn_box_loss, mrcnn_loss, wd_cost
], 'total_cost')
add_moving_summary(total_cost, wd_cost)
return total_cost * (1. / cfg.TRAIN.NUM_GPUS)
else:
final_boxes, final_labels = self.fastrcnn_inference(
image_shape2d, rcnn_boxes, fastrcnn_label_logits,
fastrcnn_box_logits)
if cfg.MODE_MASK:
roi_resized = roi_align(
featuremap, final_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE),
14)
feature_maskrcnn = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', feature_maskrcnn, cfg.DATA.NUM_CATEGORY,
0) # #result x #cat x 14x14
indices = tf.stack(
[
tf.range(tf.size(final_labels)),
tf.to_int32(final_labels) - 1
],
axis=1)
final_mask_logits = tf.gather_nd(mask_logits,
indices) # #resultx14x14
tf.sigmoid(final_mask_logits, name='final_masks')
def build_graph(self, *inputs):
inputs = dict(zip(self.input_names, inputs))
is_training = get_current_tower_context().is_training
image = self.preprocess(inputs['image']) # 1CHW
featuremap = resnet_c4_backbone(image, cfg.BACKBONE.RESNET_NUM_BLOCK[:3])
rpn_label_logits, rpn_box_logits = rpn_head('rpn', featuremap, cfg.RPN.HEAD_DIM, cfg.RPN.NUM_ANCHOR)
anchors = RPNAnchors(get_all_anchors(), inputs['anchor_labels'], inputs['anchor_boxes'])
anchors = anchors.narrow_to(featuremap)
image_shape2d = tf.shape(image)[2:] # h,w
pred_boxes_decoded = anchors.decode_logits(rpn_box_logits) # fHxfWxNAx4, floatbox
proposal_boxes, proposal_scores = generate_rpn_proposals(
tf.reshape(pred_boxes_decoded, [-1, 4]),
tf.reshape(rpn_label_logits, [-1]),
image_shape2d,
cfg.RPN.TRAIN_PRE_NMS_TOPK if is_training else cfg.RPN.TEST_PRE_NMS_TOPK,
cfg.RPN.TRAIN_POST_NMS_TOPK if is_training else cfg.RPN.TEST_POST_NMS_TOPK)
gt_boxes, gt_labels = inputs['gt_boxes'], inputs['gt_labels']
if is_training:
# sample proposal boxes in training
proposals = sample_fast_rcnn_targets(proposal_boxes, gt_boxes, gt_labels)
else:
# The boxes to be used to crop RoIs.
# Use all proposal boxes in inference
proposals = BoxProposals(proposal_boxes)
boxes_on_featuremap = proposals.boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE)
roi_resized = roi_align(featuremap, boxes_on_featuremap, 14)
feature_fastrcnn = resnet_conv5(roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1]) # nxcx7x7
# Keep C5 feature to be shared with mask branch
feature_gap = GlobalAvgPooling('gap', feature_fastrcnn, data_format='channels_first')
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_outputs('fastrcnn', feature_gap, cfg.DATA.NUM_CLASS)
fastrcnn_head = FastRCNNHead(proposals, fastrcnn_box_logits, fastrcnn_label_logits,
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS, dtype=tf.float32))
if is_training:
all_losses = []
# rpn loss
all_losses.extend(rpn_losses(
anchors.gt_labels, anchors.encoded_gt_boxes(), rpn_label_logits, rpn_box_logits))
# fastrcnn loss
all_losses.extend(fastrcnn_head.losses())
if cfg.MODE_MASK:
# maskrcnn loss
# In training, mask branch shares the same C5 feature.
fg_feature = tf.gather(feature_fastrcnn, proposals.fg_inds())
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', fg_feature, cfg.DATA.NUM_CATEGORY, num_convs=0) # #fg x #cat x 14x14
target_masks_for_fg = crop_and_resize(
tf.expand_dims(inputs['gt_masks'], 1),
proposals.fg_boxes(),
proposals.fg_inds_wrt_gt, 14,
pad_border=False) # nfg x 1x14x14
target_masks_for_fg = tf.squeeze(target_masks_for_fg, 1, 'sampled_fg_mask_targets')
all_losses.append(maskrcnn_loss(mask_logits, proposals.fg_labels(), target_masks_for_fg))
wd_cost = regularize_cost(
'.*/W', l2_regularizer(cfg.TRAIN.WEIGHT_DECAY), name='wd_cost')
all_losses.append(wd_cost)
total_cost = tf.add_n(all_losses, 'total_cost')
add_moving_summary(total_cost, wd_cost)
return total_cost
else:
decoded_boxes = fastrcnn_head.decoded_output_boxes()
decoded_boxes = clip_boxes(decoded_boxes, image_shape2d, name='fastrcnn_all_boxes')
label_scores = fastrcnn_head.output_scores(name='fastrcnn_all_scores')
final_boxes, final_scores, final_labels = fastrcnn_predictions(
decoded_boxes, label_scores, name_scope='output')
if cfg.MODE_MASK:
roi_resized = roi_align(featuremap, final_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE), 14)
feature_maskrcnn = resnet_conv5(roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
mask_logits = maskrcnn_upXconv_head(
'maskrcnn', feature_maskrcnn, cfg.DATA.NUM_CATEGORY, 0) # #result x #cat x 14x14
indices = tf.stack([tf.range(tf.size(final_labels)), tf.to_int32(final_labels) - 1], axis=1)
final_mask_logits = tf.gather_nd(mask_logits, indices) # #resultx14x14
tf.sigmoid(final_mask_logits, name='output/masks')