将子模块转换为普通目录

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d.py

+_base_ = [
+    '../_base_/models/hv_pointpillars_fpn_lyft.py',
+    '../_base_/datasets/lyft-3d.py',
+    '../_base_/schedules/schedule_2x.py',
+    '../_base_/default_runtime.py',
+]
+# model settings
+model = dict(
+    type='MVXFasterRCNN',
+    pts_backbone=dict(
+        _delete_=True,
+        type='NoStemRegNet',
+        arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0),
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'),
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        strides=(1, 2, 2, 2),
+        base_channels=64,
+        stem_channels=64,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        norm_eval=False,
+        style='pytorch'),
+    pts_neck=dict(in_channels=[64, 160, 384]))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py

+_base_ = [
+    '../_base_/models/hv_pointpillars_fpn_nus.py',
+    '../_base_/datasets/nus-3d.py',
+    '../_base_/schedules/schedule_2x.py',
+    '../_base_/default_runtime.py',
+]
+# model settings
+model = dict(
+    type='MVXFasterRCNN',
+    pts_backbone=dict(
+        _delete_=True,
+        type='NoStemRegNet',
+        arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0),
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'),
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        strides=(1, 2, 2, 2),
+        base_channels=64,
+        stem_channels=64,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        norm_eval=False,
+        style='pytorch'),
+    pts_neck=dict(in_channels=[64, 160, 384]))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_fp16_2x8_2x_nus-3d.py

+_base_ = './hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py'
+data = dict(samples_per_gpu=2, workers_per_gpu=2)
+# fp16 settings, the loss scale is specifically tuned to avoid Nan
+fp16 = dict(loss_scale=32.)

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_range100_2x8_2x_lyft-3d.py

+_base_ = [
+    '../_base_/models/hv_pointpillars_fpn_range100_lyft.py',
+    '../_base_/datasets/range100_lyft-3d.py',
+    '../_base_/schedules/schedule_2x.py',
+    '../_base_/default_runtime.py',
+]
+# model settings
+model = dict(
+    type='MVXFasterRCNN',
+    pts_backbone=dict(
+        _delete_=True,
+        type='NoStemRegNet',
+        arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0),
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'),
+        out_indices=(1, 2, 3),
+        frozen_stages=-1,
+        strides=(1, 2, 2, 2),
+        base_channels=64,
+        stem_channels=64,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        norm_eval=False,
+        style='pytorch'),
+    pts_neck=dict(in_channels=[64, 160, 384]))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d.py

+_base_ = './hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d.py'
+# model settings
+model = dict(
+    pts_neck=dict(
+        type='SECONDFPN',
+        _delete_=True,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        in_channels=[64, 160, 384],
+        upsample_strides=[1, 2, 4],
+        out_channels=[128, 128, 128]),
+    pts_bbox_head=dict(
+        type='Anchor3DHead',
+        in_channels=384,
+        feat_channels=384,
+        anchor_generator=dict(
+            _delete_=True,
+            type='AlignedAnchor3DRangeGenerator',
+            ranges=[[-80, -80, -1.0715024, 80, 80, -1.0715024],
+                    [-80, -80, -0.3033737, 80, 80, -0.3033737],
+                    [-80, -80, -0.3519405, 80, 80, -0.3519405],
+                    [-80, -80, -0.8871424, 80, 80, -0.8871424],
+                    [-80, -80, -0.6276341, 80, 80, -0.6276341],
+                    [-80, -80, -1.3220503, 80, 80, -1.3220503],
+                    [-80, -80, -1.0709302, 80, 80, -1.0709302],
+                    [-80, -80, -0.9122268, 80, 80, -0.9122268],
+                    [-80, -80, -1.8012227, 80, 80, -1.8012227]],
+            sizes=[
+                [4.75, 1.92, 1.71],  # car
+                [10.24, 2.84, 3.44],  # truck
+                [12.70, 2.92, 3.42],  # bus
+                [6.52, 2.42, 2.34],  # emergency vehicle
+                [8.17, 2.75, 3.20],  # other vehicle
+                [2.35, 0.96, 1.59],  # motorcycle
+                [1.76, 0.63, 1.44],  # bicycle
+                [0.80, 0.76, 1.76],  # pedestrian
+                [0.73, 0.35, 0.50]  # animal
+            ],
+            rotations=[0, 1.57],
+            reshape_out=True)))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py

