Skip to content

Commit c543b48

Browse files
JingweiZhang12ZwwWayne
authored andcommitted
[Docs] Update all the metafiles acoording to README (#2006)
* update centerpoint, dgcnn, fcos3d and free_anchor metafile * check all metafile in configs * update centerpoint, pointpillars and second yml * rename PartA2 to parta2 in the name of config * update metafile in nuimages * update readme in nuimages
1 parent 2072a9d commit c543b48

28 files changed

+252
-161
lines changed

.dev_scripts/test_benchmark.sh

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -73,11 +73,11 @@ GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=5 ./tools/slurm_test.sh $PARTITION dv_mvx-f
7373
$CHECKPOINT_DIR/configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py/latest.pth --eval map \
7474
2>&1|tee $CHECKPOINT_DIR/configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py/FULL_LOG.txt &
7575

76-
echo 'configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py' &
77-
mkdir -p $CHECKPOINT_DIR/configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py
78-
GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=5 ./tools/slurm_test.sh $PARTITION hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py \
79-
$CHECKPOINT_DIR/configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py/latest.pth --eval map \
80-
2>&1|tee $CHECKPOINT_DIR/configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py/FULL_LOG.txt &
76+
echo 'configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py' &
77+
mkdir -p $CHECKPOINT_DIR/configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py
78+
GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=5 ./tools/slurm_test.sh $PARTITION hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py \
79+
$CHECKPOINT_DIR/configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py/latest.pth --eval map \
80+
2>&1|tee $CHECKPOINT_DIR/configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py/FULL_LOG.txt &
8181

8282
echo 'configs/pointnet2/pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py' &
8383
mkdir -p $CHECKPOINT_DIR/configs/pointnet2/pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py

.dev_scripts/train_benchmark.sh

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -73,11 +73,11 @@ GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=5 ./tools/slurm_train.sh $PARTITION dv_mvx-
7373
$CHECKPOINT_DIR/configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py --cfg-options checkpoint_config.max_keep_ckpts=1 \
7474
2>&1|tee $CHECKPOINT_DIR/configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py/FULL_LOG.txt &
7575

76-
echo 'configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py' &
77-
mkdir -p $CHECKPOINT_DIR/configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py
78-
GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=5 ./tools/slurm_train.sh $PARTITION hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py \
79-
$CHECKPOINT_DIR/configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py --cfg-options checkpoint_config.max_keep_ckpts=1 \
80-
2>&1|tee $CHECKPOINT_DIR/configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py/FULL_LOG.txt &
76+
echo 'configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py' &
77+
mkdir -p $CHECKPOINT_DIR/configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py
78+
GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=5 ./tools/slurm_train.sh $PARTITION hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py \
79+
$CHECKPOINT_DIR/configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py --cfg-options checkpoint_config.max_keep_ckpts=1 \
80+
2>&1|tee $CHECKPOINT_DIR/configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py/FULL_LOG.txt &
8181

8282
echo 'configs/pointnet2/pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py' &
8383
mkdir -p $CHECKPOINT_DIR/configs/pointnet2/pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py

configs/centerpoint/README.md

Lines changed: 19 additions & 17 deletions
Large diffs are not rendered by default.

configs/centerpoint/metafile.yml

Lines changed: 31 additions & 31 deletions
Original file line numberDiff line numberDiff line change
@@ -16,80 +16,80 @@ Collections:
1616
Version: v0.6.0
1717

1818
Models:
19-
- Name: centerpoint_01voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus
19+
- Name: centerpoint_voxel01_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d
2020
In Collection: CenterPoint
2121
Config: configs/centerpoint/centerpoint_voxel01_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py
22-
Metadata:
23-
Training Memory (GB): 4.9
22+
metadata:
23+
Training Memory (GB): 5.2
2424
Results:
2525
- Task: 3D Object Detection
2626
Dataset: nuScenes
2727
Metrics:
28-
mAP: 56.19
29-
NDS: 64.43
30-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/centerpoint/centerpoint_01voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus/centerpoint_01voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus_20201001_135205-5db91e00.pth
28+
mAP: 56.11
29+
NDS: 64.61
30+
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/centerpoint/centerpoint_01voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus/centerpoint_01voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus_20220810_030004-9061688e.pth
3131

32-
- Name: centerpoint_01voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus
32+
- Name: centerpoint_voxel01_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d
3333
In Collection: CenterPoint
3434
Config: configs/centerpoint/centerpoint_voxel01_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py
3535
Metadata:
36-
Training Memory (GB): 5.2
36+
Training Memory (GB): 5.5
3737
Results:
3838
- Task: 3D Object Detection
3939
Dataset: nuScenes
4040
Metrics:
41-
mAP: 56.34
42-
NDS: 64.81
43-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/centerpoint/centerpoint_01voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus/centerpoint_01voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus_20201004_075317-26d8176c.pth
41+
mAP: 56.10
42+
NDS: 64.69
43+
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/centerpoint/centerpoint_01voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus/centerpoint_01voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus_20220810_052355-a6928835.pth
4444

