def fastrcnn_inference(self, image_shape2d,
rcnn_boxes, rcnn_label_logits, rcnn_box_logits):
"""
Args:
image_shape2d: h, w
rcnn_boxes (nx4): the proposal boxes
rcnn_label_logits (n):
rcnn_box_logits (nx #class x 4):
Returns:
boxes (mx4):
labels (m): each >= 1
"""
rcnn_box_logits = rcnn_box_logits[:, 1:, :]
rcnn_box_logits.set_shape([None, cfg.DATA.NUM_CATEGORY, None])
label_probs = tf.nn.softmax(rcnn_label_logits, name='fastrcnn_all_probs') # #proposal x #Class
anchors = tf.tile(tf.expand_dims(rcnn_boxes, 1), [1, cfg.DATA.NUM_CATEGORY, 1]) # #proposal x #Cat x 4
decoded_boxes = decode_bbox_target(
rcnn_box_logits /
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS, dtype=tf.float32), anchors)
decoded_boxes = clip_boxes(decoded_boxes, image_shape2d, name='fastrcnn_all_boxes')
# indices: Nx2. Each index into (#proposal, #category)
pred_indices, final_probs = fastrcnn_predictions(decoded_boxes, label_probs)
final_probs = tf.identity(final_probs, 'final_probs')
final_boxes = tf.gather_nd(decoded_boxes, pred_indices, name='final_boxes')
final_labels = tf.add(pred_indices[:, 1], 1, name='final_labels')
return final_boxes, final_labels
def fastrcnn_inference(self, image_shape2d, fastrcnn_head):
"""
Args:
image_shape2d: h, w
fastrcnn_head (FastRCNNHead):
Returns:
boxes (mx4):
labels (m): each >= 1
"""
decoded_boxes = fastrcnn_head.decoded_output_boxes()
decoded_boxes = clip_boxes(decoded_boxes,
image_shape2d,
name='fastrcnn_all_boxes')
label_probs = fastrcnn_head.output_scores(name='fastrcnn_all_probs')
# indices: Nx2. Each index into (#box, #class)
pred_indices, final_probs = fastrcnn_predictions(
decoded_boxes, label_probs)
final_probs = tf.identity(final_probs, 'final_probs')
final_boxes = tf.gather_nd(decoded_boxes,
pred_indices,
name='final_boxes')
final_labels = tf.gather(pred_indices, 1, axis=1, name='final_labels')
return final_boxes, final_labels
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 roi_heads(self, image, features, proposals, targets):
image_shape2d = tf.shape(image)[2:] # h,w
featuremap = features[0]
gt_boxes, gt_labels, *_ = targets
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])
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))
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')
fastrcnn_predictions(decoded_boxes, label_scores, name_scope='output')
def fastrcnn_inference_cascade(self, image_shape2d,
rcnn_boxes, rcnn_label_logits, rcnn_box_logits, stage_num):
"""
Args:
image_shape2d: h, w
rcnn_boxes (nx4): the proposal boxes
rcnn_label_logits (n):
rcnn_box_logits (nx #class x 4):
Returns:
boxes (mx4):
labels (m): each >= 1
"""
if stage_num == 1:
bbox_reg_weights = cfg.CASCADERCNN.BBOX_REG_WEIGHTS_STAGE1
elif stage_num == 2:
bbox_reg_weights = cfg.CASCADERCNN.BBOX_REG_WEIGHTS_STAGE2
elif stage_num == 3:
bbox_reg_weights = cfg.CASCADERCNN.BBOX_REG_WEIGHTS_STAGE3