+_base_ = './hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py'
+# model settings
+model = dict(
+    pts_neck=dict(
+        type='SECONDFPN',
+        _delete_=True,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        in_channels=[64, 160, 384],
+        upsample_strides=[1, 2, 4],
+        out_channels=[128, 128, 128]),
+    pts_bbox_head=dict(
+        type='Anchor3DHead',
+        in_channels=384,
+        feat_channels=384,
+        anchor_generator=dict(
+            _delete_=True,
+            type='AlignedAnchor3DRangeGenerator',
+            ranges=[
+                [-49.6, -49.6, -1.80032795, 49.6, 49.6, -1.80032795],
+                [-49.6, -49.6, -1.74440365, 49.6, 49.6, -1.74440365],
+                [-49.6, -49.6, -1.68526504, 49.6, 49.6, -1.68526504],
+                [-49.6, -49.6, -1.67339111, 49.6, 49.6, -1.67339111],
+                [-49.6, -49.6, -1.61785072, 49.6, 49.6, -1.61785072],
+                [-49.6, -49.6, -1.80984986, 49.6, 49.6, -1.80984986],
+                [-49.6, -49.6, -1.763965, 49.6, 49.6, -1.763965],
+            ],
+            sizes=[
+                [4.60718145, 1.95017717, 1.72270761],  # car
+                [6.73778078, 2.4560939, 2.73004906],  # truck
+                [12.01320693, 2.87427237, 3.81509561],  # trailer
+                [1.68452161, 0.60058911, 1.27192197],  # bicycle
+                [0.7256437, 0.66344886, 1.75748069],  # pedestrian
+                [0.40359262, 0.39694519, 1.06232151],  # traffic_cone
+                [0.48578221, 2.49008838, 0.98297065],  # barrier
+            ],
+            custom_values=[0, 0],
+            rotations=[0, 1.57],
+            reshape_out=True)))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_range100_2x8_2x_lyft-3d.py

+_base_ = \
+    './hv_pointpillars_regnet-400mf_fpn_sbn-all_range100_2x8_2x_lyft-3d.py'
+# model settings
+model = dict(
+    pts_neck=dict(
+        type='SECONDFPN',
+        _delete_=True,
+        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
+        in_channels=[64, 160, 384],
+        upsample_strides=[1, 2, 4],
+        out_channels=[128, 128, 128]),
+    pts_bbox_head=dict(
+        type='Anchor3DHead',
+        in_channels=384,
+        feat_channels=384,
+        anchor_generator=dict(
+            _delete_=True,
+            type='AlignedAnchor3DRangeGenerator',
+            ranges=[[-100, -100, -1.0715024, 100, 100, -1.0715024],
+                    [-100, -100, -0.3033737, 100, 100, -0.3033737],
+                    [-100, -100, -0.3519405, 100, 100, -0.3519405],
+                    [-100, -100, -0.8871424, 100, 100, -0.8871424],
+                    [-100, -100, -0.6276341, 100, 100, -0.6276341],
+                    [-100, -100, -1.3220503, 100, 100, -1.3220503],
+                    [-100, -100, -1.0709302, 100, 100, -1.0709302],
+                    [-100, -100, -0.9122268, 100, 100, -0.9122268],
+                    [-100, -100, -1.8012227, 100, 100, -1.8012227]],
+            sizes=[
+                [4.75, 1.92, 1.71],  # car
+                [10.24, 2.84, 3.44],  # truck
+                [12.70, 2.92, 3.42],  # bus
+                [6.52, 2.42, 2.34],  # emergency vehicle
+                [8.17, 2.75, 3.20],  # other vehicle
+                [2.35, 0.96, 1.59],  # motorcycle
+                [1.76, 0.63, 1.44],  # bicycle
+                [0.80, 0.76, 1.76],  # pedestrian
+                [0.73, 0.35, 0.50]  # animal
+            ],
+            rotations=[0, 1.57],
+            reshape_out=True)))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/regnet/metafile.yml

