def add_single_scale_rpn_outputs(model, blob_in, dim_in, spatial_scale):
"""Add RPN outputs to a single scale model (i.e., no FPN)."""
anchors = generate_anchors(stride=1. / spatial_scale,
sizes=cfg.RPN.SIZES,
aspect_ratios=cfg.RPN.ASPECT_RATIOS)
num_anchors = anchors.shape[0]
dim_out = dim_in
# RPN hidden representation
model.Conv(blob_in,
'conv_rpn',
dim_in,
dim_out,
kernel=3,
pad=1,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0))
model.Relu('conv_rpn', 'conv_rpn')
# Proposal classification scores
model.Conv('conv_rpn',
'rpn_cls_logits',
dim_in,
num_anchors,
kernel=1,
pad=0,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0))
# Proposal bbox regression deltas
model.Conv('conv_rpn',
'rpn_bbox_pred',
dim_in,
4 * num_anchors,
kernel=1,
pad=0,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0))
if not model.train or cfg.MODEL.FASTER_RCNN:
# Proposals are needed during:
# 1) inference (== not model.train) for RPN only and Faster R-CNN
# OR
# 2) training for Faster R-CNN
# Otherwise (== training for RPN only), proposals are not needed
model.net.Sigmoid('rpn_cls_logits', 'rpn_cls_probs')
model.GenerateProposals(['rpn_cls_probs', 'rpn_bbox_pred', 'im_info'],
['rpn_rois', 'rpn_roi_probs'],
anchors=anchors,
spatial_scale=spatial_scale)
if cfg.MODEL.FASTER_RCNN:
if model.train:
# Add op that generates training labels for in-network RPN proposals
model.GenerateProposalLabels(['rpn_rois', 'roidb', 'im_info'])
else:
# Alias rois to rpn_rois for inference
model.net.Alias('rpn_rois', 'rois')
def add_rfcn_outputs(model, blob_in, dim_in, dim_reduce, spatial_scale):
if dim_reduce is not None:
# Optional dim reduction
blob_in = model.Conv(blob_in,
'conv_dim_reduce',
dim_in,
dim_reduce,
kernel=1,
pad=0,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0))
blob_in = model.Relu(blob_in, blob_in)
dim_in = dim_reduce
# Classification conv
model.Conv(blob_in,
'conv_cls',
dim_in,
model.num_classes * cfg.RFCN.PS_GRID_SIZE**2,
kernel=1,
pad=0,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0))
# Bounding-box regression conv
num_bbox_reg_classes = (2 if cfg.MODEL.CLS_AGNOSTIC_BBOX_REG else
model.num_classes)
model.Conv(blob_in,
'conv_bbox_pred',
dim_in,
4 * num_bbox_reg_classes * cfg.RFCN.PS_GRID_SIZE**2,
kernel=1,
pad=0,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0))
# Classification PS RoI pooling
model.net.PSRoIPool(['conv_cls', 'rois'],
['psroipooled_cls', '_mapping_channel_cls'],
group_size=cfg.RFCN.PS_GRID_SIZE,
output_dim=model.num_classes,
spatial_scale=spatial_scale)
model.AveragePool('psroipooled_cls',
'cls_score_4d',
kernel=cfg.RFCN.PS_GRID_SIZE)
model.net.Reshape('cls_score_4d', ['cls_score', '_cls_scores_shape'],
shape=(-1, cfg.MODEL.NUM_CLASSES))
if not model.train:
model.Softmax('cls_score', 'cls_prob', engine='CUDNN')
# Bbox regression PS RoI pooling
model.net.PSRoIPool(['conv_bbox_pred', 'rois'],
['psroipooled_bbox', '_mapping_channel_bbox'],
group_size=cfg.RFCN.PS_GRID_SIZE,
output_dim=4 * num_bbox_reg_classes,
spatial_scale=spatial_scale)
model.AveragePool('psroipooled_bbox',
'bbox_pred',
kernel=cfg.RFCN.PS_GRID_SIZE)
def mask_rcnn_fcn_head_v0upshare(model, blob_in, dim_in, spatial_scale):
"""Use a ResNet "conv5" / "stage5" head for mask prediction. Weights and
computation are shared with the conv5 box head. Computation can only be
shared during training, since inference is cascaded.
v0upshare design: conv5, convT 2x2.