prefix = ''
if stage_num == 1:
prefix = '_1st'
elif stage_num == 2:
prefix = '_2nd'
elif stage_num == 3:
prefix ='_3rd'
rcnn_box_logits = rcnn_box_logits[:, 1:, :]
rcnn_box_logits.set_shape([None, cfg.DATA.NUM_CATEGORY, None])
label_probs = tf.nn.softmax(rcnn_label_logits, name='fastrcnn_all_probs') # #proposal x #Class
anchors = tf.tile(tf.expand_dims(rcnn_boxes, 1), [1, cfg.DATA.NUM_CATEGORY, 1]) # #proposal x #Cat x 4
decoded_boxes = decode_bbox_target(
rcnn_box_logits /
tf.constant(bbox_reg_weights, dtype=tf.float32), anchors)
decoded_boxes = clip_boxes(decoded_boxes, image_shape2d, name='fastrcnn_all_boxes')
# indices: Nx2. Each index into (#proposal, #category)
#TODO add box voting after NMS
if cfg.TEST.BOX_VOTING.ENABLED:
final_boxes, final_probs, pred_indices = fastrcnn_predictions_box_voting(decoded_boxes, label_probs)
final_probs = tf.identity(final_probs, 'final_probs'+prefix)
final_boxes = tf.identity(final_boxes, 'final_boxes'+prefix)
final_labels = tf.add(pred_indices[:, 1], 1, name='final_labels'+prefix)
else:
pred_indices, final_probs = fastrcnn_predictions(decoded_boxes, label_probs)
final_probs = tf.identity(final_probs, 'final_probs'+prefix)
final_boxes = tf.gather_nd(decoded_boxes, pred_indices, name='final_boxes'+prefix)
final_labels = tf.add(pred_indices[:, 1], 1, name='final_labels'+prefix)
return final_boxes, final_labels
def roi_heads(self, image, features, proposals, targets):
image_shape2d = tf.shape(image)[2:] # h,w
assert len(features) == 5, "Features have to be P23456!"
gt_boxes, gt_labels, *_ = targets
if self.training:
proposals = sample_fast_rcnn_targets(proposals.boxes, gt_boxes, gt_labels)
fastrcnn_head_func = getattr(model_frcnn, cfg.FPN.FRCNN_HEAD_FUNC)
if not cfg.FPN.CASCADE:
roi_feature_fastrcnn = multilevel_roi_align(features[:4], proposals.boxes, 7)
head_feature = fastrcnn_head_func('fastrcnn', roi_feature_fastrcnn)
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_outputs(
'fastrcnn/outputs', head_feature, 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))
else:
def roi_func(boxes):
return multilevel_roi_align(features[:4], boxes, 7)
fastrcnn_head = CascadeRCNNHead(
proposals, roi_func, fastrcnn_head_func,
(gt_boxes, gt_labels), image_shape2d, cfg.DATA.NUM_CLASS)
if self.training:
all_losses = fastrcnn_head.losses()
if cfg.MODE_MASK:
gt_masks = targets[2]
# maskrcnn loss
roi_feature_maskrcnn = multilevel_roi_align(
features[:4], proposals.fg_boxes(), 14,
name_scope='multilevel_roi_align_mask')
maskrcnn_head_func = getattr(model_mrcnn, cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn, cfg.DATA.NUM_CATEGORY) # #fg x #cat x 28 x 28
target_masks_for_fg = crop_and_resize(
tf.expand_dims(gt_masks, 1),
proposals.fg_boxes(),
proposals.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')
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:
# Cascade inference needs roi transform with refined boxes.
roi_feature_maskrcnn = multilevel_roi_align(features[:4], final_boxes, 14)
maskrcnn_head_func = getattr(model_mrcnn, cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn, cfg.DATA.NUM_CATEGORY) # #fg x #cat x 28 x 28
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) # #resultx28x28
tf.sigmoid(final_mask_logits, name='output/masks')
return []
def build_graph(self, *inputs):
inputs = dict(zip(self.input_names, 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
all_anchors_fpn = get_all_anchors_fpn()
multilevel_anchors = [
RPNAnchors(all_anchors_fpn[i],
inputs['anchor_labels_lvl{}'.format(i + 2)],
inputs['anchor_boxes_lvl{}'.format(i + 2)])
for i in range(len(all_anchors_fpn))
]
image = self.preprocess(inputs['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)
gt_boxes, gt_labels = inputs['gt_boxes'], inputs['gt_labels']
if is_training:
proposals = sample_fast_rcnn_targets(proposal_boxes, gt_boxes,
gt_labels)
else:
proposals = BoxProposals(proposal_boxes)
fastrcnn_head_func = getattr(model_frcnn, cfg.FPN.FRCNN_HEAD_FUNC)
if not cfg.FPN.CASCADE:
roi_feature_fastrcnn = multilevel_roi_align(
p23456[:4], proposals.boxes, 7)
head_feature = fastrcnn_head_func('fastrcnn', roi_feature_fastrcnn)
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_outputs(
'fastrcnn/outputs', head_feature, cfg.DATA.NUM_CLASS)
fastrcnn_head = FastRCNNHead(
proposals, fastrcnn_box_logits, fastrcnn_label_logits,
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS, dtype=tf.float32))
else:
def roi_func(boxes):
return multilevel_roi_align(p23456[:4], boxes, 7)
fastrcnn_head = CascadeRCNNHead(proposals, roi_func,
fastrcnn_head_func, image_shape2d,
cfg.DATA.NUM_CLASS)
if is_training:
all_losses = []
all_losses.extend(
multilevel_rpn_losses(multilevel_anchors,
multilevel_label_logits,
multilevel_box_logits))
all_losses.extend(fastrcnn_head.losses())
if cfg.MODE_MASK:
# maskrcnn loss
roi_feature_maskrcnn = multilevel_roi_align(
p23456[:4],
proposals.fg_boxes(),
14,
name_scope='multilevel_roi_align_mask')
maskrcnn_head_func = getattr(model_mrcnn,
cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn,
cfg.DATA.NUM_CATEGORY) # #fg x #cat x 28 x 28
target_masks_for_fg = crop_and_resize(
tf.expand_dims(inputs['gt_masks'], 1),
proposals.fg_boxes(),
proposals.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')
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:
# Cascade inference needs roi transform with refined boxes.
roi_feature_maskrcnn = multilevel_roi_align(
p23456[:4], final_boxes, 14)
maskrcnn_head_func = getattr(model_mrcnn,
cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn,
cfg.DATA.NUM_CATEGORY) # #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='output/masks')
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 roi_heads(self,
image,
ref_features,
ref_box,
features,
proposals,
targets,
hard_negative_features=None,
hard_positive_features=None,
hard_positive_ious=None,
hard_positive_gt_boxes=None,
hard_positive_jitter_boxes=None,
precomputed_ref_features=None,
extra_feats=None):
image_shape2d = tf.shape(image)[2:] # h,w
assert len(features) == 5, "Features have to be P23456!"
