def __init__(self, cfg, input_shape: ShapeSpec):
"""
The following attributes are parsed from config:
conv_dim: the output dimension of the conv layers
fc_dim: the feature dimenstion of the FC layers
num_fc: the number of FC layers
output_side_resolution: side resolution of the output square mask prediction
"""
super(CoarseMaskHead, self).__init__()
# fmt: off
self.num_classes = cfg.MODEL.ROI_HEADS.NUM_CLASSES
conv_dim = cfg.MODEL.ROI_MASK_HEAD.CONV_DIM
self.fc_dim = cfg.MODEL.ROI_MASK_HEAD.FC_DIM
num_fc = cfg.MODEL.ROI_MASK_HEAD.NUM_FC
self.output_side_resolution = cfg.MODEL.ROI_MASK_HEAD.OUTPUT_SIDE_RESOLUTION
self.input_channels = input_shape.channels
self.input_h = input_shape.height
self.input_w = input_shape.width
# fmt: on
self.conv_layers = []
if self.input_channels > conv_dim:
self.reduce_channel_dim_conv = Conv2d(
self.input_channels,
conv_dim,
kernel_size=1,
stride=1,
padding=0,
bias=True,
activation=F.relu,
)
self.conv_layers.append(self.reduce_channel_dim_conv)
self.reduce_spatial_dim_conv = Conv2d(
conv_dim, conv_dim, kernel_size=2, stride=2, padding=0, bias=True, activation=F.relu
)
self.conv_layers.append(self.reduce_spatial_dim_conv)
input_dim = conv_dim * self.input_h * self.input_w
input_dim //= 4
self.fcs = []
for k in range(num_fc):
fc = nn.Linear(input_dim, self.fc_dim)
self.add_module("coarse_mask_fc{}".format(k + 1), fc)
self.fcs.append(fc)
input_dim = self.fc_dim
output_dim = self.num_classes * self.output_side_resolution * self.output_side_resolution
self.prediction = nn.Linear(self.fc_dim, output_dim)
# use normal distribution initialization for mask prediction layer
nn.init.normal_(self.prediction.weight, std=0.001)
nn.init.constant_(self.prediction.bias, 0)
for layer in self.conv_layers:
weight_init.c2_msra_fill(layer)
for layer in self.fcs:
weight_init.c2_xavier_fill(layer)
def __init__(self, in_channels, out_channels, in_feature="res5"):
super().__init__()
self.num_levels = 2
self.in_feature = in_feature
self.p6 = nn.Conv2d(in_channels, out_channels, 3, 2, 1)
self.p7 = nn.Conv2d(out_channels, out_channels, 3, 2, 1)
for module in [self.p6, self.p7]:
weight_init.c2_xavier_fill(module)
self.use_P5 = in_channels == out_channels
def __init__(self, in_channels, out_channels, in_feature="res5"):
"""
Args:
in_feature: input feature name, e.g. "res5" stands for C5 features,
"p5" stands for P5 feature.
"""
super().__init__()
self.num_levels = 2
self.in_feature = in_feature
self.p6 = nn.Conv2d(in_channels, out_channels, 3, 2, 1)
self.p7 = nn.Conv2d(out_channels, out_channels, 3, 2, 1)
for module in [self.p6, self.p7]:
weight_init.c2_xavier_fill(module)
def _init_weight(self):
weight_init.c2_xavier_fill(self.lateral_conv)
weight_init.c2_xavier_fill(self.fpn_conv)
for m in [self.lateral_norm, self.fpn_norm]:
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
for m in self.dilated_encoder_blocks.modules():
if isinstance(m, nn.Conv2d):
nn.init.normal_(m.weight, mean=0, std=0.01)
if hasattr(m, 'bias') and m.bias is not None:
nn.init.constant_(m.bias, 0)
if isinstance(m, (nn.GroupNorm, nn.BatchNorm2d, nn.SyncBatchNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def __init__(self, cfg, input_shape: ShapeSpec):
"""
The following attributes are parsed from config:
num_conv, num_fc: the number of conv/fc layers
conv_dim/fc_dim: the dimension of the conv/fc layers
norm: normalization for the conv layers
"""
super().__init__()
# fmt: off
num_conv = cfg.MODEL.ROI_BOX_HEAD.NUM_CONV
conv_dim = cfg.MODEL.ROI_BOX_HEAD.CONV_DIM
num_fc = cfg.MODEL.ROI_BOX_HEAD.NUM_FC
fc_dim = cfg.MODEL.ROI_BOX_HEAD.FC_DIM
norm = cfg.MODEL.ROI_BOX_HEAD.NORM
# fmt: on
assert num_conv + num_fc > 0
self._output_size = (input_shape.channels, input_shape.height,
input_shape.width)
self.conv_norm_relus = []
for k in range(num_conv):
conv = Conv2d(
self._output_size[0],
conv_dim,
kernel_size=3,
padding=1,
bias=not norm,
norm=get_norm(norm, conv_dim),
activation=F.relu,
)
self.add_module("conv{}".format(k + 1), conv)
self.conv_norm_relus.append(conv)
self._output_size = (conv_dim, self._output_size[1],
self._output_size[2])
self.fcs = []
for k in range(num_fc):
fc = nn.Linear(np.prod(self._output_size), fc_dim)
self.add_module("fc{}".format(k + 1), fc)
self.fcs.append(fc)
self._output_size = fc_dim
for layer in self.conv_norm_relus:
weight_init.c2_msra_fill(layer)
for layer in self.fcs:
weight_init.c2_xavier_fill(layer)
def __init__(
self, bottom_up, in_features, out_channels, norm="", top_block=None, fuse_type="sum"
):
"""
Args:
bottom_up (Backbone): module representing the bottom up subnetwork.
