def run_head(self, proposals, stage):
"""
Args:
proposals: BoxProposals
stage: 0, 1, 2
Returns:
FastRCNNHead
Nx4, updated boxes
"""
reg_weights = tf.constant(cfg.CASCADE.BBOX_REG_WEIGHTS[stage],
dtype=tf.float32)
pooled_feature = self.roi_func(proposals.boxes) # N,C,S,S
pooled_feature = self.scale_gradient(pooled_feature)
head_feature = self.fastrcnn_head_func('head', pooled_feature)
label_logits, box_logits = fastrcnn_outputs(
'outputs',
head_feature,
self.num_classes,
class_agnostic_regression=True)
head = FastRCNNHead(proposals, box_logits, label_logits, self.gt_boxes,
reg_weights)
refined_boxes = head.decoded_output_boxes_class_agnostic()
refined_boxes = clip_boxes(refined_boxes, self.image_shape2d)
return head, tf.stop_gradient(refined_boxes, name='output_boxes')
def run_head(self, proposals, stage):
"""
Args:
proposals: BoxProposals
stage: 0, 1, 2
Returns:
FastRCNNHead
Nx4, updated boxes
"""
reg_weights = tf.constant(cfg.CASCADE.BBOX_REG_WEIGHTS[stage], dtype=tf.float32) # 创建cascade的权重，是持久化常量浮点数
pooled_feature = self.roi_func(proposals.boxes) # N,C,S,S
if self.roi_func_extra != None:
# pooled_feature = tf.concat([pooled_feature, self.roi_func_extra(proposals.boxes)], 0)
pooled_feature = (self.roi_func_extra(proposals.boxes) + pooled_feature) / 2
pooled_feature = self.scale_gradient(pooled_feature) # 这里不太理解为什么重新赋值
head_feature = self.fastrcnn_head_func('head', pooled_feature)
# 82-87不太理解.....
# changed by Paul
label_logits, box_logits = fastrcnn_outputs(
'outputs_new', head_feature, self.num_classes, class_agnostic_regression=True)
head = FastRCNNHead(proposals, box_logits, label_logits, self.gt_boxes, reg_weights)
refined_boxes = head.decoded_output_boxes_class_agnostic()
refined_boxes = clip_boxes(refined_boxes, self.image_shape2d)
# tf.stop_gradient：停止梯度计算；参数 - 张量 + 操作名称
return head, tf.stop_gradient(refined_boxes, name='output_boxes')
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):
featuremap = features[0]
gt_boxes, gt_labels, *_ = targets
proposals = sample_fast_rcnn_targets(proposals.boxes, gt_boxes, gt_labels)
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))
return fastrcnn_head.losses()
def run_head(self, proposals, stage):
"""
Args:
proposals: BoxProposals
stage: 0, 1, 2
Returns:
FastRCNNHead
Nx4, updated boxes
"""
reg_weights = tf.constant(cfg.CASCADE.BBOX_REG_WEIGHTS[stage], dtype=tf.float32)
pooled_feature = self.roi_func(proposals.boxes) # N,C,S,S
pooled_feature = self.scale_gradient(pooled_feature)
head_feature = self.fastrcnn_head_func('head', pooled_feature)
label_logits, box_logits = fastrcnn_outputs(
'outputs', head_feature, self.num_classes, class_agnostic_regression=True)
head = FastRCNNHead(proposals, box_logits, label_logits, reg_weights)
refined_boxes = head.decoded_output_boxes_class_agnostic()
refined_boxes = clip_boxes(refined_boxes, self.image_shape2d)
return head, tf.stop_gradient(refined_boxes, name='output_boxes')
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 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 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)
# freeze
# rpn_label_logits = tf.stop_gradient(rpn_label_logits)
# rpn_box_logits = tf.stop_gradient(rpn_box_logits)
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
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], useDropout=True) # nxcx7x7
# Keep C5 feature to be shared with mask branch
# feature_fastrcnn = tf.stop_gradient(feature_fastrcnn)
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, useDropout=True)
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(
'(fastrcnn|rpn|group3)/.*/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, 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')
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,
def build_graph(self, *inputs):
is_training = get_current_tower_context().is_training
image, anchor_labels, anchor_boxes, gt_boxes, gt_labels, gt_ids, orig_shape = 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
# decode into actual image coordinates
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
boxes_on_featuremap = rcnn_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE)