+Models:
+  - Name: hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d
+    In Collection: PointPillars
+    Config: configs/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py
+    Metadata:
+      Training Data: nuScenes
+      Training Memory (GB): 16.4
+      Architecture:
+        - RegNetX
+        - Hard Voxelization
+    Results:
+      - Task: 3D Object Detection
+        Dataset: nuScenes
+        Metrics:
+          mAP: 41.2
+          NDS: 55.2
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230334-53044f32.pth
+
+  - Name: hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d
+    In Collection: PointPillars
+    Config: configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py
+    Metadata:
+      Training Data: nuScenes
+      Training Memory (GB): 17.3
+      Architecture:
+        - RegNetX
+        - Hard Voxelization
+    Results:
+      - Task: 3D Object Detection
+        Dataset: nuScenes
+        Metrics:
+          mAP: 44.8
+          NDS: 56.4
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d_20200620_230239-c694dce7.pth
+
+  - Name: hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d
+    In Collection: PointPillars
+    Config: configs/regnet/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d.py
+    Metadata:
+      Training Data: nuScenes
+      Training Memory (GB): 24.0
+      Architecture:
+        - RegNetX
+        - Hard Voxelization
+    Results:
+      - Task: 3D Object Detection
+        Dataset: nuScenes
+        Metrics:
+          mAP: 48.2
+          NDS: 59.3
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d_20200629_050311-dcd4e090.pth
+
+  - Name: hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d
+    In Collection: PointPillars
+    Config: configs/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d.py
+    Metadata:
+      Training Data: Lyft
+      Training Memory (GB): 15.9
+      Architecture:
+        - RegNetX
+        - Hard Voxelization
+    Results:
+      - Task: 3D Object Detection
+        Dataset: Lyft
+        Metrics:
+          Private Score: 14.9
+          Public Score: 15.1
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d_20210524_092151-42513826.pth
+
+  - Name: hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d
+    In Collection: PointPillars
+    Config: configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d.py
+    Metadata:
+      Training Data: Lyft
+      Training Memory (GB): 13.0
+      Architecture:
+        - RegNetX
+        - Hard Voxelization
+    Results:
+      - Task: 3D Object Detection
+        Dataset: Lyft
+        Metrics:
+          Private Score: 16.0
+          Public Score: 16.1
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d_20210521_115618-823dcf18.pth

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/sassd/README.md

+# Structure Aware Single-stage 3D Object Detection from Point Cloud
+
+> [Structure Aware Single-stage 3D Object Detection from Point Cloud]([https://arxiv.org/abs/2104.02323](https://openaccess.thecvf.com/content_CVPR_2020/papers/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.pdf))
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+3D object detection from point cloud data plays an essential role in autonomous driving. Current single-stage detectors are efficient by progressively downscaling the 3D point clouds in a fully convolutional manner. However, the downscaled features inevitably lose spatial information and cannot make full use of the structure information of 3D point cloud, degrading their localization precision. In this work, we propose to improve the localization precision of single-stage detectors by explicitly leveraging the structure information of 3D point cloud. Specifically, we design an auxiliary network which converts the convolutional features in the backbone network back to point-level representations. The auxiliary network is jointly optimized, by two point-level supervisions, to guide the convolutional features in the backbone network to be aware of the object structure. The auxiliary network can be detached after training and therefore introduces no extra computation in the inference stage. Besides, considering that single-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient part-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed detector ranks at the top of KITTI 3D/BEV detection leaderboards and runs at 25 FPS for inference.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/30491025/172526367-c8b9bdf7-f901-4f2f-8855-bfd55c39f8d1.png" width="800"/>
+</div>
+
+## Introduction
+
+We implement SA-SSD and provide the results and checkpoints on KITTI dataset.
+
+## Citation
+
+```latex
+@InProceedings{he2020sassd,
+    title={Structure Aware Single-stage 3D Object Detection from Point Cloud},
+    author={He, Chenhang and Zeng, Hui and Huang, Jianqiang and Hua, Xian-Sheng and Zhang, Lei},
+    booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
+    year={2020}
+}
+```

