supporting voxelnext inference

mmdet3d/configs/_base_/models/voxelnext.py

@@ -0,0 +1,73 @@
+voxel_size = [0.1, 0.1, 0.2]
+model = dict(
+ type='VoxelNeXt',
+ data_preprocessor=dict(
+ type='Det3DDataPreprocessor',
+ voxel=True,
+ voxel_layer=dict(
+ max_num_points=10,
+ voxel_size=voxel_size,
+ max_voxels=(90000, 120000))),
+ pts_voxel_encoder=dict(type='HardSimpleVFE', num_features=5),
+ pts_middle_encoder=dict(
+ type='SparseEncoderVOXELNEXT',
+ in_channels=5,
+ sparse_shape=[41, 1024, 1024],
+ output_channels=128,
+ order=('conv', 'norm', 'act'),
+ encoder_channels=((16, 16, 32), (32, 32, 64), (64, 64, 128), (128, 128, 128), (128, 128, 128), (128,
+ 128)),
+ encoder_paddings=((0, 0, 1), (0, 0, 1), (0, 0, 1), (0, 0, 1), (0, 0, [0, 1, 1]), (0, 0)),
+ block_type='basicblock'),
+ pts_bbox_head=dict(
+ type='VoxelNeXtHead',
+ in_channels=sum([64, 64]),
+ tasks=[
+ dict(num_class=1, class_names=['car']),
+ dict(num_class=2, class_names=['truck', 'construction_vehicle']),
+ dict(num_class=2, class_names=['bus', 'trailer']),
+ dict(num_class=1, class_names=['barrier']),
+ dict(num_class=2, class_names=['motorcycle', 'bicycle']),
+ dict(num_class=2, class_names=['pedestrian', 'traffic_cone']),
+ ],
+ common_heads=dict(
+ reg=(2, 2), height=(1, 2), dim=(3, 2), rot=(2, 2), vel=(2, 2)),
+ share_conv_channel=128,
+ bbox_coder=dict(
+ type='VoxelNeXtBBoxCoder',
+ post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
+ max_num=500,
+ score_threshold=0.1,
+ out_size_factor=8,
+ voxel_size=voxel_size[:2],
+ code_size=9),
+ separate_head=dict(
+ type='VoxelNeXt_SeparateHead', init_bias=-2.19, final_kernel=3),
+ loss_cls=dict(type='mmdet.GaussianFocalLoss', reduction='mean'),
+ loss_bbox=dict(
+ type='mmdet.L1Loss', reduction='mean', loss_weight=0.25),
+ norm_bbox=True),
+ # model training and testing settings
+ train_cfg=dict(
+ pts=dict(
+ grid_size=[1024, 1024, 40],
+ voxel_size=voxel_size,
+ out_size_factor=8,
+ dense_reg=1,
+ gaussian_overlap=0.1,
+ max_objs=500,
+ min_radius=2,
+ code_weights=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2])),
+ test_cfg=dict(
+ pts=dict(
+ post_center_limit_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
+ max_per_img=500,
+ max_pool_nms=False,
+ min_radius=[4, 12, 10, 1, 0.85, 0.175],
+ score_threshold=0.1,
+ out_size_factor=8,
+ voxel_size=voxel_size[:2],
+ nms_type='rotate',
+ pre_max_size=1000,
+ post_max_size=83,
+ nms_thr=0.2)))

mmdet3d/configs/voxelnext/voxelnext_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py

