def __init__(self,
voxel_layer,
voxel_encoder,
middle_encoder,
backbone,
neck=None,
bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(VoxelNet, self).__init__(
backbone=backbone,
neck=neck,
bbox_head=bbox_head,
train_cfg=train_cfg,
test_cfg=test_cfg,
pretrained=pretrained,
)
self.voxel_layer = Voxelization(**voxel_layer)
self.voxel_encoder = builder.build_voxel_encoder(voxel_encoder)
self.middle_encoder = builder.build_middle_encoder(middle_encoder)
self.img_encoder = ImgFeatExtractor()
self.refmap_encoder = nn.Sequential(
nn.Conv2d(1, 64, kernel_size=3, padding=1, stride=1),
nn.BatchNorm2d(64), nn.ReLU(),
nn.Conv2d(64, 64, kernel_size=3, padding=1, stride=2),
nn.BatchNorm2d(64), nn.ReLU())
self.ref_to_cls = nn.Sequential(nn.Conv2d(64, 18, kernel_size=1),
nn.BatchNorm2d(18), nn.ReLU())
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,
pts_fusion_layer=None,
img_backbone=None,
pts_backbone=None,
img_neck=None,
pts_neck=None,
pts_bbox_head=None,
img_roi_head=None,
img_rpn_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(MVXTwoStageDetector, self).__init__()
if 'type' in pts_voxel_layer:
self.pts_voxel_cfg = pts_voxel_layer
else:
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_fusion_layer:
self.pts_fusion_layer = builder.build_fusion_layer(
pts_fusion_layer)
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)
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if img_neck is not None:
self.img_neck = builder.build_neck(img_neck)
if img_rpn_head is not None:
self.img_rpn_head = builder.build_head(img_rpn_head)
if img_roi_head is not None:
self.img_roi_head = builder.build_head(img_roi_head)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
def __init__(self,
model_cfg,
num_point_features,
voxel_size,
point_cloud_range,
mode='max',
norm_cfg=dict(type='BN1d', eps=1e-3, momentum=0.01)):
super().__init__(model_cfg=model_cfg)
self.point_cloud_range = point_cloud_range
self.vx = voxel_size[0]
self.vy = voxel_size[1]
self.vz = voxel_size[2]
self.x_offset = self.vx / 2 + point_cloud_range[0]
self.y_offset = self.vy / 2 + point_cloud_range[1]
self.z_offset = self.vz / 2 + point_cloud_range[2]
# self.use_norm = self.model_cfg.USE_NORM
self.with_distance = self.model_cfg.WITH_DISTANCE
self.use_absolute_xyz = self.model_cfg.USE_ABSLOTE_XYZ
num_point_features += 5 if self.use_absolute_xyz else 3
if self.with_distance:
num_point_features += 1
self.num_filters = self.model_cfg.NUM_FILTERS
assert len(self.num_filters) > 0
self.num_filters = [num_point_features] + list(self.num_filters)
pfn_layers = []
# TODO: currently only support one PFNLayer
for i in range(len(self.num_filters) - 1):
in_filters = self.num_filters[i]
out_filters = self.num_filters[i + 1]
if i > 0:
in_filters *= 2
_, norm_layer = build_norm_layer(norm_cfg, out_filters)
pfn_layers.append(
nn.Sequential(nn.Linear(in_filters, out_filters, bias=False),
norm_layer, nn.ReLU(inplace=True)))
self.num_pfn = len(pfn_layers)
self.pfn_layers = nn.ModuleList(pfn_layers)
self.pfn_scatter = DynamicScatter(voxel_size, point_cloud_range,
(mode != 'max'))
self.cluster_scatter = DynamicScatter(voxel_size,
point_cloud_range,
average_points=True)
voxel_layer = dict(max_num_points=-1,
point_cloud_range=point_cloud_range,
voxel_size=voxel_size,
max_voxels=(-1, -1))
self.voxel_layer = Voxelization(**voxel_layer)
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,
pts_voxel_layer=None,
pts_voxel_encoder=None,
pts_middle_encoder=None,
pts_fusion_layer=None,
img_backbone=None,
pts_backbone=None,
pts_neck=None,
pts_bbox_head=None,
img_seg_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(MMDA, self).__init__()
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_fusion_layer:
self.pts_fusion_layer = builder.build_fusion_layer(
pts_fusion_layer)
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)
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)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
def __init__(self,
voxel_layer,
voxel_encoder,
middle_encoder,
backbone,
neck=None,
rpn_head=None,
roi_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(PartA2, self).__init__(
backbone=backbone,
neck=neck,
rpn_head=rpn_head,
roi_head=roi_head,
train_cfg=train_cfg,
test_cfg=test_cfg,
pretrained=pretrained,
)