"""
# Since box and mask head are shared, these must match
assert cfg.MRCNN.ROI_XFORM_RESOLUTION == cfg.FAST_RCNN.ROI_XFORM_RESOLUTION
if model.train: # share computation with bbox head at training time
dim_conv5 = 2048
blob_conv5 = model.net.SampleAs(['res5_2_sum', 'roi_has_mask_int32'],
['_[mask]_res5_2_sum_sliced'])
else: # re-compute at test time
blob_conv5, dim_conv5 = add_ResNet_roi_conv5_head_for_masks(
model, blob_in, dim_in, spatial_scale)
dim_reduced = cfg.MRCNN.DIM_REDUCED
blob_mask = model.ConvTranspose(
blob_conv5,
'conv5_mask',
dim_conv5,
dim_reduced,
kernel=2,
pad=0,
stride=2,
weight_init=(cfg.MRCNN.CONV_INIT, {
'std': 0.001
}), # std only for gauss
bias_init=const_fill(0.0))
model.Relu('conv5_mask', 'conv5_mask')
return blob_mask, dim_reduced
def add_mask_rcnn_outputs(model, blob_in, dim):
"""Add Mask R-CNN specific outputs: either mask logits or probs."""
num_cls = cfg.MODEL.NUM_CLASSES if cfg.MRCNN.CLS_SPECIFIC_MASK else 1
if cfg.MRCNN.USE_FC_OUTPUT:
# Predict masks with a fully connected layer (ignore 'fcn' in the blob
# name)
blob_out = model.FC(blob_in,
'mask_fcn_logits',
dim,
num_cls * cfg.MRCNN.RESOLUTION**2,
weight_init=gauss_fill(0.001),
bias_init=const_fill(0.0))
else:
# Predict mask using Conv
# Use GaussianFill for class-agnostic mask prediction; fills based on
# fan-in can be too large in this case and cause divergence
fill = (cfg.MRCNN.CONV_INIT
if cfg.MRCNN.CLS_SPECIFIC_MASK else 'GaussianFill')
blob_out = model.Conv(blob_in,
'mask_fcn_logits',
dim,
num_cls,
kernel=1,
pad=0,
stride=1,
weight_init=(fill, {
'std': 0.001
}),
bias_init=const_fill(0.0))
if cfg.MRCNN.UPSAMPLE_RATIO > 1:
blob_out = model.BilinearInterpolation('mask_fcn_logits',
'mask_fcn_logits_up',
num_cls, num_cls,
cfg.MRCNN.UPSAMPLE_RATIO)
if not model.train: # == if test
blob_out = model.net.Sigmoid(blob_out, 'mask_fcn_probs')
return blob_out
def add_topdown_lateral_module(
model, fpn_top, fpn_lateral, fpn_bottom, dim_top, dim_lateral
):
"""Add a top-down lateral module."""