# size? #proposals*h*w*c?
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
# outputs from fg proposals
fg_sampled_boxes = tf.gather(rcnn_boxes, fg_inds_wrt_sample)
fg_fastrcnn_box_logits = tf.gather(fastrcnn_box_logits,
fg_inds_wrt_sample)
# rcnn_labels: the labels of the proposals
# fg_sampled_boxes: fg proposals
# matched_gt_boxes: just like RPN, the gt boxes
# that match the corresponding fg proposals
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)
# acquire pred for re-id training
# turning NMS off gives re-id branch more training samples
if cfg.RE_ID.NMS:
boxes, final_labels, final_probs = self.fastrcnn_inference(
image_shape2d, rcnn_boxes, fastrcnn_label_logits,
fastrcnn_box_logits)
else:
boxes, final_labels, final_probs = self.fastrcnn_inference_id(
image_shape2d, rcnn_boxes, fastrcnn_label_logits,
fastrcnn_box_logits)
# scale = tf.sqrt(tf.cast(image_shape2d[0], tf.float32) / tf.cast(orig_shape[0], tf.float32) *
# tf.cast(image_shape2d[1], tf.float32) / tf.cast(orig_shape[1], tf.float32))
# final_boxes = boxes / scale
# # boxes are already clipped inside the graph, but after the floating point scaling, this may not be true any more.
# final_boxes = tf_clip_boxes(final_boxes, orig_shape)
# IOU, discard bad dets, assign re-id labels
# the results are already NMS so no need to NMS again
# crop from conv4 with dets (maybe plus gts)
# feedforward re-id branch
# resizing during ROIalign?
iou = pairwise_iou(boxes, gt_boxes) # are the gt boxes resized?
tp_mask = tf.reduce_max(iou, axis=1) >= cfg.RE_ID.IOU_THRESH
iou = tf.boolean_mask(iou, tp_mask)
# return iou to debug
def re_id_loss(pred_boxes, pred_matching_gt_ids, featuremap):
with tf.variable_scope('id_head'):
num_of_samples_used = tf.get_variable(
'num_of_samples_used', initializer=0, trainable=False)
num_of_samples_used = num_of_samples_used.assign_add(
tf.shape(pred_boxes)[0])
boxes_on_featuremap = pred_boxes * (1.0 /
cfg.RPN.ANCHOR_STRIDE)
# name scope?
# stop gradient
roi_resized = roi_align(featuremap, boxes_on_featuremap,
14)
feature_idhead = resnet_conv5(
roi_resized,
cfg.BACKBONE.RESNET_NUM_BLOCK[-1]) # nxcx7x7
feature_gap = GlobalAvgPooling(
'gap', feature_idhead, data_format='channels_first')
init = tf.variance_scaling_initializer()
hidden = FullyConnected('fc6',
feature_gap,
1024,
kernel_initializer=init,
activation=tf.nn.relu)
hidden = FullyConnected('fc7',
hidden,
1024,
kernel_initializer=init,
activation=tf.nn.relu)
hidden = FullyConnected('fc8',
hidden,
256,
kernel_initializer=init,
activation=tf.nn.relu)
id_logits = FullyConnected(
'class',
hidden,
cfg.DATA.NUM_ID,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01))
label_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=pred_matching_gt_ids, logits=id_logits)
label_loss = tf.reduce_mean(label_loss, name='label_loss')
return label_loss, num_of_samples_used
def check_unid_pedes(iou, gt_ids, boxes, tp_mask, featuremap):
pred_gt_ind = tf.argmax(iou, axis=1)
# output following tensors
# pick out the -2 class here
pred_matching_gt_ids = tf.gather(gt_ids, pred_gt_ind)
pred_boxes = tf.boolean_mask(boxes, tp_mask)
# label 1 corresponds to unid pedes
unid_ind = tf.not_equal(pred_matching_gt_ids, 1)
pred_matching_gt_ids = tf.boolean_mask(pred_matching_gt_ids,
unid_ind)
pred_boxes = tf.boolean_mask(pred_boxes, unid_ind)
ret = tf.cond(
tf.equal(tf.size(pred_boxes), 0), lambda:
(tf.constant(cfg.RE_ID.STABLE_LOSS), tf.constant(0)),
lambda: re_id_loss(pred_boxes, pred_matching_gt_ids,
featuremap))
return ret
with tf.name_scope('id_head'):
# no detection has IOU > 0.7, re-id returns 0 loss
re_id_loss, num_of_samples_used = tf.cond(
tf.equal(tf.size(iou), 0), lambda:
(tf.constant(cfg.RE_ID.STABLE_LOSS), tf.constant(0)),
lambda: check_unid_pedes(iou, gt_ids, boxes, tp_mask,
featuremap))
add_tensor_summary(num_of_samples_used, ['scalar'],
name='num_of_samples_used')
# for debug, use tensor name to take out the handle
# return re_id_loss
# pred_gt_ind = tf.argmax(iou, axis=1)
# # output following tensors
# # pick out the -2 class here
# pred_gt_ids = tf.gather(gt_ids, pred_gt_ind)
# pred_boxes = tf.boolean_mask(boxes, tp_mask)
# unid_ind = pred_gt_ids != 1
# return unid_ind
# return tf.shape(boxes)[0]
unnormed_id_loss = tf.identity(re_id_loss, name='unnormed_id_loss')
re_id_loss = tf.divide(re_id_loss, cfg.RE_ID.LOSS_NORMALIZATION,
're_id_loss')
add_moving_summary(unnormed_id_loss)
add_moving_summary(re_id_loss)
wd_cost = regularize_cost('.*/W',
l2_regularizer(cfg.TRAIN.WEIGHT_DECAY),
name='wd_cost')
