def __init__(self, dim_in, roi_xform_func, spatial_scale):
super().__init__()
self.dim_in = dim_in
self.roi_xform = roi_xform_func
self.spatial_scale = spatial_scale
hidden_dim = cfg.FAST_RCNN.CONV_HEAD_DIM
module_list = []
for i in range(cfg.FAST_RCNN.NUM_STACKED_CONVS - 1):
module_list.extend([
nn.Conv2d(dim_in, hidden_dim, 3, 1, 1, bias=False),
nn.GroupNorm(net_utils.get_group_gn(hidden_dim),
hidden_dim,
eps=cfg.GROUP_NORM.EPSILON),
nn.ReLU(inplace=True)
])
dim_in = hidden_dim
self.convs = nn.Sequential(*module_list)
self.dim_out = fc_dim = cfg.FAST_RCNN.MLP_HEAD_DIM
roi_size = cfg.FAST_RCNN.ROI_XFORM_RESOLUTION
self.fc = nn.Linear(dim_in * roi_size * roi_size, fc_dim)
self.num_levels = cfg.FPN.ROI_MAX_LEVEL - cfg.FPN.ROI_MIN_LEVEL + 1
self.conv1_head = nn.ModuleList()
for i in range(self.num_levels):
self.conv1_head.append(
nn.Sequential(
nn.Conv2d(dim_in, hidden_dim, 3, 1, 1, bias=False),
nn.GroupNorm(net_utils.get_group_gn(hidden_dim),
hidden_dim,
eps=cfg.GROUP_NORM.EPSILON),
nn.ReLU(inplace=True)))
self._init_weights()
def __init__(self, dim_in, roi_xform_func, spatial_scale, num_convs):
super().__init__()
self.dim_in = dim_in
self.roi_xform = roi_xform_func
self.spatial_scale = spatial_scale
self.num_convs = num_convs
dilation = cfg.MRCNN.DILATION
dim_inner = cfg.MRCNN.DIM_REDUCED
self.dim_out = dim_inner
module_list = []
for i in range(num_convs - 1):
module_list.extend([
nn.Conv2d(dim_in, dim_inner, 3, 1, padding=1*dilation, dilation=dilation, bias=False),
nn.GroupNorm(net_utils.get_group_gn(dim_inner), dim_inner, eps=cfg.GROUP_NORM.EPSILON),
nn.ReLU(inplace=True)
])
dim_in = dim_inner
self.conv_fcn = nn.Sequential(*module_list)
self.mask_conv1 = nn.ModuleList()
self.num_levels = cfg.FPN.ROI_MAX_LEVEL - cfg.FPN.ROI_MIN_LEVEL + 1
for i in range(self.num_levels):
self.mask_conv1.append(nn.Sequential(
nn.Conv2d(dim_in, dim_inner, 3, 1, padding=1*dilation, dilation=dilation, bias=False),
nn.GroupNorm(net_utils.get_group_gn(dim_inner), dim_inner, eps=cfg.GROUP_NORM.EPSILON),
nn.ReLU(inplace=True)
))
# upsample layer
self.upconv = nn.ConvTranspose2d(dim_inner, dim_inner, 2, 2, 0)
self.apply(self._init_weights)
def __init__(self, dim_in, roi_xform_func, spatial_scale):
super().__init__()
self.dim_in = dim_in
self.roi_xform = roi_xform_func
self.spatial_scale = spatial_scale
self.dim_out = hidden_dim = cfg.FAST_RCNN.MLP_HEAD_DIM
roi_size = cfg.FAST_RCNN.ROI_XFORM_RESOLUTION
self.num_levels = cfg.FPN.ROI_MAX_LEVEL - cfg.FPN.ROI_MIN_LEVEL + 1
self.fc1 = nn.ModuleList()
for i in range(self.num_levels):
self.fc1.append(
nn.Sequential(
nn.Linear(dim_in * roi_size**2, hidden_dim),
nn.GroupNorm(net_utils.get_group_gn(hidden_dim),
hidden_dim,
eps=cfg.GROUP_NORM.EPSILON),
nn.ReLU(inplace=True)))
self.fc2 = nn.Sequential(
nn.Linear(hidden_dim, hidden_dim),
nn.GroupNorm(net_utils.get_group_gn(hidden_dim),
hidden_dim,
eps=cfg.GROUP_NORM.EPSILON), nn.ReLU(inplace=True))
self._init_weights()
def basic_gn_stem():
return nn.Sequential(OrderedDict([
('conv1', nn.Conv2d(3, 64, 7, stride=2, padding=3, bias=False)),
('gn1', nn.GroupNorm(net_utils.get_group_gn(64), 64,
eps=cfg.GROUP_NORM.EPSILON)),
('relu', nn.ReLU(inplace=True)),
