def __init__(self, cfg, in_channels):
super(KeypointRCNNFeatureExtractor, self).__init__()
resolution = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_RESOLUTION
scales = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_SCALES
sampling_ratio = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_SAMPLING_RATIO
pooler = Pooler(
output_size=(resolution, resolution),
scales=scales,
sampling_ratio=sampling_ratio,
)
self.pooler = pooler
input_features = in_channels
layers = cfg.MODEL.ROI_KEYPOINT_HEAD.CONV_LAYERS
next_feature = input_features
self.blocks = []
for layer_idx, layer_features in enumerate(layers, 1):
layer_name = "conv_fcn{}".format(layer_idx)
module = Conv2d(next_feature,
layer_features,
3,
stride=1,
padding=1)
init.kaiming_normal_(module.weight,
mode="fan_out",
nonlinearity="relu")
init.constant_(module.bias, 0)
setattr(self, layer_name, module)
next_feature = layer_features
self.blocks.append(layer_name)
self.out_channels = layer_features
def __init__(self, config, in_channels):
super(ResNet50Conv5ROIFeatureExtractor, self).__init__()
resolution = config.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
scales = config.MODEL.ROI_BOX_HEAD.POOLER_SCALES
sampling_ratio = config.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
pooler = Pooler(
output_size=(resolution, resolution),
scales=scales,
sampling_ratio=sampling_ratio,
)
stage = resnet.StageSpec(index=4, block_count=3, return_features=False)
head = resnet.ResNetHead(
block_module=config.MODEL.RESNETS.TRANS_FUNC,
stages=(stage, ),
num_groups=config.MODEL.RESNETS.NUM_GROUPS,
width_per_group=config.MODEL.RESNETS.WIDTH_PER_GROUP,
stride_in_1x1=config.MODEL.RESNETS.STRIDE_IN_1X1,
stride_init=None,
res2_out_channels=config.MODEL.RESNETS.RES2_OUT_CHANNELS,
dilation=config.MODEL.RESNETS.RES5_DILATION)
self.pooler = pooler
self.head = head
self.out_channels = head.out_channels
def __init__(self, cfg, in_channels):
super(FPNXconv1fcFeatureExtractor, self).__init__()
resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
scales = cfg.MODEL.ROI_BOX_HEAD.POOLER_SCALES
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
pooler = Pooler(
output_size=(resolution, resolution),
scales=scales,
sampling_ratio=sampling_ratio,
)
self.pooler = pooler
use_gn = cfg.MODEL.ROI_BOX_HEAD.USE_GN
conv_head_dim = cfg.MODEL.ROI_BOX_HEAD.CONV_HEAD_DIM
num_stacked_convs = cfg.MODEL.ROI_BOX_HEAD.NUM_STACKED_CONVS
dilation = cfg.MODEL.ROI_BOX_HEAD.DILATION
xconvs = []
for ix in range(num_stacked_convs):
xconvs.append(
nn.Conv(in_channels,
conv_head_dim,
kernel_size=3,
stride=1,
padding=dilation,
dilation=dilation,
bias=False if use_gn else True))
in_channels = conv_head_dim
if use_gn:
xconvs.append(group_norm(in_channels))
xconvs.append(nn.ReLU())
self.xconvs = nn.Sequential(*xconvs)
for modules in [
self.xconvs,
]:
for l in modules.modules():
if isinstance(l, nn.Conv):
init.gauss_(l.weight, std=0.01)
if not use_gn:
init.constant_(l.bias, 0)
input_size = conv_head_dim * resolution**2
representation_size = cfg.MODEL.ROI_BOX_HEAD.MLP_HEAD_DIM
self.fc6 = make_fc(input_size, representation_size, use_gn=False)
self.out_channels = representation_size
def __init__(self, cfg, in_channels):
super(FPN2MLPFeatureExtractor, self).__init__()
resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
scales = cfg.MODEL.ROI_BOX_HEAD.POOLER_SCALES
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
pooler = Pooler(
output_size=(resolution, resolution),
scales=scales,
sampling_ratio=sampling_ratio,
)
input_size = in_channels * resolution**2
representation_size = cfg.MODEL.ROI_BOX_HEAD.MLP_HEAD_DIM
use_gn = cfg.MODEL.ROI_BOX_HEAD.USE_GN
self.pooler = pooler
self.fc6 = make_fc(input_size, representation_size, use_gn)
self.fc7 = make_fc(representation_size, representation_size, use_gn)
self.out_channels = representation_size
def __init__(self, cfg, in_channels):
"""
Arguments:
num_classes (int): number of output classes
input_size (int): number of channels of the input once it's flattened
representation_size (int): size of the intermediate representation
"""
super(MaskRCNNFPNSpatialAttentionFeatureExtractor, self).__init__()
resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION
scales = cfg.MODEL.ROI_MASK_HEAD.POOLER_SCALES
sampling_ratio = cfg.MODEL.ROI_MASK_HEAD.POOLER_SAMPLING_RATIO
lvl_map_func = cfg.MODEL.ROI_MASK_HEAD.LEVEL_MAP_FUNCTION
self.maskiou = cfg.MODEL.MASKIOU_ON
pooler = Pooler(output_size=(resolution, resolution),
scales=scales,
sampling_ratio=sampling_ratio,
lvl_map_func=lvl_map_func)
input_size = in_channels
self.pooler = pooler
use_gn = cfg.MODEL.ROI_MASK_HEAD.USE_GN
layers = cfg.MODEL.ROI_MASK_HEAD.CONV_LAYERS
dilation = cfg.MODEL.ROI_MASK_HEAD.DILATION
#spatial attention module
self.spatialAtt = SpatialAttention()
self.num_pooler = len(scales)
next_feature = input_size
self.blocks = []
for layer_idx, layer_features in enumerate(layers, 1):
layer_name = "mask_fcn{}".format(layer_idx)
module = make_conv3x3(next_feature,
layer_features,
dilation=dilation,
stride=1,
use_gn=use_gn)
setattr(self, layer_name, module)
next_feature = layer_features
self.blocks.append(layer_name)
self.out_channels = layer_features