def __init__(self, cfg, input_shape: ShapeSpec):
"""
The following attributes are parsed from config:
num_conv: the number of conv layers
conv_dim: the dimension of the conv layers
norm: normalization for the conv layers
"""
super(MaskRCNNConvUpsampleHead, self).__init__()
# fmt: off
num_classes = cfg.MODEL.ROI_HEADS.NUM_CLASSES
conv_dims = cfg.MODEL.ROI_MASK_HEAD.CONV_DIM
self.norm = cfg.MODEL.ROI_MASK_HEAD.NORM
num_conv = cfg.MODEL.ROI_MASK_HEAD.NUM_CONV
input_channels = input_shape.channels
cls_agnostic_mask = cfg.MODEL.ROI_MASK_HEAD.CLS_AGNOSTIC_MASK
# fmt: on
self.conv_norm_relus = []
for k in range(num_conv):
conv = Conv2d(
input_channels if k == 0 else conv_dims,
conv_dims,
kernel_size=3,
stride=1,
padding=1,
bias=not self.norm,
norm=get_norm(self.norm, conv_dims),
activation=F.relu,
)
self.add_module("mask_fcn{}".format(k + 1), conv)
self.conv_norm_relus.append(conv)
self.deconv = ConvTranspose2d(
conv_dims if num_conv > 0 else input_channels,
conv_dims,
kernel_size=2,
stride=2,
padding=0,
)
num_mask_classes = 1 if cls_agnostic_mask else num_classes
self.predictor = Conv2d(conv_dims,
num_mask_classes,
kernel_size=1,
stride=1,
padding=0)
for layer in self.conv_norm_relus + [self.deconv]:
weight_init.c2_msra_fill(layer)
# use normal distribution initialization for mask prediction layer
nn.init.normal_(self.predictor.weight, std=0.001)
if self.predictor.bias is not None:
nn.init.constant_(self.predictor.bias, 0)
def __init__(self, cfg, input_shape: Dict[str, ShapeSpec]):
super().__init__()
# fmt: off
self.in_features = cfg.MODEL.SEM_SEG_HEAD.IN_FEATURES
feature_strides = {k: v.stride for k, v in input_shape.items()}
feature_channels = {k: v.channels for k, v in input_shape.items()}
self.ignore_value = cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE
num_classes = cfg.MODEL.SEM_SEG_HEAD.NUM_CLASSES
conv_dims = cfg.MODEL.SEM_SEG_HEAD.CONVS_DIM
self.common_stride = cfg.MODEL.SEM_SEG_HEAD.COMMON_STRIDE
norm = cfg.MODEL.SEM_SEG_HEAD.NORM
self.loss_weight = cfg.MODEL.SEM_SEG_HEAD.LOSS_WEIGHT
# fmt: on
self.scale_heads = []
for in_feature in self.in_features:
head_ops = []
head_length = max(
1,
int(
np.log2(feature_strides[in_feature]) -
np.log2(self.common_stride)))
for k in range(head_length):
norm_module = nn.GroupNorm(32,
conv_dims) if norm == "GN" else None
conv = Conv2d(
feature_channels[in_feature] if k == 0 else conv_dims,
conv_dims,
kernel_size=3,
stride=1,
padding=1,
bias=not norm,
norm=norm_module,
activation=F.relu,
)
weight_init.c2_msra_fill(conv)
head_ops.append(conv)
if feature_strides[in_feature] != self.common_stride:
head_ops.append(
nn.Upsample(scale_factor=2,
mode="bilinear",
align_corners=False))
self.scale_heads.append(nn.Sequential(*head_ops))
self.add_module(in_feature, self.scale_heads[-1])
self.predictor = Conv2d(conv_dims,
num_classes,
kernel_size=1,
stride=1,
padding=0)
weight_init.c2_msra_fill(self.predictor)
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, cfg, input_shape: ShapeSpec):
"""
The following attributes are parsed from config:
conv_dims: an iterable of output channel counts for each conv in the head
e.g. (512, 512, 512) for three convs outputting 512 channels.
num_keypoints: number of keypoint heatmaps to predicts, determines the number of
channels in the final output.
"""
super(KRCNNConvDeconvUpsampleHead, self).__init__()
# fmt: off
# default up_scale to 2 (this can eventually be moved to config)
up_scale = 2
conv_dims = cfg.MODEL.ROI_KEYPOINT_HEAD.CONV_DIMS
num_keypoints = cfg.MODEL.ROI_KEYPOINT_HEAD.NUM_KEYPOINTS
in_channels = input_shape.channels
# fmt: on
self.blocks = []
for idx, layer_channels in enumerate(conv_dims, 1):
module = Conv2d(in_channels,
layer_channels,
3,
stride=1,
padding=1)
self.add_module("conv_fcn{}".format(idx), module)
self.blocks.append(module)
in_channels = layer_channels
deconv_kernel = 4
self.score_lowres = ConvTranspose2d(in_channels,
num_keypoints,
deconv_kernel,
stride=2,
padding=deconv_kernel // 2 - 1)
self.up_scale = up_scale
for name, param in self.named_parameters():
if "bias" in name:
nn.init.constant_(param, 0)
elif "weight" in name:
# Caffe2 implementation uses MSRAFill, which in fact
# corresponds to kaiming_normal_ in PyTorch
nn.init.kaiming_normal_(param,
mode="fan_out",
nonlinearity="relu")
def __init__(self, in_channels=3, out_channels=64, norm="BN"):
"""
Args:
norm (str or callable): a callable that takes the number of
channels and return a `nn.Module`, or a pre-defined string
(one of {"FrozenBN", "BN", "GN"}).