self.voxel_layer = Voxelization(**voxel_layer)
self.voxel_encoder = builder.build_voxel_encoder(voxel_encoder)
self.middle_encoder = builder.build_middle_encoder(middle_encoder)
# 转换RangeImage部分相关代码
self.H = 48
self.W = 512
self.fov_up = 3
self.fov_down = -15.0
self.pi = torch.tensor(np.pi)
fov_up = self.fov_up * self.pi / 180.0
fov_down = self.fov_down * self.pi / 180.0
fov = abs(fov_up) + abs(fov_down)
self.uv = torch.zeros((2, self.H, self.W))
self.uv[1] = torch.arange(0, self.W)
self.uv.permute((0, 2, 1))[0] = torch.arange(0, self.H)
self.uv[0] = (
(self.H - self.uv[0]) * fov - abs(fov_down) * self.H) / self.H
self.uv[1] = (self.uv[1] * 2.0 - self.W) * self.pi / (
self.W * 4) # 最后一个 4 用来控制水平范围
# self.range_encoder = RangeEncoder(5, 64, use_img=True)
self.fusion = Fusion(5, 3)
def __init__(self,
voxel_layer,
voxel_encoder,
middle_encoder,
backbone,
neck=None,
bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(VoxelNet, self).__init__(
backbone=backbone,
neck=neck,
bbox_head=bbox_head,
train_cfg=train_cfg,
test_cfg=test_cfg,
pretrained=pretrained,
)
self.voxel_layer = Voxelization(**voxel_layer)
self.voxel_encoder = builder.build_voxel_encoder(voxel_encoder)
self.middle_encoder = builder.build_middle_encoder(middle_encoder)
def __init__(self,
voxel_layer,
voxel_encoder,
middle_encoder,
backbone,
neck=None,
rpn_head=None,
roi_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None,
init_cfg=None):
super(PartA2, self).__init__(backbone=backbone,
neck=neck,
rpn_head=rpn_head,
roi_head=roi_head,
train_cfg=train_cfg,
test_cfg=test_cfg,
pretrained=pretrained,
init_cfg=init_cfg)
self.voxel_layer = Voxelization(**voxel_layer)
self.voxel_encoder = builder.build_voxel_encoder(voxel_encoder)
self.middle_encoder = builder.build_middle_encoder(middle_encoder)
def __init__(self,
voxel_layer,
voxel_encoder,
middle_encoder,
backbone,
neck=None,
bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(VoxelNet_RAN, self).__init__(
backbone=backbone,
neck=neck,
bbox_head=bbox_head,
train_cfg=train_cfg,
test_cfg=test_cfg,
pretrained=pretrained,
)
self.voxel_layer = Voxelization(**voxel_layer)
# self.backbone_second = build_backbone(backbone)
# if neck is not None:
# self.neck_secondfpn = build_neck(neck)
self.voxel_encoder = builder.build_voxel_encoder(voxel_encoder)
self.middle_encoder = builder.build_middle_encoder(middle_encoder)
def __init__(self,
pts_voxel_layer=None,
pts_voxel_encoder=None,
pts_middle_encoder=None,
pts_fusion_layer=None,
img_backbone=None,
pts_backbone=None,
img_neck=None,
pts_neck=None,
pts_bbox_head=None,
img_roi_head=None,
img_rpn_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None,
init_cfg=None):
super(MVXTwoStageDetector, self).__init__(init_cfg=init_cfg)
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_fusion_layer:
self.pts_fusion_layer = builder.build_fusion_layer(
pts_fusion_layer)
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)
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if img_neck is not None:
self.img_neck = builder.build_neck(img_neck)
if img_rpn_head is not None:
self.img_rpn_head = builder.build_head(img_rpn_head)
if img_roi_head is not None:
self.img_roi_head = builder.build_head(img_roi_head)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
if pretrained is None:
img_pretrained = None
pts_pretrained = None
elif isinstance(pretrained, dict):
img_pretrained = pretrained.get('img', None)
pts_pretrained = pretrained.get('pts', None)
else:
raise ValueError(
f'pretrained should be a dict, got {type(pretrained)}')
if self.with_img_backbone:
if img_pretrained is not None:
warnings.warn('DeprecationWarning: pretrained is a deprecated \
key, please consider using init_cfg')
self.img_backbone.init_cfg = dict(type='Pretrained',
checkpoint=img_pretrained)
if self.with_img_roi_head:
if img_pretrained is not None:
warnings.warn('DeprecationWarning: pretrained is a deprecated \
key, please consider using init_cfg')
self.img_roi_head.init_cfg = dict(type='Pretrained',
checkpoint=img_pretrained)
if self.with_pts_backbone:
if img_pretrained is not None:
warnings.warn('DeprecationWarning: pretrained is a deprecated \
key, please consider using init_cfg')
self.pts_backbone.init_cfg = dict(type='Pretrained',
checkpoint=pts_pretrained)