45-
- Name: centerpoint_0075voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus
45+
- Name: centerpoint_voxel0075_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d
4646
In Collection: CenterPoint
4747
Config: configs/centerpoint/centerpoint_voxel0075_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py
4848
Metadata:
49-
Training Memory (GB): 7.8
49+
Training Memory (GB): 8.2
5050
Results:
5151
- Task: 3D Object Detection
5252
Dataset: nuScenes
5353
Metrics:
54-
mAP: 57.34
55-
NDS: 65.23
56-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/centerpoint/centerpoint_0075voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus/centerpoint_0075voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus_20200925_230905-358fbe3b.pth
54+
mAP: 56.54
55+
NDS: 65.17
56+
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/centerpoint/centerpoint_0075voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus/centerpoint_0075voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus_20220810_011659-04cb3a3b.pth
5757

58-
- Name: centerpoint_0075voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus
58+
- Name: centerpoint_voxel0075_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d
5959
In Collection: CenterPoint
6060
Config: configs/centerpoint/centerpoint_voxel0075_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py
6161
Metadata:
62-
Training Memory (GB): 8.5
62+
Training Memory (GB): 8.7
6363
Results:
6464
- Task: 3D Object Detection
6565
Dataset: nuScenes
6666
Metrics:
67-
mAP: 57.27
68-
NDS: 65.58
69-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/centerpoint/centerpoint_0075voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus/centerpoint_0075voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus_20200930_201619-67c8496f.pth
67+
mAP: 56.92
68+
NDS: 65.27
69+
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/centerpoint/centerpoint_0075voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus/centerpoint_0075voxel_second_secfpn_dcn_circlenms_4x8_cyclic_20e_nus_20220810_025930-657f67e0.pth
7070

71-
- Name: centerpoint_02pillar_second_secfpn_circlenms_4x8_cyclic_20e_nus
71+
- Name: centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d
7272
In Collection: CenterPoint
7373
Config: configs/centerpoint/centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py
7474
Metadata:
75-
Training Memory (GB): 4.4
75+
Training Memory (GB): 4.6
7676
Results:
7777
- Task: 3D Object Detection
7878
Dataset: nuScenes
7979
Metrics:
80-
mAP: 49.07
81-
NDS: 59.66
82-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/centerpoint/centerpoint_01voxel_second_secfpn_circlenms_4x8_cyclic_20e_nus/centerpoint_02pillar_second_secfpn_circlenms_4x8_cyclic_20e_nus_20201004_170716-a134a233.pth
80+
mAP: 48.70
81+
NDS: 59.62
82+
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/centerpoint/centerpoint_02pillar_second_secfpn_circlenms_4x8_cyclic_20e_nus/centerpoint_02pillar_second_secfpn_circlenms_4x8_cyclic_20e_nus_20220811_031844-191a3822.pth
8383

84-
- Name: centerpoint_02pillar_second_secfpn_dcn_4x8_cyclic_20e_nus
84+
- Name: centerpoint_pillar02_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d
8585
In Collection: CenterPoint
8686
Config: configs/centerpoint/centerpoint_pillar02_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py
8787
Metadata:
88-
Training Memory (GB): 4.6
88+
Training Memory (GB): 4.9
8989
Results:
9090
- Task: 3D Object Detection
9191
Dataset: nuScenes
9292
Metrics:
93-
mAP: 48.8
94-
NDS: 59.67
95-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/centerpoint/centerpoint_02pillar_second_secfpn_dcn_4x8_cyclic_20e_nus/centerpoint_02pillar_second_secfpn_dcn_4x8_cyclic_20e_nus_20200930_103722-3bb135f2.pth
93+
mAP: 48.38
94+
NDS: 59.79
95+
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/centerpoint/centerpoint_02pillar_second_secfpn_dcn_4x8_cyclic_20e_nus/centerpoint_02pillar_second_secfpn_dcn_4x8_cyclic_20e_nus_20220811_045458-808e69ad.pth

configs/fcos3d/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -52,7 +52,7 @@ We also provide visualization functions to show the monocular 3D detection resul
5252

5353
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP | NDS | Download |
5454
| :-------------------------------------------------------------------------------------: | :-----: | :------: | :------------: | :--: | :--: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
55-
| \[ResNet101 w/ DCN\](./fcos3d_r101-caffe- fpn-head-gn-dcn_8xb2-1x_nus-mono3d.py) | 1x | 8.69 | | 29.8 | 37.7 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_20210715_235813-4bed5239.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_20210715_235813.log.json) |
55+
| \[ResNet101 w/ DCN\](./fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d.py) | 1x | 8.69 | | 29.8 | 37.7 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_20210715_235813-4bed5239.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_20210715_235813.log.json) |
5656
| [above w/ finetune](./fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d_finetune.py) | 1x | 8.69 | | 32.1 | 39.5 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210717_095645-8d806dc2.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210717_095645.log.json) |
5757
| above w/ tta | 1x | 8.69 | | 33.1 | 40.3 | |
5858

configs/fcos3d/metafile.yml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@ Models:
2727
Metrics:
2828
mAP: 29.9
2929
NDS: 37.3
30-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_20210425_181341-8d5a21fe.pth
30+
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_20210715_235813-4bed5239.pth
3131

