def __init__(self,
img_backbone=None,
pts_backbone=None,
num_classes=None,
prelogits_dim=None,
class_weights=None,
pretrained=None,
contrast_criterion=None,
max_pts=1024,
lambda_contrast=0.1,
train_cfg=None,
test_cfg=None):
super(SegFusionV2, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
self.init_weights(pretrained=pretrained)
self.seg_head = nn.Linear(prelogits_dim, num_classes)
self.class_weights = torch.tensor(class_weights)
if contrast_criterion:
self.contrast_criterion = builder.build_loss(contrast_criterion)
self.max_pts = max_pts
self.lambda_contrast = lambda_contrast
self.g1 = nn.Sequential(nn.Linear(64, 64), nn.ReLU(inplace=True),
nn.Linear(64, 16))
self.g2 = nn.Sequential(nn.Linear(16, 16), nn.ReLU(inplace=True),
nn.Linear(16, 16))
def __init__(
self,
img_backbone=None,
pts_backbone=None,
num_classes=None,
prelogits_dim=None,
class_weights=None,
pretrained=None,
contrast_criterion=None,
max_pts=1024, # max_pts_per_group
groups=1, # number of groups per sample
lambda_contrast=0.1,
img_fcs=(64, 64, 16),
pts_fcs=(16, 16, 16),
train_cfg=None,
test_cfg=None):
super(SegFusionContra, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
self.init_weights(pretrained=pretrained)
self.seg_head = nn.Linear(prelogits_dim, num_classes)
self.class_weights = torch.tensor(class_weights)
if contrast_criterion:
self.contrast_criterion = builder.build_loss(contrast_criterion)
self.max_pts = max_pts
self.groups = groups
self.lambda_contrast = lambda_contrast
self.img_fc = build_mlp(img_fcs)
self.pts_fc = build_mlp(pts_fcs)
def __init__(self,
pts_voxel_layer=None,
pts_voxel_encoder=None,
pts_middle_encoder=None,
img_backbone=None,
img_seg_head=None,
pts_backbone=None,
pts_neck=None,
pts_bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None,
pts_fc=[],
contrast_criterion=None,
max_pts=4096,
lambda_contrast=0.1):
super(FusionContrastV2, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if img_seg_head:
self.img_seg_head = builder.build_head(img_seg_head)
if pts_voxel_layer:
self.pts_voxel_layer = Voxelization(**pts_voxel_layer)
if pts_voxel_encoder:
self.pts_voxel_encoder = builder.build_voxel_encoder(
pts_voxel_encoder)
if pts_middle_encoder:
self.pts_middle_encoder = builder.build_middle_encoder(
pts_middle_encoder)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
if pts_neck:
self.pts_neck = builder.build_neck(pts_neck)
if pts_bbox_head:
pts_train_cfg = train_cfg.pts if train_cfg else None
pts_bbox_head.update(train_cfg=pts_train_cfg)
pts_test_cfg = test_cfg.pts if test_cfg else None
pts_bbox_head.update(test_cfg=pts_test_cfg)
self.pts_bbox_head = builder.build_head(pts_bbox_head)
if contrast_criterion:
self.contrast_criterion = builder.build_loss(contrast_criterion)
self.max_pts = max_pts
self.lambda_contrast = lambda_contrast
fc_layers = []
for i, (in_c, out_c) in enumerate(zip(pts_fc[:-1], pts_fc[1:])):
fc_layers.append(nn.Linear(in_c, out_c))
if i == len(pts_fc) - 2:
break
fc_layers.append(nn.ReLU(inplace=True))
self.fc_layers = nn.Sequential(*fc_layers)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
def __init__(self,
pts_voxel_layer=None,
pts_voxel_encoder=None,
pts_middle_encoder=None,
img_backbone=None,
img_seg_head=None,
pts_backbone=None,
pts_neck=None,
pts_bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None,
pts_fc=[]):
super(FusionBaseline4, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if img_seg_head:
self.img_seg_head = builder.build_head(img_seg_head)
if pts_voxel_layer:
self.pts_voxel_layer = Voxelization(**pts_voxel_layer)
if pts_voxel_encoder:
self.pts_voxel_encoder = builder.build_voxel_encoder(
pts_voxel_encoder)
if pts_middle_encoder:
self.pts_middle_encoder = builder.build_middle_encoder(
pts_middle_encoder)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
if pts_neck is not None:
self.pts_neck = builder.build_neck(pts_neck)
if pts_bbox_head:
pts_train_cfg = train_cfg.pts if train_cfg else None
pts_bbox_head.update(train_cfg=pts_train_cfg)
pts_test_cfg = test_cfg.pts if test_cfg else None
pts_bbox_head.update(test_cfg=pts_test_cfg)