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/sassd/sassd_6x8_80e_kitti-3d-3class.py

+_base_ = [
+    '../_base_/datasets/kitti-3d-3class.py',
+    '../_base_/schedules/cyclic_40e.py', '../_base_/default_runtime.py'
+]
+
+voxel_size = [0.05, 0.05, 0.1]
+
+model = dict(
+    type='SASSD',
+    voxel_layer=dict(
+        max_num_points=5,
+        point_cloud_range=[0, -40, -3, 70.4, 40, 1],
+        voxel_size=voxel_size,
+        max_voxels=(16000, 40000)),
+    voxel_encoder=dict(type='HardSimpleVFE'),
+    middle_encoder=dict(
+        type='SparseEncoderSASSD',
+        in_channels=4,
+        sparse_shape=[41, 1600, 1408],
+        order=('conv', 'norm', 'act')),
+    backbone=dict(
+        type='SECOND',
+        in_channels=256,
+        layer_nums=[5, 5],
+        layer_strides=[1, 2],
+        out_channels=[128, 256]),
+    neck=dict(
+        type='SECONDFPN',
+        in_channels=[128, 256],
+        upsample_strides=[1, 2],
+        out_channels=[256, 256]),
+    bbox_head=dict(
+        type='Anchor3DHead',
+        num_classes=3,
+        in_channels=512,
+        feat_channels=512,
+        use_direction_classifier=True,
+        anchor_generator=dict(
+            type='Anchor3DRangeGenerator',
+            ranges=[
+                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
+                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
+                [0, -40.0, -1.78, 70.4, 40.0, -1.78],
+            ],
+            sizes=[[0.6, 0.8, 1.73], [0.6, 1.76, 1.73], [1.6, 3.9, 1.56]],
+            rotations=[0, 1.57],
+            reshape_out=False),
+        diff_rad_by_sin=True,
+        bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
+        loss_dir=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)),
+    # model training and testing settings
+    train_cfg=dict(
+        assigner=[
+            dict(  # for Pedestrian
+                type='MaxIoUAssigner',
+                iou_calculator=dict(type='BboxOverlapsNearest3D'),
+                pos_iou_thr=0.35,
+                neg_iou_thr=0.2,
+                min_pos_iou=0.2,
+                ignore_iof_thr=-1),
+            dict(  # for Cyclist
+                type='MaxIoUAssigner',
+                iou_calculator=dict(type='BboxOverlapsNearest3D'),
+                pos_iou_thr=0.35,
+                neg_iou_thr=0.2,
+                min_pos_iou=0.2,
+                ignore_iof_thr=-1),
+            dict(  # for Car
+                type='MaxIoUAssigner',
+                iou_calculator=dict(type='BboxOverlapsNearest3D'),
+                pos_iou_thr=0.6,
+                neg_iou_thr=0.45,
+                min_pos_iou=0.45,
+                ignore_iof_thr=-1),
+        ],
+        allowed_border=0,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        use_rotate_nms=True,
+        nms_across_levels=False,
+        nms_thr=0.01,
+        score_thr=0.1,
+        min_bbox_size=0,
+        nms_pre=100,
+        max_num=50))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/second/README.md

