def __init__(self,
in_channels,
out_channels,
num_outs,
start_level=0,
end_level=-1,
norm_cfg=None,
act_cfg=None,
order=('conv', 'norm', 'act'),
upsample_cfg=dict(type='carafe',
up_kernel=5,
up_group=1,
encoder_kernel=3,
encoder_dilation=1)):
super(FPN_CARAFE, self).__init__()
assert isinstance(in_channels, list)
self.in_channels = in_channels
self.out_channels = out_channels
self.num_ins = len(in_channels)
self.num_outs = num_outs
self.norm_cfg = norm_cfg
self.act_cfg = act_cfg
self.with_bias = norm_cfg is None
self.upsample_cfg = upsample_cfg.copy()
self.upsample = self.upsample_cfg.get('type')
self.relu = nn.ReLU(inplace=False)
self.fp16_enabled = False
self.order = order
assert order in [('conv', 'norm', 'act'), ('act', 'conv', 'norm')]
assert self.upsample in [
'nearest', 'bilinear', 'deconv', 'pixel_shuffle', 'carafe', None
]
if self.upsample in ['deconv', 'pixel_shuffle']:
assert hasattr(
self.upsample_cfg,
'upsample_kernel') and self.upsample_cfg.upsample_kernel > 0
self.upsample_kernel = self.upsample_cfg.pop('upsample_kernel')
if end_level == -1:
self.backbone_end_level = self.num_ins
assert num_outs >= self.num_ins - start_level
else:
# if end_level < inputs, no extra level is allowed
self.backbone_end_level = end_level
assert end_level <= len(in_channels)
assert num_outs == end_level - start_level
self.start_level = start_level
self.end_level = end_level
self.lateral_convs = nn.ModuleList()
self.fpn_convs = nn.ModuleList()
self.upsample_modules = nn.ModuleList()
for i in range(self.start_level, self.backbone_end_level):
l_conv = ConvModule(in_channels[i],
out_channels,
1,
norm_cfg=norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order)
fpn_conv = ConvModule(out_channels,
out_channels,
3,
padding=1,
norm_cfg=self.norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order)
if i != self.backbone_end_level - 1:
upsample_cfg_ = self.upsample_cfg.copy()
if self.upsample == 'deconv':
upsample_cfg_.update(
in_channels=out_channels,
out_channels=out_channels,
kernel_size=self.upsample_kernel,
stride=2,
padding=(self.upsample_kernel - 1) // 2,
output_padding=(self.upsample_kernel - 1) // 2)
elif self.upsample == 'pixel_shuffle':
upsample_cfg_.update(in_channels=out_channels,
out_channels=out_channels,
scale_factor=2,
upsample_kernel=self.upsample_kernel)
elif self.upsample == 'carafe':
upsample_cfg_.update(channels=out_channels, scale_factor=2)
else:
# suppress warnings
align_corners = (None
if self.upsample == 'nearest' else False)
upsample_cfg_.update(scale_factor=2,
mode=self.upsample,
align_corners=align_corners)
upsample_module = build_upsample_layer(upsample_cfg_)
self.upsample_modules.append(upsample_module)
self.lateral_convs.append(l_conv)
self.fpn_convs.append(fpn_conv)
# add extra conv layers (e.g., RetinaNet)
extra_out_levels = (num_outs - self.backbone_end_level +
self.start_level)
if extra_out_levels >= 1:
for i in range(extra_out_levels):
in_channels = (self.in_channels[self.backbone_end_level -
1] if i == 0 else out_channels)
extra_l_conv = ConvModule(in_channels,
out_channels,
3,
stride=2,
padding=1,
norm_cfg=norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order)
if self.upsample == 'deconv':
upsampler_cfg_ = dict(
in_channels=out_channels,
out_channels=out_channels,
kernel_size=self.upsample_kernel,
stride=2,
padding=(self.upsample_kernel - 1) // 2,
output_padding=(self.upsample_kernel - 1) // 2)
elif self.upsample == 'pixel_shuffle':
upsampler_cfg_ = dict(in_channels=out_channels,
out_channels=out_channels,
scale_factor=2,
upsample_kernel=self.upsample_kernel)
elif self.upsample == 'carafe':
upsampler_cfg_ = dict(channels=out_channels,
scale_factor=2,