# Lateral 1x1 conv
if cfg.FPN.USE_GN:
# use GroupNorm
lat = model.ConvGN(
fpn_lateral,
fpn_bottom + '_lateral',
dim_in=dim_lateral,
dim_out=dim_top,
group_gn=get_group_gn(dim_top),
kernel=1,
pad=0,
stride=1,
weight_init=(
const_fill(0.0) if cfg.FPN.ZERO_INIT_LATERAL
else ('XavierFill', {})),
bias_init=const_fill(0.0)
)
else:
lat = model.Conv(
fpn_lateral,
fpn_bottom + '_lateral',
dim_in=dim_lateral,
dim_out=dim_top,
kernel=1,
pad=0,
stride=1,
weight_init=(
const_fill(0.0)
if cfg.FPN.ZERO_INIT_LATERAL else ('XavierFill', {})
),
bias_init=const_fill(0.0)
)
# Top-down 2x upsampling
td = model.net.UpsampleNearest(fpn_top, fpn_bottom + '_topdown', scale=2)
# Sum lateral and top-down
model.net.Sum([lat, td], fpn_bottom)
def mask_rcnn_fcn_head_v1upXconvs_gn(model, blob_in, dim_in, spatial_scale,
num_convs):
"""v1upXconvs design: X * (conv 3x3), convT 2x2, with GroupNorm"""
current = model.RoIFeatureTransform(
blob_in,
blob_out='_mask_roi_feat',
blob_rois='mask_rois',
method=cfg.MRCNN.ROI_XFORM_METHOD,
resolution=cfg.MRCNN.ROI_XFORM_RESOLUTION,
sampling_ratio=cfg.MRCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale)
dilation = cfg.MRCNN.DILATION
dim_inner = cfg.MRCNN.DIM_REDUCED
for i in range(num_convs):
current = model.ConvGN(current,
'_mask_fcn' + str(i + 1),
dim_in,
dim_inner,
group_gn=get_group_gn(dim_inner),
kernel=3,
pad=1 * dilation,
stride=1,
weight_init=(cfg.MRCNN.CONV_INIT, {
'std': 0.001
}),
bias_init=('ConstantFill', {
'value': 0.
}))
current = model.Relu(current, current)
dim_in = dim_inner
# upsample layer
model.ConvTranspose(current,
'conv5_mask',
dim_inner,
dim_inner,
kernel=2,
pad=0,
stride=2,
weight_init=(cfg.MRCNN.CONV_INIT, {
'std': 0.001
}),
bias_init=const_fill(0.0))
blob_mask = model.Relu('conv5_mask', 'conv5_mask')
return blob_mask, dim_inner
def mask_rcnn_fcn_head_v0up(model, blob_in, dim_in, spatial_scale):
"""v0up design: conv5, deconv 2x2 (no weight sharing with the box head)."""
blob_conv5, dim_conv5 = add_ResNet_roi_conv5_head_for_masks(
model, blob_in, dim_in, spatial_scale)
dim_reduced = cfg.MRCNN.DIM_REDUCED
model.ConvTranspose(blob_conv5,
'conv5_mask',
dim_conv5,
dim_reduced,
kernel=2,
pad=0,
stride=2,
weight_init=('GaussianFill', {
'std': 0.001
}),
bias_init=const_fill(0.0))
blob_mask = model.Relu('conv5_mask', 'conv5_mask')
return blob_mask, dim_reduced
def add_keypoint_outputs(model, blob_in, dim):
"""Add Mask R-CNN keypoint specific outputs: keypoint heatmaps."""