+# Second: Sparsely embedded convolutional detection
+
+> [SECOND: Sparsely Embedded Convolutional Detection](https://www.mdpi.com/1424-8220/18/10/3337)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+LiDAR-based or RGB-D-based object detection is used in numerous applications, ranging from autonomous driving to robot vision. Voxel-based 3D convolutional networks have been used for some time to enhance the retention of information when processing point cloud LiDAR data. However, problems remain, including a slow inference speed and low orientation estimation performance. We therefore investigate an improved sparse convolution method for such networks, which significantly increases the speed of both training and inference. We also introduce a new form of angle loss regression to improve the orientation estimation performance and a new data augmentation approach that can enhance the convergence speed and performance. The proposed network produces state-of-the-art results on the KITTI 3D object detection benchmarks while maintaining a fast inference speed.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/79644370/143889364-10be11c3-838e-4fc9-9613-184f0cd08907.png" width="800"/>
+</div>
+
+## Introduction
+
+We implement SECOND and provide the results and checkpoints on KITTI dataset.
+
+## Results and models
+
+### KITTI
+
+|                              Backbone                               |  Class  |  Lr schd   | Mem (GB) | Inf time (fps) |  mAP  |                                                                                                                                                                                             Download                                                                                                                                                                                             |
+| :-----------------------------------------------------------------: | :-----: | :--------: | :------: | :------------: | :---: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|        [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-car.py)         |   Car   | cyclic 80e |   5.4    |                | 79.07 |               [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-car/hv_second_secfpn_6x8_80e_kitti-3d-car_20200620_230238-393f000c.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-car/hv_second_secfpn_6x8_80e_kitti-3d-car_20200620_230238.log.json)               |
+|  [SECFPN (FP16)](./hv_second_secfpn_fp16_6x8_80e_kitti-3d-car.py)   |   Car   | cyclic 80e |   2.9    |                | 78.72 |       [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car_20200924_211301-1f5ad833.pth)\| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car_20200924_211301.log.json)        |
+|       [SECFPN](./hv_second_secfpn_6x8_80e_kitti-3d-3class.py)       | 3 Class | cyclic 80e |   5.4    |                | 65.74 |         [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-3class/hv_second_secfpn_6x8_80e_kitti-3d-3class_20210831_022017-ae782e87.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-3class/hv_second_secfpn_6x8_80e_kitti-3d-3class_20210831_022017log.json)          |
+| [SECFPN (FP16)](./hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class.py) | 3 Class | cyclic 80e |   2.9    |                | 67.4  | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class_20200925_110059-05f67bdf.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class_20200925_110059.log.json) |
+
+### Waymo
+
+|                           Backbone                            | Load Interval |  Class  | Lr schd | Mem (GB) | Inf time (fps) | mAP@L1 | mAPH@L1 | mAP@L2 | **mAPH@L2** |                                                                                           Download                                                                                            |
+| :-----------------------------------------------------------: | :-----------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :----: | :---------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [SECFPN](./hv_second_secfpn_sbn_2x16_2x_waymoD5-3d-3class.py) |       5       | 3 Class |   2x    |   8.12   |                |  65.3  |  61.7   |  58.9  |    55.7     | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_sbn_4x8_2x_waymoD5-3d-3class/hv_second_secfpn_sbn_4x8_2x_waymoD5-3d-3class_20201115_112448.log.json) |
+|                          above @ Car                          |               |         |   2x    |   8.12   |                |  67.1  |  66.6   |  58.7  |    58.2     |                                                                                                                                                                                               |
+|                      above @ Pedestrian                       |               |         |   2x    |   8.12   |                |  68.1  |  59.1   |  59.5  |    51.5     |                                                                                                                                                                                               |
+|                        above @ Cyclist                        |               |         |   2x    |   8.12   |                |  60.7  |  59.5   |  58.4  |    57.3     |                                                                                                                                                                                               |
+
+Note:
+
+- See more details about metrics and data split on Waymo [HERE](https://github.com/open-mmlab/mmdetection3d/tree/master/configs/pointpillars). For implementation details, we basically follow the original settings. All of these results are achieved without bells-and-whistles, e.g. ensemble, multi-scale training and test augmentation.
+- `FP16` means Mixed Precision (FP16) is adopted in training.
+
+## Citation
+
+```latex
+@article{yan2018second,
+  title={Second: Sparsely embedded convolutional detection},
+  author={Yan, Yan and Mao, Yuxing and Li, Bo},
+  journal={Sensors},
+  year={2018},
+  publisher={Multidisciplinary Digital Publishing Institute}
+}
+```

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py

+_base_ = [
+    '../_base_/models/hv_second_secfpn_kitti.py',
+    '../_base_/datasets/kitti-3d-3class.py',
+    '../_base_/schedules/cyclic_40e.py', '../_base_/default_runtime.py'
+]

