def build_graph(self, *inputs):
inputs = dict(zip(self.input_names, inputs))
image = self.preprocess(inputs['image']) # 1CHW
# build resnet c4
featuremap = resnet_c4_backbone(image, cfg.BACKBONE.RESNET_NUM_BLOCK[:3])
# ROI_align
x, y, w, h = tf.split(inputs['gt_boxes'], 4, axis=1)
gt_boxes = tf.concat([x, y, x + w, y + h], axis=1)
boxes_on_featuremap = gt_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE) # ANCHOR_STRIDE = 16
roi_resized = roi_align(featuremap, boxes_on_featuremap, 14) # 14x14 for each roi
person_labels = tf.ones_like(inputs['male'])
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(person_labels)), tf.to_int32(person_labels) - 1], axis=1)
final_mask_logits = tf.gather_nd(mask_logits, indices) # #resultx14x14
final_mask_logits = tf.sigmoid(final_mask_logits, name='output/masks')
final_mask_logits_expand = tf.expand_dims(final_mask_logits, axis=1)
final_mask_logits_tile = tf.tile(final_mask_logits_expand, multiples=[1, 1024, 1, 1])
fg_mask_roi_resized = tf.where(final_mask_logits_tile >= 0.5, roi_resized,
roi_resized * 1.0)
feature_attrs = resnet_conv5_attr(fg_mask_roi_resized,
cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
feature_gap = GlobalAvgPooling('gap', feature_attrs, data_format='channels_first') # ??
# attrs_logits = attrs_head('attrs', feature_gap)
attrs_labels = attrs_predict(feature_gap)
def build_graph(self, *inputs):
inputs = dict(zip(self.input_names, inputs))
image = self.preprocess(inputs['image']) # 1CHW
# build resnet c4
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)
# HEAD_DIM = 1024, NUM_ANCHOR = 15
# rpn_label_logits: fHxfWxNA
# rpn_box_logits: fHxfWxNAx4
anchors = RPNAnchors(get_all_anchors(), inputs['anchor_labels'],
inputs['anchor_boxes'])
# anchor_boxes is Groundtruth boxes corresponding to each anchor
anchors = anchors.narrow_to(featuremap) # ??
image_shape2d = tf.shape(image)[2:] # h,w
pred_boxes_decoded = anchors.decode_logits(
rpn_box_logits) # fHxfWxNAx4, floatbox
# ProposalCreator (get the topk proposals)
proposal_boxes, proposal_scores = generate_rpn_proposals(
tf.reshape(pred_boxes_decoded, [-1, 4]),
tf.reshape(rpn_label_logits, [-1]),
image_shape2d,
cfg.RPN.TEST_PRE_NMS_TOPK, # 2000
cfg.RPN.TEST_POST_NMS_TOPK) # 1000
x, y, w, h = tf.split(inputs['gt_boxes'], 4, axis=1)
gt_boxes = tf.concat([x, y, x + w, y + h], axis=1)
boxes_on_featuremap = gt_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE
) # ANCHOR_STRIDE = 16
roi_resized = roi_align(featuremap, boxes_on_featuremap, 14)
feature_fastrcnn = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1]
) # nxcx7x7 # RESNET_NUM_BLOCK = [3, 4, 6, 3]
# 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) # ??
# Returns:
# cls_logits: Tensor("fastrcnn/class/output:0", shape=(n, 81), dtype=float32)
# reg_logits: Tensor("fastrcnn/output_box:0", shape=(n, 81, 4), dtype=float32)
# ------------------Fastrcnn_Head------------------------
fastrcnn_head = FastRCNNHead(
proposal_boxes,
fastrcnn_box_logits,
fastrcnn_label_logits, #
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS,
dtype=tf.float32)) # [10., 10., 5., 5.]
decoded_boxes = fastrcnn_head.decoded_output_boxes(
) # pre_boxes_on_images
decoded_boxes = clip_boxes(decoded_boxes,
image_shape2d,
name='fastrcnn_all_boxes')
label_scores = tf.nn.softmax(fastrcnn_label_logits,
name='fastrcnn_all_scores')
