[Fix] Update links of configs and restrict the version of MMCV (#2337)

* update config link in readme * update version restriction * update * fix some configs error in metafile * add pvrcnn and fcaf3d in model-index.yml

[Fix] Update links of configs and restrict the version of MMCV (#2337)
* update config link in readme * update version restriction * update * fix some configs error in metafile * add pvrcnn and fcaf3d in model-index.yml
06b56888 · Jingwei Zhang · GitHub · e943e84d · 06b56888 · 06b56888
Unverified Commit 06b56888 authored Mar 16, 2023 by Jingwei Zhang Committed by GitHub Mar 16, 2023
15 changed files
--- a/configs/centerpoint/README.md
+++ b/configs/centerpoint/README.md
--- a/configs/fcos3d/README.md
+++ b/configs/fcos3d/README.md
@@ -52,7 +52,7 @@ We also provide visualization functions to show the monocular 3D detection resul
 |                                        Backbone                                         | Lr schd | Mem (GB) | Inf time (fps) | mAP  | NDS  |                                                                                                                                                                                                                             Download                                                                                                                                                                                                                             |
 | :-------------------------------------------------------------------------------------: | :-----: | :------: | :------------: | :--: | :--: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
-|     \[ResNet101 w/ DCN\](./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)                   |
+|      [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)                   |
 | [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) |
 |                                      above w/ tta                                       |   1x    |   8.69   |                | 33.1 | 40.3 |                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |

--- a/configs/pointpillars/README.md
+++ b/configs/pointpillars/README.md
@@ -30,9 +30,9 @@ We implement PointPillars and provide the results and checkpoints on KITTI, nuSc
 |                                Backbone                                 | Lr schd | Mem (GB) | Inf time (fps) |  mAP  |  NDS  |                                                                                                                                                                                                     Download                                                                                                                                                                                                     |
 | :---------------------------------------------------------------------: | :-----: | :------: | :------------: | :---: | :---: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
 |      [SECFPN](./pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py)       |   2x    |   16.4   |                | 34.33 | 49.1  |   [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20210826_225857-f19d00a3.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20210826_225857.log.json)   |
-| [SECFPN (FP16)](./hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d.py) |   2x    |   8.37   |                | 35.19 | 50.27 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d_20201020_222626-c3f0483e.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d_20201020_222626.log.json) |
+| [SECFPN (FP16)](./pointpillars_hv_secfpn_sbn-all_8xb2-amp-2x_nus-3d.py) |   2x    |   8.37   |                | 35.19 | 50.27 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d_20201020_222626-c3f0483e.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_fp16_2x8_2x_nus-3d_20201020_222626.log.json) |
 |         [FPN](./pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d.py)          |   2x    |   16.3   |                | 39.7  | 53.2  |         [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20210826_104936-fca299c1.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20210826_104936.log.json)         |
-|    [FPN (FP16)](./hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d.py)    |   2x    |   8.40   |                | 39.26 | 53.26 |       [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d_20201021_120719-269f9dd6.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d_20201021_120719.log.json)       |
+|    [FPN (FP16)](./pointpillars_hv_fpn_sbn-all_8xb2-amp-2x_nus-3d.py)    |   2x    |   8.40   |                | 39.26 | 53.26 |       [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d_20201021_120719-269f9dd6.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fp16/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_fp16_2x8_2x_nus-3d_20201021_120719.log.json)       |
 ### Lyft

