def _build_res5_block(self, cfg):
# fmt: off
stage_channel_factor = 2**3 # res5 is 8x res2
num_groups = cfg.MODEL.RESNETS.NUM_GROUPS
width_per_group = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
bottleneck_channels = num_groups * width_per_group * stage_channel_factor
out_channels = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS * stage_channel_factor
stride_in_1x1 = cfg.MODEL.RESNETS.STRIDE_IN_1X1
norm = cfg.MODEL.RESNETS.NORM
assert not cfg.MODEL.RESNETS.DEFORM_ON_PER_STAGE[-1], \
"Deformable conv is not yet supported in res5 head."
# fmt: on
blocks = make_stage(
TripletAttentionBottleneckBlock,
3,
first_stride=2,
in_channels=out_channels // 2,
bottleneck_channels=bottleneck_channels,
out_channels=out_channels,
num_groups=num_groups,
norm=norm,
stride_in_1x1=stride_in_1x1,
)
return nn.Sequential(*blocks), out_channels
def build_resnet_backbone_caffe_maxpool(cfg, input_shape):
"""
Create a ResNet instance from config.
Returns:
ResNet: a :class:`ResNet` instance.
"""
# need registration of new blocks/stems?
norm = cfg.MODEL.RESNETS.NORM
stem = BasicStemCaffeeMaxPool( #modified BasicStem -> BasicStemCaffeeMaxPool
in_channels=input_shape.channels,
out_channels=cfg.MODEL.RESNETS.STEM_OUT_CHANNELS,
norm=norm,
caffe_maxpool=cfg.MODEL.CAFFE_MAXPOOL, #added
)
freeze_at = cfg.MODEL.BACKBONE.FREEZE_AT
if freeze_at >= 1:
for p in stem.parameters():
p.requires_grad = False
stem = FrozenBatchNorm2d.convert_frozen_batchnorm(stem)
# fmt: off
out_features = cfg.MODEL.RESNETS.OUT_FEATURES
depth = cfg.MODEL.RESNETS.DEPTH
num_groups = cfg.MODEL.RESNETS.NUM_GROUPS
width_per_group = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
bottleneck_channels = num_groups * width_per_group
in_channels = cfg.MODEL.RESNETS.STEM_OUT_CHANNELS
out_channels = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS
stride_in_1x1 = cfg.MODEL.RESNETS.STRIDE_IN_1X1
res5_dilation = cfg.MODEL.RESNETS.RES5_DILATION
deform_on_per_stage = cfg.MODEL.RESNETS.DEFORM_ON_PER_STAGE
deform_modulated = cfg.MODEL.RESNETS.DEFORM_MODULATED
deform_num_groups = cfg.MODEL.RESNETS.DEFORM_NUM_GROUPS
# fmt: on
assert res5_dilation in {1, 2}, "res5_dilation cannot be {}.".format(res5_dilation)
num_blocks_per_stage = {50: [3, 4, 6, 3], 101: [3, 4, 23, 3], 152: [3, 8, 36, 3]}[depth]
stages = []
# Avoid creating variables without gradients
# It consumes extra memory and may cause allreduce to fail
out_stage_idx = [{"res2": 2, "res3": 3, "res4": 4, "res5": 5}[f] for f in out_features]
max_stage_idx = max(out_stage_idx)
for idx, stage_idx in enumerate(range(2, max_stage_idx + 1)):
dilation = res5_dilation if stage_idx == 5 else 1
first_stride = 1 if idx == 0 or (stage_idx == 5 and dilation == 2) else 2
stage_kargs = {
"num_blocks": num_blocks_per_stage[idx],
"first_stride": first_stride,
"in_channels": in_channels,
"bottleneck_channels": bottleneck_channels,
"out_channels": out_channels,
"num_groups": num_groups,
"norm": norm,
"stride_in_1x1": stride_in_1x1,
"dilation": dilation,
}
if deform_on_per_stage[idx]:
stage_kargs["block_class"] = DeformBottleneckBlock
stage_kargs["deform_modulated"] = deform_modulated
stage_kargs["deform_num_groups"] = deform_num_groups
else:
stage_kargs["block_class"] = BottleneckBlock
blocks = make_stage(**stage_kargs)
in_channels = out_channels
out_channels *= 2
bottleneck_channels *= 2
if freeze_at >= stage_idx:
for block in blocks:
block.freeze()
stages.append(blocks)
return ResNet(stem, stages, out_features=out_features)
def build_trident_resnet_backbone(cfg, input_shape):
"""
Create a ResNet instance from config for TridentNet.