('maxpool', nn.MaxPool2d(kernel_size=3, stride=2, padding=1))]))
def basic_gn_shortcut(inplanes, outplanes, stride):
return nn.Sequential(
nn.Conv2d(inplanes,
outplanes,
kernel_size=1,
stride=stride,
bias=False),
nn.GroupNorm(net_utils.get_group_gn(outplanes), outplanes,
eps=cfg.GROUP_NORM.EPSILON)
)
def __init__(self, dim_in, roi_xform_func, spatial_scale):
super().__init__()
self.dim_in = dim_in
self.roi_xform = roi_xform_func
self.spatial_scale = spatial_scale
self.dim_out = hidden_dim = cfg.FAST_RCNN.MLP_HEAD_DIM
roi_size = cfg.FAST_RCNN.ROI_XFORM_RESOLUTION
self.fc1 = nn.Sequential(
nn.Linear(dim_in * roi_size**2, hidden_dim),
nn.GroupNorm(net_utils.get_group_gn(hidden_dim),
hidden_dim,
eps=cfg.GROUP_NORM.EPSILON))
self.fc2 = nn.Sequential(
nn.Linear(hidden_dim, hidden_dim),
nn.GroupNorm(net_utils.get_group_gn(hidden_dim),
hidden_dim,
eps=cfg.GROUP_NORM.EPSILON))
self._init_weights()
def __init__(self, inplanes, outplanes, innerplanes, stride=1, dilation=1, group=1,
downsample=None, use_nonlocal=False, use_deform=False):
super().__init__()
# In original resnet, stride=2 is on 1x1.
# In fb.torch resnet, stride=2 is on 3x3.
(str1x1, str3x3) = (stride, 1) if cfg.RESNETS.STRIDE_1X1 else (1, stride)
self.stride = stride
self.use_nonlocal = use_nonlocal
self.use_deform = use_deform
self.conv1 = nn.Conv2d(
inplanes, innerplanes, kernel_size=1, stride=str1x1, bias=False)
self.gn1 = nn.GroupNorm(net_utils.get_group_gn(innerplanes), innerplanes,
eps=cfg.GROUP_NORM.EPSILON)
if self.use_deform:
self.conv2_offset = nn.Conv2d(
innerplanes, 72, kernel_size=3, stride=1, padding=1, bias=True)
self.conv2 = DeformConv2d(
innerplanes, innerplanes, kernel_size=3, stride=str3x3,
padding=1 * dilation, dilation=dilation, num_deformable_groups=4)
else:
self.conv2 = nn.Conv2d(
innerplanes, innerplanes, kernel_size=3, stride=str3x3, bias=False,
padding=1 * dilation, dilation=dilation, groups=group)
self.gn2 = nn.GroupNorm(net_utils.get_group_gn(innerplanes), innerplanes,
eps=cfg.GROUP_NORM.EPSILON)
self.conv3 = nn.Conv2d(
innerplanes, outplanes, kernel_size=1, stride=1, bias=False)
self.gn3 = nn.GroupNorm(net_utils.get_group_gn(outplanes), outplanes,
eps=cfg.GROUP_NORM.EPSILON)
self.downsample = downsample
self.relu = nn.ReLU(inplace=True)
if self.use_nonlocal:
self.non_local = nonlocal_helper.SpaceNonLocal(outplanes, outplanes // 2, outplanes)
def __init__(self, dim_in_top, dim_in_lateral):
super().__init__()
self.dim_in_top = dim_in_top
self.dim_in_lateral = dim_in_lateral
self.dim_out = dim_in_top
if cfg.FPN.USE_GN:
self.conv_lateral = nn.Sequential(
nn.Conv2d(dim_in_lateral, self.dim_out, 1, 1, 0, bias=False),
nn.GroupNorm(net_utils.get_group_gn(self.dim_out),
self.dim_out,
eps=cfg.GROUP_NORM.EPSILON))
else:
self.conv_lateral = nn.Conv2d(dim_in_lateral, self.dim_out, 1, 1,
0)
self._init_weights()
def __init__(self,
conv_body_func,
fpn_level_info,
P2only=False,
panet_buttomup=False,
net_type='res'):
super().__init__()
self.fpn_level_info = fpn_level_info
self.P2only = P2only
self.panet_buttomup = panet_buttomup
self.net_type = net_type
self.dim_out = fpn_dim = cfg.FPN.DIM
min_level, max_level = get_min_max_levels()