--- a/configs/pointpillars/metafile.yml
+++ b/configs/pointpillars/metafile.yml
@@ -147,9 +147,9 @@ Models:
          Public Score: 15.0
    Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_fpn_sbn-all_2x8_2x_lyft-3d_20210822_095429-0b3d6196.pth
-  - Name: hv_pointpillars_secfpn_sbn_2x16_2x_waymoD5-3d-car
+  - Name: pointpillars_hv_secfpn_sbn_2x16_2x_waymoD5-3d-car
    In Collection: PointPillars
-    Config: configs/pointpillars/hv_pointpillars_secfpn_sbn_2x16_2x_waymoD5-3d-car.py
+    Config: configs/pointpillars/pointpillars_hv_secfpn_sbn_2x16_2x_waymoD5-3d-car.py
    Metadata:
      Training Data: Waymo
      Training Memory (GB): 7.76
@@ -164,7 +164,7 @@ Models:
          mAPH@L2: 62.1
    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn_2x16_2x_waymoD5-3d-car/hv_pointpillars_secfpn_sbn_2x16_2x_waymoD5-3d-car_20200901_204315-302fc3e7.pth
-  - Name: hv_pointpillars_secfpn_sbn_2x16_2x_waymoD5-3d-3class
+  - Name: pointpillars_hv_secfpn_sbn_2x16_2x_waymoD5-3d-3class
    Alias: pointpillars_waymod5-3class
    In Collection: PointPillars
    Config: configs/pointpillars/pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymoD5-3d-3class.py
@@ -182,7 +182,7 @@ Models:
          mAPH@L2: 52.1
    Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn_2x16_2x_waymoD5-3d-3class/hv_pointpillars_secfpn_sbn_2x16_2x_waymoD5-3d-3class_20200831_204144-d1a706b1.pth
-  - Name: hv_pointpillars_secfpn_sbn_2x16_2x_waymo-3d-car
+  - Name: pointpillars_hv_secfpn_sbn_2x16_2x_waymo-3d-car
    In Collection: PointPillars
    Config: configs/pointpillars/pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymo-3d-car.py
    Metadata:
@@ -198,7 +198,7 @@ Models:
          mAP@L2: 63.6
          mAPH@L2: 63.1
-  - Name: hv_pointpillars_secfpn_sbn_2x16_2x_waymo-3d-3class
+  - Name: pointpillars_hv_secfpn_sbn_2x16_2x_waymo-3d-3class
    In Collection: PointPillars
    Config: configs/pointpillars/pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymo-3d-3class.py
    Metadata:

--- a/configs/pointpillars/pointpillars_hv_fpn_sbn-all_8xb4-amp-2x_nus-3d.py
+++ b/configs/pointpillars/pointpillars_hv_fpn_sbn-all_8xb4-amp-2x_nus-3d.py
-_base_ = 'pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d.py'
+_base_ = './pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d.py'
+train_dataloader = dict(batch_size=2, num_workers=2)
 # schedule settings
 optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=512.)
--- a/configs/pointpillars/pointpillars_hv_secfpn_sbn-all_8xb4-amp-2x_nus-3d.py
+++ b/configs/pointpillars/pointpillars_hv_secfpn_sbn-all_8xb4-amp-2x_nus-3d.py
-_base_ = 'pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py'
+_base_ = './pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py'
+train_dataloader = dict(batch_size=2, num_workers=2)
 # schedule settings
 optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=512.)
--- a/configs/pv_rcnn/README.md
+++ b/configs/pv_rcnn/README.md
@@ -4,7 +4,7 @@
 <!-- [ALGORITHM] -->
-## Introduction
+## Abstract
 3D object detection has been receiving increasing attention from both industry and academia thanks to its wide applications in various fields such as autonomous driving and robotics. LiDAR sensors are widely adopted in autonomous driving vehicles and robots for capturing 3D scene information as sparse and irregular point clouds, which provide vital cues for 3D scene perception and understanding. In this paper, we propose to achieve high performance 3D object detection by designing novel point-voxel integrated networks to learn better 3D features from irregular point clouds.

--- a/configs/regnet/metafile.yml
+++ b/configs/regnet/metafile.yml
 Models:
-  - Name: hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d
+  - Name: pointpillars_hv_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d
    In Collection: PointPillars
-    Config: configs/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_8xb4-2x_nus-3d.py
+    Config: configs/regnet/pointpillars_hv_regnet-400mf_secfpn_sbn-all_8xb4-2x_nus-3d.py
    Metadata:
      Training Data: nuScenes
      Training Memory (GB): 16.4
@@ -16,9 +16,9 @@ Models:
          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_8xb4-2x_nus-3d
+  - Name: pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb4-2x_nus-3d
    In Collection: PointPillars
-    Config: configs/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_8xb4-2x_nus-3d.py
+    Config: configs/regnet/pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb4-2x_nus-3d.py
    Metadata:
      Training Data: nuScenes
      Training Memory (GB): 17.3
@@ -33,9 +33,9 @@ Models:
          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_8xb4-2x_nus-3d
+  - Name: pointpillars_hv_regnet-1.6gf_fpn_sbn-all_8xb4-2x_nus-3d
    In Collection: PointPillars
-    Config: configs/regnet/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_8xb4-2x_nus-3d.py
+    Config: configs/regnet/pointpillars_hv_regnet-1.6gf_fpn_sbn-all_8xb4-2x_nus-3d.py
    Metadata:
      Training Data: nuScenes
      Training Memory (GB): 24.0
@@ -50,9 +50,9 @@ Models:
          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
+  - Name: pointpillars_hv_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
+    Config: configs/regnet/pointpillars_hv_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d.py
    Metadata:
      Training Data: Lyft
      Training Memory (GB): 15.9
@@ -67,9 +67,9 @@ Models:
          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
+  - Name: pointpillars_hv_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
+    Config: configs/regnet/pointpillars_hv_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d.py
    Metadata:
      Training Data: Lyft
      Training Memory (GB): 13.0