gt_boxes, gt_labels, *_ = targets
if self.training:
proposals = sample_fast_rcnn_targets(proposals.boxes, gt_boxes,
gt_labels)
fastrcnn_head_func = getattr(model_frcnn, cfg.FPN.FRCNN_HEAD_FUNC)
if precomputed_ref_features is None:
roi_aligned_ref_features = multilevel_roi_align(
ref_features[:4], ref_box[tf.newaxis], 7)
else:
roi_aligned_ref_features = precomputed_ref_features[tf.newaxis]
# //////////
roi_aligned_extra_features = extra_feats[tf.newaxis]
# //////////
if cfg.MODE_SHARED_CONV_REDUCE:
scope = tf.get_variable_scope()
else:
scope = ""
assert cfg.FPN.CASCADE
def roi_func(boxes, already_aligned_features=None):
if already_aligned_features is None:
aligned_features = multilevel_roi_align(features[:4], boxes, 7)
else:
# for hard example mining
aligned_features = already_aligned_features
tiled = tf.tile(roi_aligned_ref_features,
[tf.shape(aligned_features)[0], 1, 1, 1])
concat_features = tf.concat((tiled, aligned_features), axis=1)
with argscope(Conv2D,
data_format='channels_first',
kernel_initializer=tf.variance_scaling_initializer(
scale=2.0,
mode='fan_out',
distribution='untruncated_normal'
if get_tf_version_tuple() >=
(1, 12) else 'normal')):
with tf.variable_scope(scope, reuse=tf.AUTO_REUSE):
reduced_features = Conv2D('conv_reduce',
concat_features,
256,
1,
activation=None)
return reduced_features
def roi_func_extra(boxes, already_aligned_features=None):
if already_aligned_features is None:
aligned_features = multilevel_roi_align(features[:4], boxes, 7)
else:
# for hard example mining
aligned_features = already_aligned_features
tiled = tf.tile(roi_aligned_extra_features,
[tf.shape(aligned_features)[0], 1, 1, 1])
concat_features = tf.concat((tiled, aligned_features), axis=1)
with argscope(Conv2D,
data_format='channels_first',
kernel_initializer=tf.variance_scaling_initializer(
scale=2.0,
mode='fan_out',
distribution='untruncated_normal'
if get_tf_version_tuple() >=
(1, 12) else 'normal')):
with tf.variable_scope(scope, reuse=tf.AUTO_REUSE):
reduced_features = Conv2D('conv_reduce',
concat_features,
256,
1,
activation=None)
return reduced_features
if cfg.MODE_HARD_MINING and self.training:
fastrcnn_head = CascadeRCNNHeadWithHardExamples(
proposals, roi_func, fastrcnn_head_func, (gt_boxes, gt_labels),
image_shape2d, cfg.DATA.NUM_CLASS, hard_negative_features,
hard_positive_features, cfg.HARD_NEGATIVE_LOSS_SCALING_FACTOR,
cfg.HARD_POSITIVE_LOSS_SCALING_FACTOR, hard_positive_ious,
hard_positive_gt_boxes, hard_positive_jitter_boxes)
else:
if cfg.MODE_EXTRA_FEATURES:
fastrcnn_head = CascadeRCNNHead(proposals, roi_func,
fastrcnn_head_func,
(gt_boxes, gt_labels),
image_shape2d,
cfg.DATA.NUM_CLASS,
roi_func_extra)
else:
fastrcnn_head = CascadeRCNNHead(proposals, roi_func,
fastrcnn_head_func,
(gt_boxes, gt_labels),
image_shape2d,
cfg.DATA.NUM_CLASS)
if cfg.EXTRACT_GT_FEATURES:
# get boxes and features for each of the three cascade stages!
b0 = proposals.boxes
b1, b2, _ = fastrcnn_head._cascade_boxes
f0 = multilevel_roi_align(features[:4], b0, 7)
f1 = multilevel_roi_align(features[:4], b1, 7)
f2 = multilevel_roi_align(features[:4], b2, 7)
tf.concat([b0, b1, b2], axis=0, name="boxes_for_extraction")
tf.concat([f0, f1, f2], axis=0, name="features_for_extraction")
if self.training:
all_losses = fastrcnn_head.losses()
if cfg.MODE_MASK:
gt_masks = targets[2]
# maskrcnn loss
roi_feature_maskrcnn = multilevel_roi_align(
features[:4],
proposals.fg_boxes(),
14,
name_scope='multilevel_roi_align_mask')
maskrcnn_head_func = getattr(model_mrcnn,
cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn,
cfg.DATA.NUM_CATEGORY) # #fg x #cat x 28 x 28
target_masks_for_fg = crop_and_resize(
tf.expand_dims(gt_masks, 1),
proposals.fg_boxes(),
proposals.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')
all_losses.append(
maskrcnn_loss(mask_logits, proposals.fg_labels(),
target_masks_for_fg))
if cfg.MEASURE_IOU_DURING_TRAINING:
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_train')