Must be a subclass of :class:`Backbone`. The multi-scale feature
maps generated by the bottom up network, and listed in `in_features`,
are used to generate FPN levels.
in_features (list[str]): names of the input feature maps coming
from the backbone to which FPN is attached. For example, if the
backbone produces ["res2", "res3", "res4"], any *contiguous* sublist
of these may be used; order must be from high to low resolution.
out_channels (int): number of channels in the output feature maps.
norm (str): the normalization to use.
top_block (nn.Module or None): if provided, an extra operation will
be performed on the output of the last (smallest resolution)
FPN output, and the result will extend the result list. The top_block
further downsamples the feature map. It must have an attribute
"num_levels", meaning the number of extra FPN levels added by
this block, and "in_feature", which is a string representing
its input feature (e.g., p5).
fuse_type (str): types for fusing the top down features and the lateral
ones. It can be "sum" (default), which sums up element-wise; or "avg",
which takes the element-wise mean of the two.
"""
super(FPN, self).__init__()
assert isinstance(bottom_up, Backbone)
# Feature map strides and channels from the bottom up network (e.g. ResNet)
input_shapes = bottom_up.output_shape()
in_strides = [input_shapes[f].stride for f in in_features]
in_channels = [input_shapes[f].channels for f in in_features]
_assert_strides_are_log2_contiguous(in_strides)
lateral_convs = []
output_convs = []
use_bias = norm == ""
for idx, in_channels in enumerate(in_channels):
lateral_norm = get_norm(norm, out_channels)
output_norm = get_norm(norm, out_channels)
lateral_conv = Conv2d(
in_channels, out_channels, kernel_size=1, bias=use_bias, norm=lateral_norm
)
output_conv = Conv2d(
out_channels,
out_channels,
kernel_size=3,
stride=1,
padding=1,
bias=use_bias,
norm=output_norm,
)
weight_init.c2_xavier_fill(lateral_conv)
weight_init.c2_xavier_fill(output_conv)
stage = int(math.log2(in_strides[idx]))
self.add_module("fpn_lateral{}".format(stage), lateral_conv)
self.add_module("fpn_output{}".format(stage), output_conv)
lateral_convs.append(lateral_conv)
output_convs.append(output_conv)
# Place convs into top-down order (from low to high resolution)
# to make the top-down computation in forward clearer.
self.lateral_convs = lateral_convs[::-1]
self.output_convs = output_convs[::-1]
self.top_block = top_block
self.in_features = in_features
self.bottom_up = bottom_up
# Return feature names are "p<stage>", like ["p2", "p3", ..., "p6"]
self._out_feature_strides = {"p{}".format(int(math.log2(s))): s for s in in_strides}
# top block output feature maps.
if self.top_block is not None:
for s in range(stage, stage + self.top_block.num_levels):
self._out_feature_strides["p{}".format(s + 1)] = 2 ** (s + 1)
self._out_features = list(self._out_feature_strides.keys())
self._out_feature_channels = {k: out_channels for k in self._out_features}
self._size_divisibility = in_strides[-1]
assert fuse_type in {"avg", "sum"}
self._fuse_type = fuse_type