Returns:
ResNet: a :class:`ResNet` instance.
"""
# need registration of new blocks/stems?
norm = cfg.MODEL.RESNETS.NORM
stem = BasicStem(
in_channels=input_shape.channels,
out_channels=cfg.MODEL.RESNETS.STEM_OUT_CHANNELS,
norm=norm,
)
freeze_at = cfg.MODEL.BACKBONE.FREEZE_AT
if freeze_at >= 1:
for p in stem.parameters():
p.requires_grad = False
stem = FrozenBatchNorm2d.convert_frozen_batchnorm(stem)
# fmt: off
out_features = cfg.MODEL.RESNETS.OUT_FEATURES
depth = cfg.MODEL.RESNETS.DEPTH
num_groups = cfg.MODEL.RESNETS.NUM_GROUPS
width_per_group = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
bottleneck_channels = num_groups * width_per_group
in_channels = cfg.MODEL.RESNETS.STEM_OUT_CHANNELS
out_channels = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS
stride_in_1x1 = cfg.MODEL.RESNETS.STRIDE_IN_1X1
res5_dilation = cfg.MODEL.RESNETS.RES5_DILATION
deform_on_per_stage = cfg.MODEL.RESNETS.DEFORM_ON_PER_STAGE
deform_modulated = cfg.MODEL.RESNETS.DEFORM_MODULATED
deform_num_groups = cfg.MODEL.RESNETS.DEFORM_NUM_GROUPS
num_branch = cfg.MODEL.TRIDENT.NUM_BRANCH
branch_dilations = cfg.MODEL.TRIDENT.BRANCH_DILATIONS
trident_stage = cfg.MODEL.TRIDENT.TRIDENT_STAGE
test_branch_idx = cfg.MODEL.TRIDENT.TEST_BRANCH_IDX
# fmt: on
assert res5_dilation in {
1, 2
}, "res5_dilation cannot be {}.".format(res5_dilation)
num_blocks_per_stage = {
50: [3, 4, 6, 3],
101: [3, 4, 23, 3],
152: [3, 8, 36, 3]
}[depth]
stages = []
res_stage_idx = {"res2": 2, "res3": 3, "res4": 4, "res5": 5}
out_stage_idx = [res_stage_idx[f] for f in out_features]
trident_stage_idx = res_stage_idx[trident_stage]
max_stage_idx = max(out_stage_idx)
for idx, stage_idx in enumerate(range(2, max_stage_idx + 1)):
dilation = res5_dilation if stage_idx == 5 else 1
first_stride = 1 if idx == 0 or (stage_idx == 5
and dilation == 2) else 2
stage_kargs = {
"num_blocks": num_blocks_per_stage[idx],
"first_stride": first_stride,
"in_channels": in_channels,
"bottleneck_channels": bottleneck_channels,
"out_channels": out_channels,
"num_groups": num_groups,
"norm": norm,
"stride_in_1x1": stride_in_1x1,
"dilation": dilation,
}
if stage_idx == trident_stage_idx:
assert not deform_on_per_stage[
idx], "Not support deformable conv in Trident blocks yet."