# NxKxHxW
upsample_heatmap = (cfg.KRCNN.UP_SCALE > 1)
if cfg.KRCNN.USE_DECONV:
# Apply ConvTranspose to the feature representation; results in 2x
# upsampling
blob_in = model.ConvTranspose(
blob_in,
'kps_deconv',
dim,
cfg.KRCNN.DECONV_DIM,
kernel=cfg.KRCNN.DECONV_KERNEL,
pad=int(cfg.KRCNN.DECONV_KERNEL / 2 - 1),
stride=2,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0)
)
model.Relu('kps_deconv', 'kps_deconv')
dim = cfg.KRCNN.DECONV_DIM
if upsample_heatmap:
blob_name = 'kps_score_lowres'
else:
blob_name = 'kps_score'
if cfg.KRCNN.USE_DECONV_OUTPUT:
# Use ConvTranspose to predict heatmaps; results in 2x upsampling
blob_out = model.ConvTranspose(
blob_in,
blob_name,
dim,
cfg.KRCNN.NUM_KEYPOINTS,
kernel=cfg.KRCNN.DECONV_KERNEL,
pad=int(cfg.KRCNN.DECONV_KERNEL / 2 - 1),
stride=2,
weight_init=(cfg.KRCNN.CONV_INIT, {'std': 0.001}),
bias_init=const_fill(0.0)
)
else:
# Use Conv to predict heatmaps; does no upsampling
blob_out = model.Conv(
blob_in,
blob_name,
dim,
cfg.KRCNN.NUM_KEYPOINTS,
kernel=1,
pad=0,
stride=1,
weight_init=(cfg.KRCNN.CONV_INIT, {'std': 0.001}),
bias_init=const_fill(0.0)
)
if upsample_heatmap:
# Increase heatmap output size via bilinear upsampling
blob_out = model.BilinearInterpolation(
blob_out, 'kps_score', cfg.KRCNN.NUM_KEYPOINTS,
cfg.KRCNN.NUM_KEYPOINTS, cfg.KRCNN.UP_SCALE
)
return blob_out
def add_fpn_rpn_outputs(model, blobs_in, dim_in, spatial_scales):
"""Add RPN on FPN specific outputs."""
num_anchors = len(cfg.FPN.RPN_ASPECT_RATIOS)
dim_out = dim_in
k_max = cfg.FPN.RPN_MAX_LEVEL # coarsest level of pyramid
k_min = cfg.FPN.RPN_MIN_LEVEL # finest level of pyramid
assert len(blobs_in) == k_max - k_min + 1
for lvl in range(k_min, k_max + 1):
bl_in = blobs_in[k_max - lvl] # blobs_in is in reversed order
sc = spatial_scales[k_max - lvl] # in reversed order
slvl = str(lvl)
if lvl == k_min:
# Create conv ops with randomly initialized weights and
# zeroed biases for the first FPN level; these will be shared by
# all other FPN levels
# RPN hidden representation
conv_rpn_fpn = model.Conv(
bl_in,
'conv_rpn_fpn' + slvl,
dim_in,
dim_out,
kernel=3,
pad=1,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0)
)
model.Relu(conv_rpn_fpn, conv_rpn_fpn)
# Proposal classification scores
rpn_cls_logits_fpn = model.Conv(
conv_rpn_fpn,
'rpn_cls_logits_fpn' + slvl,
dim_in,
num_anchors,
kernel=1,
pad=0,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0)
)
# Proposal bbox regression deltas
rpn_bbox_pred_fpn = model.Conv(
conv_rpn_fpn,
'rpn_bbox_pred_fpn' + slvl,
dim_in,
4 * num_anchors,
kernel=1,
pad=0,
stride=1,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0)
)
else:
# Share weights and biases
sk_min = str(k_min)
# RPN hidden representation
conv_rpn_fpn = model.ConvShared(
bl_in,
'conv_rpn_fpn' + slvl,
dim_in,
dim_out,