"""
super().__init__()
self.conv1 = Conv2d(
in_channels,
out_channels,
kernel_size=7,
stride=2,
padding=3,
bias=False,
norm=get_norm(norm, out_channels),
)
weight_init.c2_msra_fill(self.conv1)
def __init__(
self,
in_channels,
out_channels,
*,
bottleneck_channels,
stride=1,
num_groups=1,
norm="BN",
stride_in_1x1=False,
dilation=1,
):
"""
Args:
norm (str or callable): a callable that takes the number of
channels and return a `nn.Module`, or a pre-defined string
(one of {"FrozenBN", "BN", "GN"}).
stride_in_1x1 (bool): when stride==2, whether to put stride in the
first 1x1 convolution or the bottleneck 3x3 convolution.
"""
super().__init__(in_channels, out_channels, stride)
if in_channels != out_channels:
self.shortcut = Conv2d(
in_channels,
out_channels,
kernel_size=1,
stride=stride,
bias=False,
norm=get_norm(norm, out_channels),
)
else:
self.shortcut = None
# The original MSRA ResNet models have stride in the first 1x1 conv
# The subsequent fb.torch.resnet and Caffe2 ResNe[X]t implementations have
# stride in the 3x3 conv
stride_1x1, stride_3x3 = (stride, 1) if stride_in_1x1 else (1, stride)
self.conv1 = Conv2d(
in_channels,
bottleneck_channels,
kernel_size=1,
stride=stride_1x1,
bias=False,
norm=get_norm(norm, bottleneck_channels),
)
self.conv2 = Conv2d(
bottleneck_channels,
bottleneck_channels,
kernel_size=3,
stride=stride_3x3,
padding=1 * dilation,
bias=False,
groups=num_groups,
dilation=dilation,
norm=get_norm(norm, bottleneck_channels),
)
self.conv3 = Conv2d(
bottleneck_channels,
out_channels,
kernel_size=1,
bias=False,
norm=get_norm(norm, out_channels),
)
for layer in [self.conv1, self.conv2, self.conv3, self.shortcut]:
if layer is not None: # shortcut can be None
weight_init.c2_msra_fill(layer)
def __init__(
self,
in_channels,
out_channels,
*,
bottleneck_channels,
stride=1,
num_groups=1,
norm="BN",
stride_in_1x1=False,
dilation=1,
deform_modulated=False,
deform_num_groups=1,
):
"""
Similar to :class:`BottleneckBlock`, but with deformable conv in the 3x3 convolution.
"""
super().__init__(in_channels, out_channels, stride)
self.deform_modulated = deform_modulated
if in_channels != out_channels:
self.shortcut = Conv2d(
in_channels,
out_channels,
kernel_size=1,
stride=stride,
bias=False,
norm=get_norm(norm, out_channels),
)
else:
self.shortcut = None
stride_1x1, stride_3x3 = (stride, 1) if stride_in_1x1 else (1, stride)
self.conv1 = Conv2d(
in_channels,
bottleneck_channels,
kernel_size=1,
stride=stride_1x1,
bias=False,
norm=get_norm(norm, bottleneck_channels),
)
if deform_modulated:
deform_conv_op = ModulatedDeformConv
# offset channels are 2 or 3 (if with modulated) * kernel_size * kernel_size
offset_channels = 27
else:
deform_conv_op = DeformConv
offset_channels = 18
self.conv2_offset = Conv2d(
bottleneck_channels,
offset_channels * deform_num_groups,
kernel_size=3,
stride=stride_3x3,
padding=1 * dilation,
dilation=dilation,
)
self.conv2 = deform_conv_op(
bottleneck_channels,
bottleneck_channels,
kernel_size=3,
stride=stride_3x3,
padding=1 * dilation,
bias=False,
groups=num_groups,
dilation=dilation,
deformable_groups=deform_num_groups,
norm=get_norm(norm, bottleneck_channels),
)
self.conv3 = Conv2d(
bottleneck_channels,
out_channels,
kernel_size=1,
bias=False,
norm=get_norm(norm, out_channels),
)
for layer in [self.conv1, self.conv2, self.conv3, self.shortcut]:
if layer is not None: # shortcut can be None
weight_init.c2_msra_fill(layer)
nn.init.constant_(self.conv2_offset.weight, 0)
nn.init.constant_(self.conv2_offset.bias, 0)
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)
in_strides = [bottom_up.out_feature_strides[f] for f in in_features]
in_channels = [bottom_up.out_feature_channels[f] 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