stage_kargs["block_class"] = TridentBottleneckBlock
stage_kargs["num_branch"] = num_branch
stage_kargs["dilations"] = branch_dilations
stage_kargs["test_branch_idx"] = test_branch_idx
stage_kargs.pop("dilation")
elif deform_on_per_stage[idx]:
stage_kargs["block_class"] = DeformBottleneckBlock
stage_kargs["deform_modulated"] = deform_modulated
stage_kargs["deform_num_groups"] = deform_num_groups
else:
stage_kargs["block_class"] = BottleneckBlock
blocks = (make_trident_stage(**stage_kargs) if stage_idx
== trident_stage_idx else make_stage(**stage_kargs))
in_channels = out_channels
out_channels *= 2
bottleneck_channels *= 2
if freeze_at >= stage_idx:
for block in blocks:
block.freeze()
stages.append(blocks)
return ResNet(stem, stages, out_features=out_features)
def build_resnet_triplet_attention_backbone(cfg, input_shape):
"""
Create a ResNet instance from config.
Returns:
ResNet: a :class:`ResNet` instance.
"""
# need registration of new blocks/stems?
norm = cfg.MODEL.RESNETS.NORM
stem = BasicStem(
in_channels=input_shape.channels,
out_channels=cfg.MODEL.RESNETS.STEM_OUT_CHANNELS,
norm=norm,
)
# fmt: off
freeze_at = cfg.MODEL.BACKBONE.FREEZE_AT
out_features = cfg.MODEL.RESNETS.OUT_FEATURES
depth = cfg.MODEL.RESNETS.DEPTH
num_groups = cfg.MODEL.RESNETS.NUM_GROUPS
width_per_group = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
bottleneck_channels = num_groups * width_per_group
in_channels = cfg.MODEL.RESNETS.STEM_OUT_CHANNELS
out_channels = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS
stride_in_1x1 = cfg.MODEL.RESNETS.STRIDE_IN_1X1
res5_dilation = cfg.MODEL.RESNETS.RES5_DILATION
deform_on_per_stage = cfg.MODEL.RESNETS.DEFORM_ON_PER_STAGE
deform_modulated = cfg.MODEL.RESNETS.DEFORM_MODULATED
deform_num_groups = cfg.MODEL.RESNETS.DEFORM_NUM_GROUPS
# fmt: on
assert res5_dilation in {
1, 2
}, "res5_dilation cannot be {}.".format(res5_dilation)
num_blocks_per_stage = {
18: [2, 2, 2, 2],
34: [3, 4, 6, 3],
50: [3, 4, 6, 3],
101: [3, 4, 23, 3],
152: [3, 8, 36, 3],
}[depth]
if depth in [18, 34]:
assert out_channels == 64, "Must set MODEL.RESNETS.RES2_OUT_CHANNELS = 64 for R18/R34"
assert not any(
deform_on_per_stage
), "MODEL.RESNETS.DEFORM_ON_PER_STAGE unsupported for R18/R34"
assert res5_dilation == 1, "Must set MODEL.RESNETS.RES5_DILATION = 1 for R18/R34"
assert num_groups == 1, "Must set MODEL.RESNETS.NUM_GROUPS = 1 for R18/R34"
stages = []
# Avoid creating variables without gradients
# It consumes extra memory and may cause allreduce to fail
out_stage_idx = [{
"res2": 2,
"res3": 3,
"res4": 4,
"res5": 5
}[f] for f in out_features]
max_stage_idx = max(out_stage_idx)
for idx, stage_idx in enumerate(range(2, max_stage_idx + 1)):