**self.upsample_cfg)
else:
# suppress warnings
align_corners = (None
if self.upsample == 'nearest' else False)
upsampler_cfg_ = dict(scale_factor=2,
mode=self.upsample,
align_corners=align_corners)
upsampler_cfg_['type'] = self.upsample
upsample_module = build_upsample_layer(upsampler_cfg_)
extra_fpn_conv = ConvModule(out_channels,
out_channels,
3,
padding=1,
norm_cfg=self.norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order)
self.upsample_modules.append(upsample_module)
self.fpn_convs.append(extra_fpn_conv)
self.lateral_convs.append(extra_l_conv)
def __init__(self,
num_convs=4,
roi_feat_size=14,
in_channels=256,
conv_kernel_size=3,
conv_out_channels=256,
num_classes=81,
class_agnostic=False,
upsample_cfg=dict(type='deconv', scale_factor=2),
conv_cfg=None,
norm_cfg=None,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)):
super(FCNMaskHead, self).__init__()
self.upsample_cfg = upsample_cfg.copy()
if self.upsample_cfg['type'] not in [
None, 'deconv', 'nearest', 'bilinear', 'carafe'
]:
raise ValueError(
'Invalid upsample method {}, accepted methods '
'are "deconv", "nearest", "bilinear", "carafe"'.format(
self.upsample_cfg['type']))
self.num_convs = num_convs
# WARN: roi_feat_size is reserved and not used
self.roi_feat_size = _pair(roi_feat_size)
self.in_channels = in_channels
self.conv_kernel_size = conv_kernel_size
self.conv_out_channels = conv_out_channels
self.upsample_method = self.upsample_cfg.get('type')
self.scale_factor = self.upsample_cfg.pop('scale_factor')
self.num_classes = num_classes
self.class_agnostic = class_agnostic
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.fp16_enabled = False
self.loss_mask = build_loss(loss_mask)
self.convs = nn.ModuleList()
for i in range(self.num_convs):
in_channels = (
self.in_channels if i == 0 else self.conv_out_channels)
padding = (self.conv_kernel_size - 1) // 2
self.convs.append(
ConvModule(
in_channels,
self.conv_out_channels,
self.conv_kernel_size,
padding=padding,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg))
upsample_in_channels = (
self.conv_out_channels if self.num_convs > 0 else in_channels)
upsample_cfg_ = self.upsample_cfg.copy()
if self.upsample_method is None:
self.upsample = None
elif self.upsample_method == 'deconv':
upsample_cfg_.update(
in_channels=upsample_in_channels,
out_channels=self.conv_out_channels,
kernel_size=self.scale_factor,
stride=self.scale_factor)
elif self.upsample_method == 'carafe':
upsample_cfg_.update(
channels=upsample_in_channels, scale_factor=self.scale_factor)
else:
# suppress warnings
align_corners = (None
if self.upsample_method == 'nearest' else False)
upsample_cfg_.update(
scale_factor=self.scale_factor,
mode=self.upsample_method,
align_corners=align_corners)
self.upsample = build_upsample_layer(upsample_cfg_)
out_channels = 1 if self.class_agnostic else self.num_classes
logits_in_channel = (
self.conv_out_channels
if self.upsample_method == 'deconv' else upsample_in_channels)
self.conv_logits = nn.Conv2d(logits_in_channel, out_channels, 1)
self.relu = nn.ReLU(inplace=True)
self.debug_imgs = None
def __init__(
self,
in_channels,
out_channels,
num_outs,
start_level=0,
end_level=-1,
norm_cfg=None,
act_cfg=None,
order=("conv", "norm", "act"),
upsample_cfg=dict(type="carafe",
up_kernel=5,
up_group=1,
encoder_kernel=3,
encoder_dilation=1),
):
super(FPN_CARAFE, self).__init__()
assert isinstance(in_channels, list)
self.in_channels = in_channels
self.out_channels = out_channels
self.num_ins = len(in_channels)
self.num_outs = num_outs
self.norm_cfg = norm_cfg
self.act_cfg = act_cfg
self.with_bias = norm_cfg is None
self.upsample_cfg = upsample_cfg.copy()