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/second/hv_second_secfpn_6x8_80e_kitti-3d-car.py

+_base_ = [
+    '../_base_/models/hv_second_secfpn_kitti.py',
+    '../_base_/datasets/kitti-3d-car.py', '../_base_/schedules/cyclic_40e.py',
+    '../_base_/default_runtime.py'
+]
+point_cloud_range = [0, -40, -3, 70.4, 40, 1]
+model = dict(
+    bbox_head=dict(
+        type='Anchor3DHead',
+        num_classes=1,
+        anchor_generator=dict(
+            _delete_=True,
+            type='Anchor3DRangeGenerator',
+            ranges=[[0, -40.0, -1.78, 70.4, 40.0, -1.78]],
+            sizes=[[3.9, 1.6, 1.56]],
+            rotations=[0, 1.57],
+            reshape_out=True)),
+    # model training and testing settings
+    train_cfg=dict(
+        _delete_=True,
+        assigner=dict(
+            type='MaxIoUAssigner',
+            iou_calculator=dict(type='BboxOverlapsNearest3D'),
+            pos_iou_thr=0.6,
+            neg_iou_thr=0.45,
+            min_pos_iou=0.45,
+            ignore_iof_thr=-1),
+        allowed_border=0,
+        pos_weight=-1,
+        debug=False))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/second/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class.py

+_base_ = './hv_second_secfpn_6x8_80e_kitti-3d-3class.py'
+# fp16 settings
+fp16 = dict(loss_scale=512.)

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/second/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car.py

+_base_ = './hv_second_secfpn_6x8_80e_kitti-3d-car.py'
+# fp16 settings
+fp16 = dict(loss_scale=512.)

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/second/hv_second_secfpn_sbn_2x16_2x_waymoD5-3d-3class.py

+_base_ = [
+    '../_base_/models/hv_second_secfpn_waymo.py',
+    '../_base_/datasets/waymoD5-3d-3class.py',
+    '../_base_/schedules/schedule_2x.py',
+    '../_base_/default_runtime.py',
+]
+
+dataset_type = 'WaymoDataset'
+data_root = 'data/waymo/kitti_format/'
+class_names = ['Car', 'Pedestrian', 'Cyclist']
+point_cloud_range = [-76.8, -51.2, -2, 76.8, 51.2, 4]
+input_modality = dict(use_lidar=True, use_camera=False)
+
+db_sampler = dict(
+    data_root=data_root,
+    info_path=data_root + 'waymo_dbinfos_train.pkl',
+    rate=1.0,
+    prepare=dict(
+        filter_by_difficulty=[-1],
+        filter_by_min_points=dict(Car=5, Pedestrian=5, Cyclist=5)),
+    classes=class_names,
+    sample_groups=dict(Car=15, Pedestrian=10, Cyclist=10),
+    points_loader=dict(
+        type='LoadPointsFromFile',
+        coord_type='LIDAR',
+        load_dim=6,
+        use_dim=[0, 1, 2, 3, 4]))
+
+train_pipeline = [
+    dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=6, use_dim=5),
+    dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
+    dict(type='ObjectSample', db_sampler=db_sampler),
+    dict(
+        type='RandomFlip3D',
+        sync_2d=False,
+        flip_ratio_bev_horizontal=0.5,
+        flip_ratio_bev_vertical=0.5),
+    dict(
+        type='GlobalRotScaleTrans',
+        rot_range=[-0.78539816, 0.78539816],
+        scale_ratio_range=[0.95, 1.05]),
+    dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='PointShuffle'),
+    dict(type='DefaultFormatBundle3D', class_names=class_names),
+    dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+
+test_pipeline = [
+    dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=6, use_dim=5),
+    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='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='Collect3D', keys=['points'])
+        ])
+]
+
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(
+        type='RepeatDataset',
+        times=2,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file=data_root + 'waymo_infos_train.pkl',
+            split='training',
+            pipeline=train_pipeline,
+            modality=input_modality,
+            classes=class_names,
+            test_mode=False,
+            # 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',
+            # load one frame every five frames
+            load_interval=5)),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'waymo_infos_val.pkl',
+        split='training',
+        pipeline=test_pipeline,
+        modality=input_modality,
+        classes=class_names,
+        test_mode=True,
+        box_type_3d='LiDAR'),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'waymo_infos_val.pkl',
+        split='training',
+        pipeline=test_pipeline,
+        modality=input_modality,
+        classes=class_names,
+        test_mode=True,
+        box_type_3d='LiDAR'))