3232
- Name: fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune
3333
In Collection: FCOS3D
@@ -40,4 +40,4 @@ Models:
4040
Metrics:
4141
mAP: 32.1
4242
NDS: 39.3
43-
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210427_091419-35aaaad0.pth
43+
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210717_095645-8d806dc2.pth

configs/free_anchor/metafile.yml

Lines changed: 31 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,20 @@ Collections:
1717
Version: v0.5.0
1818

1919
Models:
20-
- Name: hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d
20+
- Name: pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d
21+
In Collection: FreeAnchor
22+
Config: pointpillars/pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d.py
23+
Metadata:
24+
Training Memory (GB): 17.1
25+
Results:
26+
- Task: 3D Object Detection
27+
Dataset: nuScenes
28+
Metrics:
29+
mAP: 40.0
30+
NDS: 53.3
31+
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth
32+
33+
- Name: pointpillars_hv_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d
2134
In Collection: FreeAnchor
2235
Config: free_anchor/pointpillars_hv_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py
2336
Metadata:
@@ -28,9 +41,22 @@ Models:
2841
Metrics:
2942
mAP: 43.82
3043
NDS: 54.86
44+
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20210816_163441-ae0897e7.pth
45+
46+
- Name: pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb4-2x_nus-3d
47+
In Collection: FreeAnchor
48+
Config: configs/regnet/pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb4-2x_nus-3d.py
49+
Metadata:
50+
Training Memory (GB): 17.3
51+
Results:
52+
- Task: 3D Object Detection
53+
Dataset: nuScenes
54+
Metrics:
55+
mAP: 44.8
56+
NDS: 56.4
3157
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/free_anchor/hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20210816_163441-ae0897e7.pth
3258

33-
- Name: hv_pointpillars_regnet-400mf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d
59+
- Name: pointpillars_hv_regnet-400mf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d
3460
In Collection: FreeAnchor
3561
Config: configs/free_anchor/pointpillars_hv_regnet-400mf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py
3662
Metadata:
@@ -56,7 +82,7 @@ Models:
5682
NDS: 61.49
5783
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/free_anchor/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20210828_025608-bfbd506e.pth
5884

59-
- Name: hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d
85+
- Name: pointpillars_hv_regnet-1.6gf_fpn_head-free-anchor_sbn-all_8xb4-strong-aug-3x_nus-3d
6086
In Collection: FreeAnchor
6187
Config: configs/free_anchor/pointpillars_hv_regnet-1.6gf_fpn_head-free-anchor_sbn-all_8xb4-strong-aug-3x_nus-3d.py
6288
Metadata:
@@ -69,7 +95,7 @@ Models:
6995
NDS: 62.45
7096
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/free_anchor/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d_20210827_184909-14d2dbd1.pth
7197

72-
- Name: hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d
98+
- Name: pointpillars_hv_regnet-3.2gf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d
7399
In Collection: FreeAnchor
74100
Config: configs/free_anchor/pointpillars_hv_regnet-3.2gf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py
75101
Metadata:
@@ -82,7 +108,7 @@ Models:
82108
NDS: 61.94
83109
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/free_anchor/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d/hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_4x8_2x_nus-3d_20210827_181237-e385c35a.pth
84110

85-
- Name: hv_pointpillars_regnet-3.2gf_fpn_sbn-all_free-anchor_strong-aug_4x8_3x_nus-3d
111+
- Name: pointpillars_hv_regnet-3.2gf_fpn_head-free-anchor_sbn-all_8xb4-strong-aug-3x_nus-3d
86112
In Collection: FreeAnchor
87113
Config: configs/free_anchor/pointpillars_hv_regnet-3.2gf_fpn_head-free-anchor_sbn-all_8xb4-strong-aug-3x_nus-3d.py
88114
Metadata:

configs/monoflex/metafile.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,5 +26,5 @@ Models:
2626
- Task: 3D Object Detection
2727
Dataset: KITTI
2828
Metrics:
29-
mAP: 21.98
29+
mAP: 21.86
3030
Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/monoflex/monoflex_dla34_pytorch_dlaneck_gn-all_2x4_6x_kitti-mono3d_20211228_027553-d46d9bb0.pth

configs/nuimages/README.md

Lines changed: 12 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,16 @@
1-
# NuImages Results
1+
# Mask R-CNN
22

3-
<!-- [DATASET] -->
3+
> [Mask R-CNN](https://arxiv.org/abs/1703.06870)
4+
5+
<!-- [ALGORITHM] -->
6+
7+
## Abstract
8+
9+
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition.
10+
11+
<div align=center>
12+
<img src="https://user-images.githubusercontent.com/40661020/143967081-c2552bed-9af2-46c4-ae44-5b3b74e5679f.png"/>
13+
</div>
414

515
## Introduction
616

0 commit comments

Comments
 (0)