# if predictions are empty, this might break...
# to prevent, stack dummy box
boxes_for_iou = tf.concat([
final_boxes[:1],
tf.constant([[0.0, 0.0, 1.0, 1.0]], dtype=tf.float32)
],
axis=0)
from examples.FasterRCNN.utils.box_ops import pairwise_iou
iou_at_1 = tf.identity(pairwise_iou(gt_boxes[:1],
boxes_for_iou)[0, 0],
name="train_iou_at_1")
add_moving_summary(iou_at_1)
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:
# Cascade inference needs roi transform with refined boxes.
roi_feature_maskrcnn = multilevel_roi_align(
features[:4], final_boxes, 14)
maskrcnn_head_func = getattr(model_mrcnn,
cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn,
cfg.DATA.NUM_CATEGORY) # #fg x #cat x 28 x 28
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) # #resultx28x28
tf.sigmoid(final_mask_logits, name='output/masks')
return []
def build_graph(self, *inputs):
inputs = dict(zip(self.input_names, 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
all_anchors_fpn = get_all_anchors_fpn()
multilevel_anchors = [RPNAnchors(
all_anchors_fpn[i],
inputs['anchor_labels_lvl{}'.format(i + 2)],
inputs['anchor_boxes_lvl{}'.format(i + 2)]) for i in range(len(all_anchors_fpn))]
image = self.preprocess(inputs['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)
gt_boxes, gt_labels = inputs['gt_boxes'], inputs['gt_labels']
if is_training:
proposals = sample_fast_rcnn_targets(proposal_boxes, gt_boxes, gt_labels)
else:
proposals = BoxProposals(proposal_boxes)
fastrcnn_head_func = getattr(model_frcnn, cfg.FPN.FRCNN_HEAD_FUNC)
if not cfg.FPN.CASCADE:
roi_feature_fastrcnn = multilevel_roi_align(p23456[:4], proposals.boxes, 7)
head_feature = fastrcnn_head_func('fastrcnn', roi_feature_fastrcnn)
fastrcnn_label_logits, fastrcnn_box_logits = fastrcnn_outputs(
'fastrcnn/outputs', head_feature, cfg.DATA.NUM_CLASS)
fastrcnn_head = FastRCNNHead(proposals, fastrcnn_box_logits, fastrcnn_label_logits,
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS, dtype=tf.float32))
else:
def roi_func(boxes):
return multilevel_roi_align(p23456[:4], boxes, 7)
fastrcnn_head = CascadeRCNNHead(
proposals, roi_func, fastrcnn_head_func, image_shape2d, cfg.DATA.NUM_CLASS)
if is_training:
all_losses = []
all_losses.extend(multilevel_rpn_losses(
multilevel_anchors, multilevel_label_logits, multilevel_box_logits))
all_losses.extend(fastrcnn_head.losses())
if cfg.MODE_MASK:
# maskrcnn loss
roi_feature_maskrcnn = multilevel_roi_align(
p23456[:4], proposals.fg_boxes(), 14,
name_scope='multilevel_roi_align_mask')
maskrcnn_head_func = getattr(model_mrcnn, cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn, cfg.DATA.NUM_CATEGORY) # #fg x #cat x 28 x 28
target_masks_for_fg = crop_and_resize(
tf.expand_dims(inputs['gt_masks'], 1),
proposals.fg_boxes(),
proposals.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')
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:
# Cascade inference needs roi transform with refined boxes.
roi_feature_maskrcnn = multilevel_roi_align(p23456[:4], final_boxes, 14)
maskrcnn_head_func = getattr(model_mrcnn, cfg.FPN.MRCNN_HEAD_FUNC)
mask_logits = maskrcnn_head_func(
'maskrcnn', roi_feature_maskrcnn, cfg.DATA.NUM_CATEGORY) # #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='output/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')