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/second/metafile.yml

+Collections:
+  - Name: SECOND
+    Metadata:
+      Training Techniques:
+        - AdamW
+      Architecture:
+        - Hard Voxelization
+    Paper:
+      URL: https://www.mdpi.com/1424-8220/18/10/3337
+      Title: 'SECOND: Sparsely Embedded Convolutional Detection'
+    README: configs/second/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/backbones/second.py#L11
+      Version: v0.5.0
+
+Models:
+  - Name: hv_second_secfpn_6x8_80e_kitti-3d-car
+    In Collection: SECOND
+    Config: configs/second/hv_second_secfpn_6x8_80e_kitti-3d-car.py
+    Metadata:
+      Training Data: KITTI
+      Training Memory (GB): 5.4
+      Training Resources: 8x V100 GPUs
+    Results:
+      - Task: 3D Object Detection
+        Dataset: KITTI
+        Metrics:
+          mAP: 79.07
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-car/hv_second_secfpn_6x8_80e_kitti-3d-car_20200620_230238-393f000c.pth
+
+  - Name: hv_second_secfpn_6x8_80e_kitti-3d-3class
+    In Collection: SECOND
+    Config: configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py
+    Metadata:
+      Training Data: KITTI
+      Training Memory (GB): 5.4
+      Training Resources: 8x V100 GPUs
+    Results:
+      - Task: 3D Object Detection
+        Dataset: KITTI
+        Metrics:
+          mAP: 65.74
+    Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/second/hv_second_secfpn_6x8_80e_kitti-3d-3class/hv_second_secfpn_6x8_80e_kitti-3d-3class_20210831_022017-ae782e87.pth
+
+  - Name: hv_second_secfpn_fp16_6x8_80e_kitti-3d-car
+    In Collection: SECOND
+    Config: configs/second/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car.py
+    Metadata:
+      Training Techniques:
+        - AdamW
+        - Mixed Precision Training
+      Training Resources: 8x TITAN Xp
+      Training Data: KITTI
+      Training Memory (GB): 2.9
+    Results:
+      - Task: 3D Object Detection
+        Dataset: KITTI
+        Metrics:
+          mAP: 78.72
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car/hv_second_secfpn_fp16_6x8_80e_kitti-3d-car_20200924_211301-1f5ad833.pth
+    Code:
+      Version: v0.7.0
+
+  - Name: hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class
+    In Collection: SECOND
+    Config: configs/second/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class.py
+    Metadata:
+      Training Techniques:
+        - AdamW
+        - Mixed Precision Training
+      Training Resources: 8x TITAN Xp
+      Training Data: KITTI
+      Training Memory (GB): 2.9
+    Results:
+      - Task: 3D Object Detection
+        Dataset: KITTI
+        Metrics:
+          mAP: 67.4
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class/hv_second_secfpn_fp16_6x8_80e_kitti-3d-3class_20200925_110059-05f67bdf.pth
+    Code:
+      Version: v0.7.0