# weights on the losses?
total_cost = tf.add_n([
rpn_label_loss, rpn_box_loss, fastrcnn_label_loss,
fastrcnn_box_loss, re_id_loss, wd_cost
], 'total_cost')
add_moving_summary(total_cost, wd_cost)
return total_cost
else:
if cfg.RE_ID.QUERY_EVAL:
# resize the gt_boxes in dataflow
final_boxes = gt_boxes
else:
final_boxes, final_labels, _ = self.fastrcnn_inference(
image_shape2d, rcnn_boxes, fastrcnn_label_logits,
fastrcnn_box_logits)
with tf.variable_scope('id_head'):
preds_on_featuremap = final_boxes * (1.0 /
cfg.RPN.ANCHOR_STRIDE)
# name scope?
# stop gradient
roi_resized = roi_align(featuremap, preds_on_featuremap, 14)
feature_idhead = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1]) # nxcx7x7
feature_gap = GlobalAvgPooling('gap',
feature_idhead,
data_format='channels_first')
hidden = FullyConnected('fc6',
feature_gap,
1024,
activation=tf.nn.relu)
hidden = FullyConnected('fc7',
hidden,
1024,
activation=tf.nn.relu)
fv = FullyConnected('fc8', hidden, 256, activation=tf.nn.relu)
id_logits = FullyConnected(
'class',
fv,
cfg.DATA.NUM_ID,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01))
scale = tf.sqrt(
tf.cast(image_shape2d[0], tf.float32) /
tf.cast(orig_shape[0], tf.float32) *
tf.cast(image_shape2d[1], tf.float32) /
tf.cast(orig_shape[1], tf.float32))
rescaled_final_boxes = final_boxes / scale
# boxes are already clipped inside the graph, but after the floating point scaling, this may not be true any more.
# rescaled_final_boxes_pre_clip = tf.identity(rescaled_final_boxes, name='re_boxes_pre_clip')
rescaled_final_boxes = tf_clip_boxes(rescaled_final_boxes,
orig_shape)
rescaled_final_boxes = tf.identity(rescaled_final_boxes,
'rescaled_final_boxes')
fv = tf.identity(fv, name='feature_vector')
prob = tf.nn.softmax(id_logits, name='re_id_probs')
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, gt_masks = inputs['gt_boxes'], inputs[
'gt_labels'], inputs['gt_masks']
if is_training:
# sample proposal boxes in training
rcnn_boxes, rcnn_labels, fg_inds_wrt_gt, rcnn_masks = sample_fast_rcnn_targets(
proposal_boxes, gt_boxes, gt_labels, gt_masks)
matched_gt_boxes = tf.gather(gt_boxes,
fg_inds_wrt_gt,
name='gt_boxes_per_fg_proposal')
matched_gt_masks = tf.gather(gt_masks,
fg_inds_wrt_gt,
name='gt_masks_per_fg_proposal')
else:
# The boxes to be used to crop RoIs.
# Use all proposal boxes in inference
rcnn_boxes = proposal_boxes
angles = tf.ones((tf.shape(proposal_boxes)[0], 1)) * (-45.)