kernel=3,
pad=1,
stride=1,
weight='conv_rpn_fpn' + sk_min + '_w',
bias='conv_rpn_fpn' + sk_min + '_b'
)
model.Relu(conv_rpn_fpn, conv_rpn_fpn)
# Proposal classification scores
rpn_cls_logits_fpn = model.ConvShared(
conv_rpn_fpn,
'rpn_cls_logits_fpn' + slvl,
dim_in,
num_anchors,
kernel=1,
pad=0,
stride=1,
weight='rpn_cls_logits_fpn' + sk_min + '_w',
bias='rpn_cls_logits_fpn' + sk_min + '_b'
)
# Proposal bbox regression deltas
rpn_bbox_pred_fpn = model.ConvShared(
conv_rpn_fpn,
'rpn_bbox_pred_fpn' + slvl,
dim_in,
4 * num_anchors,
kernel=1,
pad=0,
stride=1,
weight='rpn_bbox_pred_fpn' + sk_min + '_w',
bias='rpn_bbox_pred_fpn' + sk_min + '_b'
)
if not model.train or cfg.MODEL.FASTER_RCNN:
# Proposals are needed during:
# 1) inference (== not model.train) for RPN only and Faster R-CNN
# OR
# 2) training for Faster R-CNN
# Otherwise (== training for RPN only), proposals are not needed
lvl_anchors = generate_anchors(
stride=2.**lvl,
sizes=(cfg.FPN.RPN_ANCHOR_START_SIZE * 2.**(lvl - k_min), ),
aspect_ratios=cfg.FPN.RPN_ASPECT_RATIOS
)
rpn_cls_probs_fpn = model.net.Sigmoid(
rpn_cls_logits_fpn, 'rpn_cls_probs_fpn' + slvl
)
model.GenerateProposals(
[rpn_cls_probs_fpn, rpn_bbox_pred_fpn, 'im_info'],
['rpn_rois_fpn' + slvl, 'rpn_roi_probs_fpn' + slvl],
anchors=lvl_anchors,
spatial_scale=sc
)
def add_fpn(model, fpn_level_info):
"""Add FPN connections based on the model described in the FPN paper."""
# FPN levels are built starting from the highest/coarest level of the
# backbone (usually "conv5"). First we build down, recursively constructing
# lower/finer resolution FPN levels. Then we build up, constructing levels
# that are even higher/coarser than the starting level.
fpn_dim = cfg.FPN.DIM
min_level, max_level = get_min_max_levels()
# Count the number of backbone stages that we will generate FPN levels for
# starting from the coarest backbone stage (usually the "conv5"-like level)
# E.g., if the backbone level info defines stages 4 stages: "conv5",
# "conv4", ... "conv2" and min_level=2, then we end up with 4 - (2 - 2) = 4
# backbone stages to add FPN to.
num_backbone_stages = (
len(fpn_level_info.blobs) - (min_level - LOWEST_BACKBONE_LVL)
)
lateral_input_blobs = fpn_level_info.blobs[:num_backbone_stages]
output_blobs = [
'fpn_inner_{}'.format(s)
for s in fpn_level_info.blobs[:num_backbone_stages]
]
fpn_dim_lateral = fpn_level_info.dims
xavier_fill = ('XavierFill', {})
# For the coarsest backbone level: 1x1 conv only seeds recursion
if cfg.FPN.USE_GN:
# use GroupNorm
c = model.ConvGN(
lateral_input_blobs[0],
output_blobs[0], # note: this is a prefix
dim_in=fpn_dim_lateral[0],
dim_out=fpn_dim,
group_gn=get_group_gn(fpn_dim),
kernel=1,
pad=0,
stride=1,
weight_init=xavier_fill,
bias_init=const_fill(0.0)
)
output_blobs[0] = c # rename it
else:
model.Conv(