dilation = res5_dilation if stage_idx == 5 else 1
first_stride = 1 if idx == 0 or (stage_idx == 5
and dilation == 2) else 2
stage_kargs = {
"num_blocks": num_blocks_per_stage[idx],
"first_stride": first_stride,
"in_channels": in_channels,
"out_channels": out_channels,
"norm": norm,
}
# Use BasicBlock for R18 and R34.
if depth in [18, 34]:
stage_kargs["block_class"] = TripletAttentionBasicBlock
else:
stage_kargs["bottleneck_channels"] = bottleneck_channels
stage_kargs["stride_in_1x1"] = stride_in_1x1
stage_kargs["dilation"] = dilation
stage_kargs["num_groups"] = num_groups
#if deform_on_per_stage[idx]:
# stage_kargs["block_class"] = DeformBottleneckBlock
# stage_kargs["deform_modulated"] = deform_modulated
# stage_kargs["deform_num_groups"] = deform_num_groups
#else:
stage_kargs["block_class"] = TripletAttentionBottleneckBlock
blocks = make_stage(**stage_kargs)
in_channels = out_channels
out_channels *= 2
bottleneck_channels *= 2
stages.append(blocks)
return ResNet(stem, stages, out_features=out_features).freeze(freeze_at)
def build_deepent_fused_resnet_backbone(cfg, input_shape):
"""
Create a ResNet instance from config.
Returns:
ResNet: a :class:`ResNet` instance.
"""
# need registration of new blocks/stems?
norm = cfg.MODEL.RESNETS.NORM
assert input_shape.channels == 4, f'{input_shape.channels} input channels specified, should be 4'
depth_shape = input_shape._replace(channels=1)
input_shape = input_shape._replace(channels=3)
depth_encoder = build_depth_encoder_backbone(cfg, depth_shape)
stem = BasicStem(
in_channels=input_shape.channels,
out_channels=cfg.MODEL.RESNETS.STEM_OUT_CHANNELS,
norm=norm,
)
freeze_at = cfg.MODEL.BACKBONE.FREEZE_AT
if freeze_at >= 1:
for p in stem.parameters():
p.requires_grad = False
stem = FrozenBatchNorm2d.convert_frozen_batchnorm(stem)
# fmt: off
in_features = cfg.MODEL.RESNETS.IN_FEATURES
fuse_method = cfg.MODEL.RESNETS.FUSE_METHOD
out_features = cfg.MODEL.RESNETS.OUT_FEATURES
depth = cfg.MODEL.RESNETS.DEPTH
num_groups = cfg.MODEL.RESNETS.NUM_GROUPS
width_per_group = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
bottleneck_channels = num_groups * width_per_group
in_channels = cfg.MODEL.RESNETS.STEM_OUT_CHANNELS
out_channels = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS
stride_in_1x1 = cfg.MODEL.RESNETS.STRIDE_IN_1X1
res5_dilation = cfg.MODEL.RESNETS.RES5_DILATION
# fmt: on
assert res5_dilation in {
1, 2
}, "res5_dilation cannot be {}.".format(res5_dilation)
num_blocks_per_stage = {
50: [3, 4, 6, 3],
101: [3, 4, 23, 3],
152: [3, 8, 36, 3]
}[depth]
stages = []
# Avoid creating variables without gradients
# It consumes extra memory and may cause allreduce to fail
out_stage_idx = [{
"res2": 2,
"res3": 3,
"res4": 4,
"res5": 5
}[f] for f in out_features]
max_stage_idx = max(out_stage_idx)
for idx, stage_idx in enumerate(range(2, max_stage_idx + 1)):
dilation = res5_dilation if stage_idx == 5 else 1
first_stride = 1 if idx == 0 or (stage_idx == 5
and dilation == 2) else 2
stage_kargs = {
"num_blocks": num_blocks_per_stage[idx],
"first_stride": first_stride,
"in_channels": in_channels,
"bottleneck_channels": bottleneck_channels,
"out_channels": out_channels,
"num_groups": num_groups,
"norm": norm,
"stride_in_1x1": stride_in_1x1,
"dilation": dilation,
"block_class": BottleneckBlock
}
blocks = make_stage(**stage_kargs)
in_channels = out_channels
out_channels *= 2
bottleneck_channels *= 2
if freeze_at >= stage_idx:
for block in blocks:
block.freeze()
stages.append(blocks)
return FusedResNet(stem,
stages,
depth_encoder=depth_encoder,
in_features=in_features,
out_features=out_features,
fuse_method=fuse_method)
