def __init__(self, dim_in, spatial_scale, stage=1):
super().__init__()
self.dim_in = dim_in[-1]
method = cfg.FAST_RCNN.ROI_XFORM_METHOD
resolution = cfg.FAST_RCNN.ROI_XFORM_RESOLUTION
sampling_ratio = cfg.FAST_RCNN.ROI_XFORM_SAMPLING_RATIO
pooler = Pooler(
method=method,
output_size=resolution,
scales=spatial_scale,
sampling_ratio=sampling_ratio,
)
self.pooler = pooler
use_lite = cfg.FAST_RCNN.CONVFC_HEAD.USE_LITE
use_bn = cfg.FAST_RCNN.CONVFC_HEAD.USE_BN
use_gn = cfg.FAST_RCNN.CONVFC_HEAD.USE_GN
conv_dim = cfg.FAST_RCNN.CONVFC_HEAD.CONV_DIM
num_stacked_convs = cfg.FAST_RCNN.CONVFC_HEAD.NUM_STACKED_CONVS
dilation = cfg.FAST_RCNN.CONVFC_HEAD.DILATION
xconvs = []
for ix in range(num_stacked_convs):
xconvs.append(
make_conv(self.dim_in,
conv_dim,
kernel=3,
stride=1,
dilation=dilation,
use_dwconv=use_lite,
use_bn=use_bn,
use_gn=use_gn,
suffix_1x1=use_lite,
use_relu=True))
self.dim_in = conv_dim
self.add_module("xconvs", nn.Sequential(*xconvs))
input_size = self.dim_in * resolution[0] * resolution[1]
mlp_dim = cfg.FAST_RCNN.CONVFC_HEAD.MLP_DIM
self.fc6 = make_fc(input_size, mlp_dim, use_bn=False, use_gn=False)
self.dim_out = mlp_dim
self.stage = stage
if cfg.FAST_RCNN.CONVFC_HEAD.USE_WS:
self = convert_conv2convws_model(self)
def __init__(self, dim_in, spatial_scale):
super().__init__()
self.dim_in = dim_in[-1]
method = cfg.GRID_RCNN.ROI_XFORM_METHOD
resolution = cfg.GRID_RCNN.ROI_XFORM_RESOLUTION_CLS
sampling_ratio = cfg.GRID_RCNN.ROI_XFORM_SAMPLING_RATIO
pooler = Pooler(
method=method,
output_size=resolution,
scales=spatial_scale,
sampling_ratio=sampling_ratio,
)
input_size = self.dim_in * resolution[0] * resolution[1]
mlp_dim = cfg.GRID_RCNN.MLP_HEAD.MLP_DIM
use_bn = cfg.GRID_RCNN.MLP_HEAD.USE_BN
use_gn = cfg.GRID_RCNN.MLP_HEAD.USE_GN
self.pooler = pooler
self.fc6 = make_fc(input_size, mlp_dim, use_bn, use_gn)
self.fc7 = make_fc(mlp_dim, mlp_dim, use_bn, use_gn)
self.dim_out = mlp_dim
if cfg.GRID_RCNN.MLP_HEAD.USE_WS:
self = convert_conv2convws_model(self)
def resnet():
model = ResNet(norm=get_norm(), stride=16)
if cfg.BACKBONE.RESNET.USE_WS:
model = convert_conv2convws_model(model)
return model
def resnet_2mlp_head(dim_in, spatial_scale):
model = ResNet_2mlp_Head(dim_in, spatial_scale, norm=get_norm())
if cfg.BACKBONE.RESNET.USE_WS:
model = convert_conv2convws_model(model)
return model
def __init__(self, dim_in, spatial_scale):
super().__init__()
self.dim_in = dim_in[-1] # 2048
self.spatial_scale = spatial_scale
fpn_dim = cfg.FPN.DIM # 256
use_lite = cfg.FPN.USE_LITE
use_bn = cfg.FPN.USE_BN
use_gn = cfg.FPN.USE_GN
min_level, max_level = get_min_max_levels() # 2, 6
self.num_backbone_stages = len(dim_in) - (
min_level - cfg.FPN.LOWEST_BACKBONE_LVL
) # 4 (cfg.FPN.LOWEST_BACKBONE_LVL=2)
# P5 in
self.p5_in = make_conv(self.dim_in,
fpn_dim,
kernel=1,
use_bn=use_bn,
use_gn=use_gn)
# P5 out
self.p5_out = make_conv(fpn_dim,
fpn_dim,
kernel=3,
use_dwconv=use_lite,
use_bn=use_bn,
use_gn=use_gn,
suffix_1x1=use_lite)
# fpn module
self.fpn_in = []
self.fpn_out = []
for i in range(self.num_backbone_stages - 1): # skip the top layer
px_in = make_conv(dim_in[-i - 2],
fpn_dim,
kernel=1,
use_bn=use_bn,
use_gn=use_gn) # from P4 to P2
px_out = make_conv(fpn_dim,
fpn_dim,
kernel=3,
use_dwconv=use_lite,
use_bn=use_bn,
use_gn=use_gn,
suffix_1x1=use_lite)
self.fpn_in.append(px_in)
self.fpn_out.append(px_out)
self.fpn_in = nn.ModuleList(self.fpn_in) # [P4, P3, P2]
self.fpn_out = nn.ModuleList(self.fpn_out)
self.dim_in = fpn_dim
# P6. Original FPN P6 level implementation from CVPR'17 FPN paper.
if not cfg.FPN.EXTRA_CONV_LEVELS and max_level == cfg.FPN.HIGHEST_BACKBONE_LVL + 1:
self.maxpool_p6 = nn.MaxPool2d(kernel_size=1, stride=2, padding=0)
self.spatial_scale.append(self.spatial_scale[-1] * 0.5)
# Coarser FPN levels introduced for RetinaNet
if cfg.FPN.EXTRA_CONV_LEVELS and max_level > cfg.FPN.HIGHEST_BACKBONE_LVL:
self.extra_pyramid_modules = nn.ModuleList()
if cfg.FPN.USE_C5:
self.dim_in = dim_in[-1]
for i in range(cfg.FPN.HIGHEST_BACKBONE_LVL + 1, max_level + 1):
self.extra_pyramid_modules.append(
make_conv(self.dim_in,
fpn_dim,
kernel=3,
stride=2,
use_dwconv=use_lite,
use_bn=use_bn,
use_gn=use_gn,
suffix_1x1=use_lite))
self.dim_in = fpn_dim
self.spatial_scale.append(self.spatial_scale[-1] * 0.5)
# self.spatial_scale.reverse() # [1/64, 1/32, 1/16, 1/8, 1/4]
# self.dim_out = [self.dim_in]
num_roi_levels = cfg.FPN.ROI_MAX_LEVEL - cfg.FPN.ROI_MIN_LEVEL + 1
# Retain only the spatial scales that will be used for RoI heads. `self.spatial_scale`
# may include extra scales that are used for RPN proposals, but not for RoI heads.
self.spatial_scale = self.spatial_scale[:num_roi_levels]
self.dim_out = [self.dim_in for _ in range(num_roi_levels)]
if cfg.FPN.USE_WS:
self = convert_conv2convws_model(self)
self._init_weights()