# class scores, summed to one for each box.
final_boxes, final_scores, final_labels = fastrcnn_predictions(
decoded_boxes, label_scores, name_scope='output')
feature_maskrcnn = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1]
) # nxcx7x7 # RESNET_NUM_BLOCK = [3, 4, 6, 3]
# Keep C5 feature to be shared with mask branch
mask_logits = maskrcnn_upXconv_head('maskrcnn', feature_maskrcnn,
cfg.DATA.NUM_CATEGORY,
0) # #result x #cat x 14x14
# Assume only person here
person_labels = tf.ones_like(inputs['male'])
indices = tf.stack(
[tf.range(tf.size(person_labels)),
tf.to_int32(person_labels) - 1],
axis=1)
final_mask_logits = tf.gather_nd(mask_logits, indices) # #resultx14x14
final_mask_logits = tf.sigmoid(final_mask_logits, name='output/masks')
mask = False
if mask:
final_mask_logits_expand = tf.expand_dims(final_mask_logits,
axis=1)
final_mask_logits_tile = tf.tile(final_mask_logits_expand,
multiples=[1, 1024, 1, 1])
fg_roi_resized = tf.where(final_mask_logits_tile >= 0.5,
roi_resized, roi_resized * 1.0)
feature_attrs = resnet_conv5_attr(
fg_roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
else:
feature_attrs = resnet_conv5_attr(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
feature_attrs_gap = GlobalAvgPooling('gap',
feature_attrs,
data_format='channels_first')
attrs_logits = attrs_head('attrs', feature_attrs_gap)
attrs_loss = all_attrs_losses(inputs, attrs_logits, attr_losses_v2)
all_losses = [attrs_loss]
# male loss
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(wd_cost, total_cost)
return total_cost
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')
def build_graph(self, *inputs):
inputs = dict(zip(self.input_names, inputs))
image = self.preprocess(inputs['image']) # 1CHW
# build resnet c4
featuremap = resnet_c4_backbone(image,
cfg.BACKBONE.RESNET_NUM_BLOCK[:3])
# build rpn
rpn_label_logits, rpn_box_logits = rpn_head('rpn', featuremap,
cfg.RPN.HEAD_DIM,
cfg.RPN.NUM_ANCHOR)
# HEAD_DIM = 1024, NUM_ANCHOR = 15
# rpn_label_logits: fHxfWxNA
# rpn_box_logits: fHxfWxNAx4
anchors = RPNAnchors(get_all_anchors(), inputs['anchor_labels'],
inputs['anchor_boxes'])
# anchor_boxes is Groundtruth boxes corresponding to each anchor
anchors = anchors.narrow_to(featuremap)
image_shape2d = tf.shape(image)[2:] # h,w
pred_boxes_decoded = anchors.decode_logits(
rpn_box_logits) # fHxfWxNAx4, floatbox
# ProposalCreator (get the topk proposals)
proposal_boxes, proposal_scores = generate_rpn_proposals(
tf.reshape(pred_boxes_decoded, [-1, 4]),
tf.reshape(rpn_label_logits, [-1]),
image_shape2d,
cfg.RPN.TEST_PRE_NMS_TOPK, # 6000
cfg.RPN.TEST_POST_NMS_TOPK) # 1000
boxes_on_featuremap = proposal_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE
) # ANCHOR_STRIDE = 16
# ROI_align
roi_resized = roi_align(featuremap, boxes_on_featuremap,
14) # 14x14 for each roi
feature_fastrcnn = resnet_conv5(
roi_resized, cfg.BACKBONE.RESNET_NUM_BLOCK[-1]
) # nxcx7x7 # RESNET_NUM_BLOCK = [3, 4, 6, 3]
# 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)
# Returns:
# cls_logits: Tensor("fastrcnn/class/output:0", shape=(n, 81), dtype=float32)
# reg_logits: Tensor("fastrcnn/output_box:0", shape=(n, 81, 4), dtype=float32)
# ------------------Fastrcnn_Head------------------------
proposals = BoxProposals(proposal_boxes)
fastrcnn_head = FastRCNNHead(
proposals,
fastrcnn_box_logits,
fastrcnn_label_logits, #
tf.constant(cfg.FRCNN.BBOX_REG_WEIGHTS,
dtype=tf.float32)) # [10., 10., 5., 5.]
decoded_boxes = fastrcnn_head.decoded_output_boxes(
) # pre_boxes_on_images
decoded_boxes = clip_boxes(decoded_boxes,
image_shape2d,
name='fastrcnn_all_boxes')
label_scores = tf.nn.softmax(fastrcnn_label_logits,
name='fastrcnn_all_scores')
# class scores, summed to one for each box.
final_boxes, final_scores, final_labels = fastrcnn_predictions(
decoded_boxes, label_scores, name_scope='output')
person_slice = tf.where(final_labels <= 1)
person_labels = tf.gather(final_labels, person_slice)
final_person_labels = tf.reshape(person_labels, (-1, ),
name='person_labels')
#
person_boxes = tf.gather(final_boxes, person_slice)
final_person_boxes = tf.reshape(person_boxes, (-1, 4),
name='person_boxes')
#
person_scores = tf.gather(final_scores, person_slice)
tf.reshape(person_scores, (-1, ), name='person_scores')
# Mask
person_roi_resized = roi_align(
featuremap, final_person_boxes * (1.0 / cfg.RPN.ANCHOR_STRIDE), 14)
feature_maskrcnn = resnet_conv5(person_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_person_labels)),
tf.to_int32(final_person_labels) - 1
],
axis=1)
final_mask_logits = tf.gather_nd(mask_logits, indices) # #resultx14x14
final_mask_logits = tf.sigmoid(final_mask_logits, name='output/masks')
person_mask_logits = tf.gather(final_mask_logits, person_slice)
tf.reshape(person_mask_logits, (-1, 14, 14), name='person_masks')
feature_attrs = resnet_conv5_attr(person_roi_resized,
cfg.BACKBONE.RESNET_NUM_BLOCK[-1])
feature_attrs_gap = GlobalAvgPooling('gap',
feature_attrs,
data_format='channels_first') #
attrs_labels = attrs_predict(feature_attrs_gap, logits_to_predict_v2)