lateral_input_blobs[0],
output_blobs[0],
dim_in=fpn_dim_lateral[0],
dim_out=fpn_dim,
kernel=1,
pad=0,
stride=1,
weight_init=xavier_fill,
bias_init=const_fill(0.0)
)
#
# Step 1: recursively build down starting from the coarsest backbone level
#
# For other levels add top-down and lateral connections
for i in range(num_backbone_stages - 1):
add_topdown_lateral_module(
model,
output_blobs[i], # top-down blob
lateral_input_blobs[i + 1], # lateral blob
output_blobs[i + 1], # next output blob
fpn_dim, # output dimension
fpn_dim_lateral[i + 1] # lateral input dimension
)
# Post-hoc scale-specific 3x3 convs
blobs_fpn = []
spatial_scales = []
for i in range(num_backbone_stages):
if cfg.FPN.USE_GN:
# use GroupNorm
fpn_blob = model.ConvGN(
output_blobs[i],
'fpn_{}'.format(fpn_level_info.blobs[i]),
dim_in=fpn_dim,
dim_out=fpn_dim,
group_gn=get_group_gn(fpn_dim),
kernel=3,
pad=1,
stride=1,
weight_init=xavier_fill,
bias_init=const_fill(0.0)
)
else:
fpn_blob = model.Conv(
output_blobs[i],
'fpn_{}'.format(fpn_level_info.blobs[i]),
dim_in=fpn_dim,
dim_out=fpn_dim,
kernel=3,
pad=1,
stride=1,
weight_init=xavier_fill,
bias_init=const_fill(0.0)
)
blobs_fpn += [fpn_blob]
spatial_scales += [fpn_level_info.spatial_scales[i]]
#
# Step 2: build up starting from the coarsest backbone level
#
# Check if we need the P6 feature map
if not cfg.FPN.EXTRA_CONV_LEVELS and max_level == HIGHEST_BACKBONE_LVL + 1:
# Original FPN P6 level implementation from our CVPR'17 FPN paper
P6_blob_in = blobs_fpn[0]
P6_name = P6_blob_in + '_subsampled_2x'
# Use max pooling to simulate stride 2 subsampling
P6_blob = model.MaxPool(P6_blob_in, P6_name, kernel=1, pad=0, stride=2)
blobs_fpn.insert(0, P6_blob)
spatial_scales.insert(0, spatial_scales[0] * 0.5)
# Coarser FPN levels introduced for RetinaNet
if cfg.FPN.EXTRA_CONV_LEVELS and max_level > HIGHEST_BACKBONE_LVL:
fpn_blob = fpn_level_info.blobs[0]
dim_in = fpn_level_info.dims[0]
for i in range(HIGHEST_BACKBONE_LVL + 1, max_level + 1):
fpn_blob_in = fpn_blob
if i > HIGHEST_BACKBONE_LVL + 1:
fpn_blob_in = model.Relu(fpn_blob, fpn_blob + '_relu')
fpn_blob = model.Conv(
fpn_blob_in,
'fpn_' + str(i),
dim_in=dim_in,
dim_out=fpn_dim,
kernel=3,
pad=1,
stride=2,
weight_init=xavier_fill,
bias_init=const_fill(0.0)
)
dim_in = fpn_dim
blobs_fpn.insert(0, fpn_blob)
spatial_scales.insert(0, spatial_scales[0] * 0.5)
return blobs_fpn, fpn_dim, spatial_scales
def add_cascade_fast_rcnn_outputs(model, blobs_in, dim, stage_num):
"""Add RoI classification and bounding box regression output ops."""
# Box regression layer
num_bbox_reg_classes = (
2 if cfg.MODEL.CLS_AGNOSTIC_BBOX_REG else model.num_classes
)
if stage_num == 1:
model.FC(
blobs_in[0],
'cls_score_1st',
dim,
model.num_classes,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0)
)