self.num_backbone_stages = len(
fpn_level_info.blobs) - (min_level - cfg.FPN.LOWEST_BACKBONE_LVL)
fpn_dim_lateral = fpn_level_info.dims
self.spatial_scale = [] # a list of scales for FPN outputs
#
# Step 1: recursively build down starting from the coarsest backbone level
#
# For the coarest backbone level: 1x1 conv only seeds recursion
self.conv_top = nn.Conv2d(fpn_dim_lateral[0], fpn_dim, 1, 1, 0)
if cfg.FPN.USE_GN:
self.conv_top = nn.Sequential(
nn.Conv2d(fpn_dim_lateral[0], fpn_dim, 1, 1, 0, bias=False),
nn.GroupNorm(net_utils.get_group_gn(fpn_dim),
fpn_dim,
eps=cfg.GROUP_NORM.EPSILON))
else:
self.conv_top = nn.Conv2d(fpn_dim_lateral[0], fpn_dim, 1, 1, 0)
self.topdown_lateral_modules = nn.ModuleList()
self.posthoc_modules = nn.ModuleList()
# For other levels add top-down and lateral connections
for i in range(self.num_backbone_stages - 1):
self.topdown_lateral_modules.append(
topdown_lateral_module(fpn_dim, fpn_dim_lateral[i + 1]))
# Post-hoc scale-specific 3x3 convs
for i in range(self.num_backbone_stages):
if cfg.FPN.USE_GN:
self.posthoc_modules.append(
nn.Sequential(
nn.Conv2d(fpn_dim, fpn_dim, 3, 1, 1, bias=False),
nn.GroupNorm(net_utils.get_group_gn(fpn_dim),
fpn_dim,
eps=cfg.GROUP_NORM.EPSILON)))
else:
self.posthoc_modules.append(
nn.Conv2d(fpn_dim, fpn_dim, 3, 1, 1))
self.spatial_scale.append(fpn_level_info.spatial_scales[i])
# add for panet buttom-up path
if self.panet_buttomup:
self.panet_buttomup_conv1_modules = nn.ModuleList()
self.panet_buttomup_conv2_modules = nn.ModuleList()
for i in range(self.num_backbone_stages - 1):
if cfg.FPN.USE_GN:
self.panet_buttomup_conv1_modules.append(
nn.Sequential(
nn.Conv2d(fpn_dim, fpn_dim, 3, 2, 1, bias=False),
nn.GroupNorm(net_utils.get_group_gn(fpn_dim),
fpn_dim,
eps=cfg.GROUP_NORM.EPSILON),
nn.ReLU(inplace=True)))
self.panet_buttomup_conv2_modules.append(
nn.Sequential(
nn.Conv2d(fpn_dim, fpn_dim, 3, 1, 1, bias=False),
nn.GroupNorm(net_utils.get_group_gn(fpn_dim),
fpn_dim,
eps=cfg.GROUP_NORM.EPSILON),
nn.ReLU(inplace=True)))
else:
self.panet_buttomup_conv1_modules.append(
nn.Conv2d(fpn_dim, fpn_dim, 3, 2, 1))
self.panet_buttomup_conv2_modules.append(
nn.Conv2d(fpn_dim, fpn_dim, 3, 1, 1))
#
# Step 2: build up starting from the coarsest backbone level
#
# Check if we need the P6 feature map
if not cfg.FPN.EXTRA_CONV_LEVELS and max_level == cfg.FPN.HIGHEST_BACKBONE_LVL + 1:
# Original FPN P6 level implementation from our CVPR'17 FPN paper
# Use max pooling to simulate stride 2 subsampling
self.maxpool_p6 = nn.MaxPool2d(kernel_size=1, stride=2, padding=0)
self.spatial_scale.insert(0, self.spatial_scale[0] * 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()
dim_in = fpn_level_info.dims[0]
for i in range(cfg.FPN.HIGHEST_BACKBONE_LVL + 1, max_level + 1):
self.extra_pyramid_modules.append(
nn.Conv2d(dim_in, fpn_dim, 3, 2, 1))
dim_in = fpn_dim
self.spatial_scale.insert(0, self.spatial_scale[0] * 0.5)
if self.P2only:
# use only the finest level
self.spatial_scale = self.spatial_scale[-1]
self._init_weights()
# Deliberately add conv_body after _init_weights.
# conv_body has its own _init_weights function
self.conv_body = conv_body_func() # e.g resnet