self.pts_bbox_head = builder.build_head(pts_bbox_head)
fc_layers = []
for i, (in_c, out_c) in enumerate(zip(pts_fc[:-1], pts_fc[1:])):
fc_layers.append(nn.Linear(in_c, out_c))
if i == len(pts_fc) - 2:
break
fc_layers.append(nn.ReLU(inplace=True))
self.fc_layers = nn.Sequential(*fc_layers)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
def __init__(self,
pts_voxel_layer=None,
pts_voxel_encoder=None,
pts_middle_encoder=None,
img_backbone=None,
img_seg_head=None,
pts_backbone=None,
pts_neck=None,
pts_bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None,
vfes=[]):
super(FusionBaseline, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if img_seg_head:
self.img_seg_head = builder.build_head(img_seg_head)
if pts_voxel_layer:
self.pts_voxel_layer = Voxelization(**pts_voxel_layer)
if pts_voxel_encoder:
self.pts_voxel_encoder = builder.build_voxel_encoder(
pts_voxel_encoder)
if pts_middle_encoder:
self.pts_middle_encoder = builder.build_middle_encoder(
pts_middle_encoder)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
if pts_neck is not None:
self.pts_neck = builder.build_neck(pts_neck)
if pts_bbox_head:
pts_train_cfg = train_cfg.pts if train_cfg else None
pts_bbox_head.update(train_cfg=pts_train_cfg)
pts_test_cfg = test_cfg.pts if test_cfg else None
pts_bbox_head.update(test_cfg=pts_test_cfg)
self.pts_bbox_head = builder.build_head(pts_bbox_head)
vfe_layers = []
for in_c, out_c in zip(vfes[:-1], vfes[1:]):
vfe_layers.append(VFELayer(in_c, out_c, max_out=False))
self.vfe_layers = nn.Sequential(*vfe_layers)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
def __init__(self,
img_backbone=None,
pts_backbone=None,
num_classes=None,
prelogits_dim=None,
class_weights=None,
pretrained=None,
train_cfg=None,
test_cfg=None):
super(Single2D3D, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
self.init_weights(pretrained=pretrained)
self.seg_head = nn.Linear(prelogits_dim, num_classes)
self.class_weights = torch.tensor(class_weights)
def __init__(self,
pts_voxel_layer=None,
pts_voxel_encoder=None,
pts_middle_encoder=None,
img_backbone=None,
img_seg_head=None,
pts_backbone=None,
pts_neck=None,
pts_bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(MultiTaskSep, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if img_seg_head:
self.img_seg_head = builder.build_head(img_seg_head)
if pts_voxel_layer:
self.pts_voxel_layer = Voxelization(**pts_voxel_layer)
if pts_voxel_encoder:
self.pts_voxel_encoder = builder.build_voxel_encoder(
pts_voxel_encoder)
if pts_middle_encoder:
self.pts_middle_encoder = builder.build_middle_encoder(
pts_middle_encoder)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
if pts_neck is not None:
self.pts_neck = builder.build_neck(pts_neck)
if pts_bbox_head:
pts_train_cfg = train_cfg.pts if train_cfg else None
pts_bbox_head.update(train_cfg=pts_train_cfg)
pts_test_cfg = test_cfg.pts if test_cfg else None
pts_bbox_head.update(test_cfg=pts_test_cfg)
self.pts_bbox_head = builder.build_head(pts_bbox_head)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
def test_centerpoint_fpn():
second_cfg = dict(
type='SECOND',
in_channels=64,
out_channels=[64, 128, 256],
layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
conv_cfg=dict(type='Conv2d', bias=False))
second = build_backbone(second_cfg)
# centerpoint usage of fpn
centerpoint_fpn_cfg = dict(
type='SECONDFPN',
in_channels=[64, 128, 256],
out_channels=[128, 128, 128],
upsample_strides=[0.5, 1, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
upsample_cfg=dict(type='deconv', bias=False),
use_conv_for_no_stride=True)
# original usage of fpn
fpn_cfg = dict(
type='SECONDFPN',
in_channels=[64, 128, 256],
upsample_strides=[1, 2, 4],
out_channels=[128, 128, 128])
second_fpn = build_neck(fpn_cfg)
centerpoint_second_fpn = build_neck(centerpoint_fpn_cfg)
input = torch.rand([4, 64, 512, 512])
sec_output = second(input)
centerpoint_output = centerpoint_second_fpn(sec_output)
second_output = second_fpn(sec_output)
assert centerpoint_output[0].shape == torch.Size([4, 384, 128, 128])
assert second_output[0].shape == torch.Size([4, 384, 256, 256])