if not model.train: # == if test
# Only add softmax when testing; during training the softmax is combined
# with the label cross entropy loss for numerical stability
model.Softmax('cls_score_1st', 'cls_prob_1st', engine='CUDNN')
model.FC(
blobs_in[0],
'bbox_pred_1st',
dim,
num_bbox_reg_classes * 4,
weight_init=gauss_fill(0.001),
bias_init=const_fill(0.0)
)
elif stage_num == 2:
model.FC(
blobs_in[0],
'cls_score_2nd',
dim,
model.num_classes,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0)
)
if not model.train: # == if test
# Only add softmax when testing; during training the softmax is combined
# with the label cross entropy loss for numerical stability
assert len(blobs_in) == 2, 'during inference, need fc2_2nd and fc2_1st_2nd as in put blobsin rcnn stage 2'
model.Softmax('cls_score_2nd', 'cls_prob_2nd_2nd', engine='CUDNN')
cls_prob_2nd_2nd = model.Softmax('cls_score_2nd', 'cls_prob_2nd_2nd', engine='CUDNN')
model.FCShared(
blobs_in[1],
'cls_score_1st_2nd',
dim,
model.num_classes,
weight='cls_score_1st_w',
bias='cls_score_1st_b'
)
cls_prob_1st_2nd = model.Softmax('cls_score_1st_2nd', 'cls_prob_1st_2nd', engine='CUDNN')
model.Sum([cls_prob_2nd_2nd, cls_prob_1st_2nd], 'cls_prob_2nd')
model.Scale('cls_prob_2nd', 'cls_prob_2nd', scale=0.5)
model.FC(
blobs_in[0],
'bbox_pred_2nd',
dim,
num_bbox_reg_classes * 4,
weight_init=gauss_fill(0.001),
bias_init=const_fill(0.0)
)
elif stage_num == 3:
model.FC(
blobs_in[0],
'cls_score_3rd',
dim,
model.num_classes,
weight_init=gauss_fill(0.01),
bias_init=const_fill(0.0)
)
if not model.train: # == if test
# Only add softmax when testing; during training the softmax is combined
# with the label cross entropy loss for numerical stability
assert len(blobs_in) == 3, 'during inference, need fc2_2nd and fc2_1st_2nd as in put blobsin rcnn stage 3'
model.Softmax('cls_score_3rd', 'cls_prob_3rd_3rd', engine='CUDNN')
cls_prob_3rd_3rd = model.Softmax('cls_score_3rd', 'cls_prob_3rd_3rd', engine='CUDNN')
model.FCShared(
blobs_in[1],
'cls_score_1st_3rd',
dim,
model.num_classes,
weight='cls_score_1st_w',
bias='cls_score_1st_b'
)
cls_prob_1st_3rd = model.Softmax('cls_score_1st_3rd', 'cls_prob_1st_3rd', engine='CUDNN')
model.FCShared(
blobs_in[2],
'cls_score_2nd_3rd',
dim,
model.num_classes,
weight='cls_score_2nd_w',
bias='cls_score_2nd_b'
)
cls_prob_2nd_3rd = model.Softmax('cls_score_2nd_3rd', 'cls_prob_2nd_3rd', engine='CUDNN')
model.Sum([cls_prob_1st_3rd, cls_prob_2nd_3rd, cls_prob_3rd_3rd], 'cls_prob_3rd')
model.Scale('cls_prob_3rd', 'cls_prob_3rd', scale=0.33333333)
model.FC(
blobs_in[0],
'bbox_pred_3rd',
dim,
num_bbox_reg_classes * 4,
weight_init=gauss_fill(0.001),
bias_init=const_fill(0.0)
)
def add_roi_cascade_2mlp_head(model, blob_in, dim_in, spatial_scale, stage_num):
"""Add cascade ReLU MLP with two hidden layers."""