x1y1, x2y2 = proposal_boxes[:, 0:2], proposal_boxes[:, 2:4]
wh = x2y2 - x1y1
xy = (x2y2 + x1y1) * 0.5
rcnn_masks = tf.concat([xy, wh, angles], axis=1)
rcnn_labels, matched_gt_boxes, matched_gt_masks = None, None, None
# ToDo
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_mask_logits = fastrcnn_outputs(
'fastrcnn', feature_gap, cfg.DATA.NUM_CLASS)
fastrcnn_head = FastRCNNHead(rcnn_boxes, rcnn_masks,
fastrcnn_box_logits, fastrcnn_mask_logits,
fastrcnn_label_logits, rcnn_labels,
matched_gt_boxes, matched_gt_masks)
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
fastrcnn_label_loss, fastrcnn_box_loss, mask_loss = fastrcnn_head.losses(
)
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, mask_loss, wd_cost
], 'total_cost')
add_moving_summary(total_cost, wd_cost)
return total_cost
else:
# ToDo
final_boxes, final_labels = self.fastrcnn_inference(
image_shape2d, fastrcnn_head)
indices = tf.stack([
tf.range(tf.size(final_labels)),
tf.to_int32(final_labels) - 1
],
axis=1)
final_mask_logits = tf.gather_nd(fastrcnn_mask_logits,
indices,
name='final_masks')
def _hard_losses(self, negative=True):
if negative:
hard_features = self._hard_negative_features
desc = "neg"
else:
hard_features = self._hard_positive_features
desc = "pos"
losses = []
for cascade_idx, iou_thres in enumerate(
cfg.CASCADE.IOUS): # 3个stages，三次循环
with tf.name_scope('cascade_loss_{}_stage{}'.format(
desc, cascade_idx + 1)):
with tf.variable_scope('cascade_rcnn_stage' +
str(cascade_idx + 1),
reuse=True):
pooled_feature = self.roi_func(
None, hard_features[:, cascade_idx])
pooled_feature = self.scale_gradient(pooled_feature)
head_feature = self.fastrcnn_head_func(
'head', pooled_feature)
# changed by Paul
label_logits, box_logits = fastrcnn_outputs(
'outputs_new',
head_feature,
self.num_classes,
class_agnostic_regression=True)
mean_label = None
box_loss = None
if negative: # negative的样本，label 全 0
labels = tf.zeros((tf.shape(label_logits)[0], ),
dtype=tf.int64)
else: # positive的样本，label为1当且仅当ious >= 当前stage的ios
labels = tf.cast(
tf.greater_equal(
self._hard_positive_ious[:, cascade_idx],
iou_thres), tf.int64)
mean_label = tf.reduce_mean(
tf.cast(labels, tf.float32),
name='hard_{}_label_mean{}'.format(
desc, cascade_idx + 1))
# config.py 中 USE_REGRESSION_LOSS_ON_HARD_POSITIVES 为false，因此第188-210行无用
if cfg.USE_REGRESSION_LOSS_ON_HARD_POSITIVES:
labels_bool = tf.cast(labels, tf.bool)
valid = tf.reduce_any(labels_bool)
def make_box_loss():
gt_boxes = tf.boolean_mask(
self._hard_positive_gt_boxes, labels_bool)
inp_boxes = tf.boolean_mask(
self.
_hard_positive_jitter_boxes[:,
cascade_idx],
labels_bool)
box_logits_masked = tf.boolean_mask(
box_logits, labels_bool)
from examples.FasterRCNN.model_box import encode_bbox_target
reg_targets = encode_bbox_target(
gt_boxes, inp_boxes
) * cfg.CASCADE.BBOX_REG_WEIGHTS[cascade_idx]
_box_loss = tf.losses.huber_loss(
reg_targets,
tf.squeeze(box_logits_masked, axis=1),
reduction=tf.losses.Reduction.SUM)
_box_loss = tf.truediv(
_box_loss,
tf.cast(
tf.shape(reg_targets)[0], tf.float32))
return _box_loss
box_loss = tf.cond(
valid, make_box_loss,
lambda: tf.constant(0, dtype=tf.float32))
box_loss = tf.multiply(
box_loss,
cfg.HARD_POSITIVE_BOX_LOSS_SCALING_FACTOR,
name='hard_{}_box_loss{}'.format(
desc, cascade_idx + 1))
losses.append(box_loss)
label_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=labels,
logits=label_logits) # softmax然后Cross-Entropy计算loss
if negative: # 乘以相应权值
label_loss *= self._hard_negative_loss_scaling_factor
else:
label_loss *= self._hard_positive_loss_scaling_factor
label_loss = tf.reduce_mean(
label_loss,
name='hard_{}_label_loss{}'.format(
desc, cascade_idx + 1)) #计算均值
prediction = tf.argmax(
label_logits,
axis=1,
name='label_prediction_hard_{}'.format(desc)) # 取最大值索引
correct = tf.cast(tf.equal(prediction, labels),
tf.float32) # 是否正确
accuracy = tf.reduce_mean(
correct,
name='hard_{}_label_accuracy{}'.format(
desc, cascade_idx + 1)) # 正确率
losses.append(label_loss)
if mean_label is not None: # 平均label是1，
add_moving_summary(mean_label) # tensorpack 汇总平均值
if box_loss is not None:
add_moving_summary(box_loss) # 汇总loss
add_moving_summary(accuracy)
add_moving_summary(label_loss)
return losses
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')