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/smoke/README.md

+# SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
+
+> [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://arxiv.org/abs/2002.10111)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating 2D region proposals, (ii) a R-CNN structure predicting 3D object pose by utilizing the acquired regions of interest. We argue that the 2D detection network is redundant and introduces non-negligible noise for 3D detection. Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, which significantly improves both training convergence and detection accuracy. In contrast to previous 3D detection techniques, our method does not require complicated pre/post-processing, extra data, and a refinement stage. Despite of its structural simplicity, our proposed SMOKE network outperforms all existing monocular 3D detection methods on the KITTI dataset, giving the best state-of-the-art result on both 3D object detection and Bird's eye view evaluation.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/79644370/143886681-52cb72b9-6635-4624-a728-1c243b046517.png" width="800"/>
+</div>
+
+## Introduction
+
+We implement SMOKE and provide the results and checkpoints on KITTI dataset.
+
+## Results and models
+
+### KITTI
+
+|                               Backbone                               | Lr schd | Mem (GB) | Inf time (fps) |  mAP  |                                                                                                                                                         Download                                                                                                                                                         |
+| :------------------------------------------------------------------: | :-----: | :------: | :------------: | :---: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [DLA34](./smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d.py) |   6x    |   9.64   |                | 13.85 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553-d46d9bb0.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553.log.json) |
+
+Note: mAP represents Car moderate 3D strict AP11 results.
+
+Detailed performance on KITTI 3D detection (3D/BEV) is as follows, evaluated by AP11 metric:
+
+|            |     Easy      |   Moderate    |     Hard      |
+| ---------- | :-----------: | :-----------: | :-----------: |
+| Car        | 16.92 / 22.97 | 13.85 / 18.32 | 11.90 / 15.88 |
+| Pedestrian | 11.13 / 12.61 | 11.10 / 11.32 | 10.67 / 11.14 |
+| Cyclist    | 0.99  / 1.47  |  0.54 / 0.65  |  0.55 / 0.67  |
+
+## Citation
+
+```latex
+@inproceedings{liu2020smoke,
+  title={Smoke: Single-stage monocular 3d object detection via keypoint estimation},
+  author={Liu, Zechen and Wu, Zizhang and T{\'o}th, Roland},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
+  pages={996--997},
+  year={2020}
+}
+```

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/smoke/metafile.yml

+Collections:
+  - Name: SMOKE
+    Metadata:
+      Training Data: KITTI
+      Training Techniques:
+        - Adam
+      Training Resources: 4x V100 GPUS
+      Architecture:
+        - SMOKEMono3DHead
+        - DLA
+    Paper:
+      URL: https://arxiv.org/abs/2002.10111
+      Title: 'SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation'
+    README: configs/smoke/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/mmdet3d/models/detectors/smoke_mono3d.py#L7
+      Version: v1.0.0
+
+Models:
+  - Name: smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d
+    In Collection: SMOKE
+    Config: configs/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d.py
+    Metadata:
+      Training Memory (GB): 9.6
+    Results:
+      - Task: 3D Object Detection
+        Dataset: KITTI
+        Metrics:
+          mAP: 13.8
+    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553-d46d9bb0.pth

docker-hub/FlashOCC/Flashocc/mmdetection3d/configs/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d.py

+_base_ = [
+    '../_base_/datasets/kitti-mono3d.py', '../_base_/models/smoke.py',
+    '../_base_/default_runtime.py'
+]
+
+# optimizer
+optimizer = dict(type='Adam', lr=2.5e-4)
+optimizer_config = dict(grad_clip=None)
+lr_config = dict(policy='step', warmup=None, step=[50])
+
+# runtime settings
+runner = dict(type='EpochBasedRunner', max_epochs=72)
+log_config = dict(interval=10)
+
+find_unused_parameters = True
+class_names = ['Pedestrian', 'Cyclist', 'Car']
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFileMono3D'),
+    dict(
+        type='LoadAnnotations3D',
+        with_bbox=True,
+        with_label=True,
+        with_attr_label=False,
+        with_bbox_3d=True,
+        with_label_3d=True,
+        with_bbox_depth=True),
+    dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
+    dict(type='RandomShiftScale', shift_scale=(0.2, 0.4), aug_prob=0.3),
+    dict(type='AffineResize', img_scale=(1280, 384), down_ratio=4),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle3D', class_names=class_names),
+    dict(
+        type='Collect3D',
+        keys=[
+            'img', 'gt_bboxes', 'gt_labels', 'gt_bboxes_3d', 'gt_labels_3d',
+            'centers2d', 'depths'
+        ]),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFileMono3D'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1280, 384),
+        flip=False,
+        transforms=[
+            dict(type='AffineResize', img_scale=(1280, 384), down_ratio=4),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(
+                type='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='Collect3D', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=4,
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))