@@ -0,0 +1,169 @@
+_base_ = [
+ '../_base_/datasets/nus-3d.py',
+ '../_base_/models/voxelneXt.py',
+ '../_base_/schedules/cyclic-20e.py', '../_base_/default_runtime.py'
+]
+
+# If point cloud range is changed, the models should also change their point
+# cloud range accordingly
+voxel_size = [0.075, 0.075, 0.2]
+point_cloud_range = [-54, -54, -5.0, 54, 54, 3.0]
+# Using calibration info convert the Lidar-coordinate point cloud range to the
+# ego-coordinate point cloud range could bring a little promotion in nuScenes.
+# point_cloud_range = [-54, -54.8, -5.0, 54, 53.2, 3.0]
+# For nuScenes we usually do 10-class detection
+class_names = [
+ 'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
+ 'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
+]
+data_prefix = dict(pts='samples/LIDAR_TOP', img='', sweeps='sweeps/LIDAR_TOP')
+model = dict(
+ data_preprocessor=dict(
+ voxel_layer=dict(
+ voxel_size=voxel_size, point_cloud_range=point_cloud_range)),
+ pts_middle_encoder=dict(sparse_shape=[41, 1440, 1440]),
+ pts_bbox_head=dict(
+ bbox_coder=dict(
+ voxel_size=voxel_size[:2], pc_range=point_cloud_range[:2])),
+ train_cfg=dict(
+ pts=dict(
+ grid_size=[1440, 1440, 40],
+ voxel_size=voxel_size,
+ point_cloud_range=point_cloud_range)),
+ test_cfg=dict(
+ pts=dict(voxel_size=voxel_size[:2], pc_range=point_cloud_range[:2])))
+
+dataset_type = 'NuScenesDataset'
+data_root = 'data/nuscenes/'
+backend_args = None
+
+db_sampler = dict(
+ data_root=data_root,
+ info_path=data_root + 'nuscenes_dbinfos_train.pkl',
+ rate=1.0,
+ prepare=dict(
+ filter_by_difficulty=[-1],
+ filter_by_min_points=dict(
+ car=5,
+ truck=5,
+ bus=5,
+ trailer=5,
+ construction_vehicle=5,
+ traffic_cone=5,
+ barrier=5,
+ motorcycle=5,
+ bicycle=5,
+ pedestrian=5)),
+ classes=class_names,
+ sample_groups=dict(
+ car=2,
+ truck=3,
+ construction_vehicle=7,
+ bus=4,
+ trailer=6,
+ barrier=2,
+ motorcycle=6,
+ bicycle=6,
+ pedestrian=2,
+ traffic_cone=2),
+ points_loader=dict(
+ type='LoadPointsFromFile',
+ coord_type='LIDAR',
+ load_dim=5,
+ use_dim=[0, 1, 2, 3, 4],
+ backend_args=backend_args),
+ backend_args=backend_args)
+
+train_pipeline = [
+ dict(
+ type='LoadPointsFromFile',
+ coord_type='LIDAR',
+ load_dim=5,
+ use_dim=5,
+ backend_args=backend_args),
+ dict(
+ type='LoadPointsFromMultiSweeps',
+ sweeps_num=9,
+ use_dim=[0, 1, 2, 3, 4],
+ pad_empty_sweeps=True,
+ remove_close=True,
+ backend_args=backend_args),
+ dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
+ dict(type='ObjectSample', db_sampler=db_sampler),
+ dict(
+ type='GlobalRotScaleTrans',
+ rot_range=[-0.3925, 0.3925],
+ scale_ratio_range=[0.95, 1.05],
+ translation_std=[0, 0, 0]),
+ dict(
+ type='RandomFlip3D',
+ sync_2d=False,
+ flip_ratio_bev_horizontal=0.5,
+ flip_ratio_bev_vertical=0.5),
+ dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
+ dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
+ dict(type='ObjectNameFilter', classes=class_names),
+ dict(type='PointShuffle'),
+ dict(
+ type='Pack3DDetInputs',
+ keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+test_pipeline = [
+ dict(
+ type='LoadPointsFromFile',
+ coord_type='LIDAR',
+ load_dim=5,
+ use_dim=5,
+ backend_args=backend_args),
+ dict(
+ type='LoadPointsFromMultiSweeps',
+ sweeps_num=9, #
+ use_dim=[0, 1, 2, 3, 4],
+ pad_empty_sweeps=True,
+ remove_close=True,
+ backend_args=backend_args),
+ dict(
+ type='MultiScaleFlipAug3D',
+ img_scale=(1333, 800),
+ pts_scale_ratio=1,
+ flip=False,
+ transforms=[
+ dict(
+ type='GlobalRotScaleTrans',
+ rot_range=[0, 0],
+ scale_ratio_range=[1., 1.],
+ translation_std=[0, 0, 0]),
+ dict(type='RandomFlip3D'),
+ dict(
+ type='PointsRangeFilter', point_cloud_range=point_cloud_range)
+ ]),
+ dict(type='Pack3DDetInputs', keys=['points'])
+]
+
+train_dataloader = dict(
+ _delete_=True,
+ batch_size=4,
+ num_workers=4,
+ persistent_workers=True,
+ sampler=dict(type='DefaultSampler', shuffle=True),
+ dataset=dict(
+ type='CBGSDataset',
+ dataset=dict(
+ type=dataset_type,
+ data_root=data_root,
+ ann_file='nuscenes_infos_train.pkl',
+ pipeline=train_pipeline,
+ metainfo=dict(classes=class_names),
+ test_mode=False,
+ data_prefix=data_prefix,
+ use_valid_flag=True,
+ # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
+ # and box_type_3d='Depth' in sunrgbd and scannet dataset.
+ box_type_3d='LiDAR',
+ backend_args=backend_args)))
+test_dataloader = dict(
+ dataset=dict(pipeline=test_pipeline, metainfo=dict(classes=class_names)))
+val_dataloader = dict(
+ dataset=dict(pipeline=test_pipeline, metainfo=dict(classes=class_names)))
+
+train_cfg = dict(val_interval=20)

mmdet3d/models/dense_heads/__init__.py

@@ -18,11 +18,13 @@
 from .smoke_mono3d_head import SMOKEMono3DHead
 from .ssd_3d_head import SSD3DHead
 from .vote_head import VoteHead
+from .voxelnext_head import VoxelNeXtHead
 
 __all__ = [
  'Anchor3DHead', 'FreeAnchor3DHead', 'PartA2RPNHead', 'VoteHead',
  'SSD3DHead', 'BaseConvBboxHead', 'CenterHead', 'ShapeAwareHead',
  'BaseMono3DDenseHead', 'AnchorFreeMono3DHead', 'FCOSMono3DHead',
  'GroupFree3DHead', 'PointRPNHead', 'SMOKEMono3DHead', 'PGDHead',
- 'MonoFlexHead', 'Base3DDenseHead', 'FCAF3DHead', 'ImVoxelHead'
+ 'MonoFlexHead', 'Base3DDenseHead', 'FCAF3DHead', 'ImVoxelHead',
+ 'VoxelNeXtHead'
 ]