self.upsample = self.upsample_cfg.get("type")
self.relu = nn.ReLU(inplace=False)
self.order = order
assert order in [("conv", "norm", "act"), ("act", "conv", "norm")]
assert self.upsample in [
"nearest",
"bilinear",
"deconv",
"pixel_shuffle",
"carafe",
None,
]
if self.upsample in ["deconv", "pixel_shuffle"]:
assert (hasattr(self.upsample_cfg, "upsample_kernel")
and self.upsample_cfg.upsample_kernel > 0)
self.upsample_kernel = self.upsample_cfg.pop("upsample_kernel")
if end_level == -1:
self.backbone_end_level = self.num_ins
assert num_outs >= self.num_ins - start_level
else:
# if end_level < inputs, no extra level is allowed
self.backbone_end_level = end_level
assert end_level <= len(in_channels)
assert num_outs == end_level - start_level
self.start_level = start_level
self.end_level = end_level
self.lateral_convs = nn.ModuleList()
self.fpn_convs = nn.ModuleList()
self.upsample_modules = nn.ModuleList()
for i in range(self.start_level, self.backbone_end_level):
l_conv = ConvModule(
in_channels[i],
out_channels,
1,
norm_cfg=norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order,
)
fpn_conv = ConvModule(
out_channels,
out_channels,
3,
padding=1,
norm_cfg=self.norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order,
)
if i != self.backbone_end_level - 1:
upsample_cfg_ = self.upsample_cfg.copy()
if self.upsample == "deconv":
upsample_cfg_.update(
in_channels=out_channels,
out_channels=out_channels,
kernel_size=self.upsample_kernel,
stride=2,
padding=(self.upsample_kernel - 1) // 2,
output_padding=(self.upsample_kernel - 1) // 2,
)
elif self.upsample == "pixel_shuffle":
upsample_cfg_.update(
in_channels=out_channels,
out_channels=out_channels,
scale_factor=2,
upsample_kernel=self.upsample_kernel,
)
elif self.upsample == "carafe":
upsample_cfg_.update(channels=out_channels, scale_factor=2)
else:
# suppress warnings
align_corners = None if self.upsample == "nearest" else False
upsample_cfg_.update(scale_factor=2,
mode=self.upsample,
align_corners=align_corners)
upsample_module = build_upsample_layer(upsample_cfg_)
self.upsample_modules.append(upsample_module)
self.lateral_convs.append(l_conv)
self.fpn_convs.append(fpn_conv)
# add extra conv layers (e.g., RetinaNet)
extra_out_levels = num_outs - self.backbone_end_level + self.start_level
if extra_out_levels >= 1:
for i in range(extra_out_levels):
in_channels = (self.in_channels[self.backbone_end_level -
1] if i == 0 else out_channels)
extra_l_conv = ConvModule(
in_channels,
out_channels,
3,
stride=2,
padding=1,
norm_cfg=norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order,
)
if self.upsample == "deconv":
upsampler_cfg_ = dict(
in_channels=out_channels,
out_channels=out_channels,
kernel_size=self.upsample_kernel,
stride=2,
padding=(self.upsample_kernel - 1) // 2,
output_padding=(self.upsample_kernel - 1) // 2,
)
elif self.upsample == "pixel_shuffle":
upsampler_cfg_ = dict(
in_channels=out_channels,
out_channels=out_channels,
scale_factor=2,
upsample_kernel=self.upsample_kernel,
)
elif self.upsample == "carafe":
upsampler_cfg_ = dict(channels=out_channels,
scale_factor=2,
**self.upsample_cfg)
else:
# suppress warnings
align_corners = None if self.upsample == "nearest" else False
upsampler_cfg_ = dict(scale_factor=2,
mode=self.upsample,
align_corners=align_corners)
upsampler_cfg_["type"] = self.upsample
upsample_module = build_upsample_layer(upsampler_cfg_)
extra_fpn_conv = ConvModule(
out_channels,
out_channels,
3,
padding=1,
norm_cfg=self.norm_cfg,
bias=self.with_bias,
act_cfg=act_cfg,
inplace=False,
order=self.order,
)
self.upsample_modules.append(upsample_module)
self.fpn_convs.append(extra_fpn_conv)
self.lateral_convs.append(extra_l_conv)