hidden_dim = cfg.FAST_RCNN.MLP_HEAD_DIM
roi_size = cfg.FAST_RCNN.ROI_XFORM_RESOLUTION
if stage_num == 1:
roi_feat = model.RoIFeatureTransform(
blob_in,
'roi_feat_1st',
blob_rois='rois_1st',
method=cfg.FAST_RCNN.ROI_XFORM_METHOD,
resolution=roi_size,
sampling_ratio=cfg.FAST_RCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale
)
model.FC(roi_feat, 'fc1' + '_1st', dim_in * roi_size * roi_size, hidden_dim, weight_init=("MSRAFill", {}), bias_init=const_fill(0.0))
model.Relu('fc1' + '_1st', 'fc1' + '_1st')
model.FC('fc1' + '_1st', 'fc2' + '_1st', hidden_dim, hidden_dim, weight_init=("MSRAFill", {}), bias_init=const_fill(0.0))
model.Relu('fc2' + '_1st', 'fc2' + '_1st')
return ['fc2' + '_1st'], hidden_dim
elif stage_num == 2:
roi_feat = model.RoIFeatureTransform(
blob_in,
'roi_feat_2nd',
blob_rois='rois_2nd',
method=cfg.FAST_RCNN.ROI_XFORM_METHOD,
resolution=roi_size,
sampling_ratio=cfg.FAST_RCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale
)
model.FC(roi_feat, 'fc1' + '_2nd', dim_in * roi_size * roi_size, hidden_dim, weight_init=("MSRAFill", {}), bias_init=const_fill(0.0))
model.Relu('fc1' + '_2nd', 'fc1' + '_2nd')
model.FC('fc1' + '_2nd', 'fc2' + '_2nd', hidden_dim, hidden_dim, weight_init=("MSRAFill", {}), bias_init=const_fill(0.0))
model.Relu('fc2' + '_2nd', 'fc2' + '_2nd')
if not model.train:
model.FCShared(roi_feat, 'fc1' + '_1st' + '_2nd', dim_in * roi_size * roi_size, hidden_dim, weight='fc1_1st_w', bias='fc1_1st_b')
model.Relu('fc1' + '_1st' + '_2nd', 'fc1' + '_1st' + '_2nd')
model.FCShared('fc1' + '_1st' + '_2nd', 'fc2' + '_1st' + '_2nd', hidden_dim, hidden_dim, weight='fc2_1st_w', bias='fc2_1st_b')
model.Relu('fc2' + '_1st' + '_2nd', 'fc2' + '_1st' + '_2nd')
return ['fc2' + '_2nd', 'fc2' + '_1st' + '_2nd'], hidden_dim
elif stage_num == 3:
roi_feat = model.RoIFeatureTransform(
blob_in,
'roi_feat_3rd',
blob_rois='rois_3rd',
method=cfg.FAST_RCNN.ROI_XFORM_METHOD,
resolution=roi_size,
sampling_ratio=cfg.FAST_RCNN.ROI_XFORM_SAMPLING_RATIO,
spatial_scale=spatial_scale
)
model.FC(roi_feat, 'fc1' + '_3rd', dim_in * roi_size * roi_size, hidden_dim, weight_init=("MSRAFill", {}), bias_init=const_fill(0.0))
model.Relu('fc1' + '_3rd', 'fc1' + '_3rd')
model.FC('fc1' + '_3rd', 'fc2' + '_3rd', hidden_dim, hidden_dim, weight_init=("MSRAFill", {}), bias_init=const_fill(0.0))
model.Relu('fc2' + '_3rd', 'fc2' + '_3rd')
if not model.train:
model.FCShared(roi_feat, 'fc1' + '_1st' + '_3rd', dim_in * roi_size * roi_size, hidden_dim, weight='fc1_1st_w', bias='fc1_1st_b')
model.Relu('fc1' + '_1st' + '_3rd', 'fc1' + '_1st' + '_3rd')
model.FCShared('fc1' + '_1st' + '_3rd', 'fc2' + '_1st' + '_3rd', hidden_dim, hidden_dim, weight='fc2_1st_w', bias='fc2_1st_b')
model.Relu('fc2' + '_1st' + '_3rd', 'fc2' + '_1st' + '_3rd')
model.FCShared(roi_feat, 'fc1' + '_2nd' + '_3rd', dim_in * roi_size * roi_size, hidden_dim, weight='fc1_2nd_w', bias='fc1_2nd_b')
model.Relu('fc1' + '_2nd' + '_3rd', 'fc1' + '_2nd' + '_3rd')
model.FCShared('fc1' + '_2nd' + '_3rd', 'fc2' + '_2nd' + '_3rd', hidden_dim, hidden_dim, weight='fc2_2nd_w', bias='fc2_2nd_b')
model.Relu('fc2' + '_2nd' + '_3rd', 'fc2' + '_2nd' + '_3rd')
return ['fc2' + '_3rd', 'fc2' + '_1st' + '_2nd', 'fc2' + '_2nd' + '_3rd'], hidden_dim