--- a/configs/second/metafile.yml
+++ b/configs/second/metafile.yml
@@ -60,7 +60,7 @@ Models:
  - Name: second_hv_secfpn_8xb6-amp-80e_kitti-3d-car
    In Collection: SECOND
-    Config: configs/second/hv_second_secfpn_8xb6-amp-80e_kitti-3d-car.py
+    Config: configs/second/second_hv_secfpn_8xb6-amp-80e_kitti-3d-car.py
    Metadata:
      Training Techniques:
        - AdamW
@@ -79,7 +79,7 @@ Models:
  - Name: second_hv_secfpn_8xb6-amp-80e_kitti-3d-3class
    In Collection: SECOND
-    Config: configs/second/hv_second_secfpn_8xb6-amp-80e_kitti-3d-3class.py
+    Config: configs/second/second_hv_secfpn_8xb6-amp-80e_kitti-3d-3class.py
    Metadata:
      Training Techniques:
        - AdamW

--- a/configs/smoke/metafile.yml
+++ b/configs/smoke/metafile.yml
@@ -17,9 +17,9 @@ Collections:
      Version: v1.0.0
 Models:
-  - Name: smoke_dla34_pytorch_dlaneck_gn-all_4xb8-6x_kitti-mono3d
+  - Name: smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d
    In Collection: SMOKE
-    Config: configs/smoke/smoke_dla34_pytorch_dlaneck_gn-all_4xb8-6x_kitti-mono3d.py
+    Config: configs/smoke/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d.py
    Metadata:
      Training Memory (GB): 9.6
    Results:

--- a/docs/en/notes/faq.md
+++ b/docs/en/notes/faq.md
@@ -11,8 +11,8 @@ We list some potential troubles encountered by users and developers, along with
  | MMDetection3D version |     MMEngine version     |      MMCV version       |   MMDetection version    |
  | --------------------- | :----------------------: | :---------------------: | :----------------------: |
  | dev-1.x               | mmengine>=0.6.0, \<1.0.0 | mmcv>=2.0.0rc4, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
-  | v1.1.0rc3             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
+  | v1.1.0rc3             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc3, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
-  | v1.1.0rc2             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
+  | v1.1.0rc2             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc3, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
  | v1.1.0rc1             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
  | v1.1.0rc0             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |

--- a/docs/zh_cn/get_started.md
+++ b/docs/zh_cn/get_started.md
@@ -44,7 +44,7 @@ conda install pytorch torchvision cpuonly -c pytorch
 ```shell
 pip install -U openmim
 mim install mmengine
-mim install 'mmcv>=2.0.0rc0'
+mim install 'mmcv>=2.0.0rc4'
 mim install 'mmdet>=3.0.0rc0'
 ```

--- a/model-index.yml
+++ b/model-index.yml
@@ -23,3 +23,5 @@ Import:
  - configs/smoke/metafile.yml
  - configs/ssn/metafile.yml
  - configs/votenet/metafile.yml
+  - configs/pv_rcnn/metafile.yml
+  - configs/fcaf3d/metafile.yml
--- a/projects/PETR/README.md
+++ b/projects/PETR/README.md
@@ -34,9 +34,9 @@ python tools/test.py projects/PETR/config/petr/petr_vovnet_gridmask_p4_800x320.p
 This Result is trained by petr_vovnet_gridmask_p4_800x320.py and use [weights](https://drive.google.com/file/d/1ABI5BoQCkCkP4B0pO5KBJ3Ni0tei0gZi/view?usp=sharing) as pretrain weight.
-|                                             Backbone                                             | Lr schd | Mem (GB) | Inf time (fps) | mAP  | NDS  |         Download         |
+|                                   Backbone                                    | Lr schd | Mem (GB) | Inf time (fps) | mAP  | NDS  |         Download         |
-| :----------------------------------------------------------------------------------------------: | :-----: | :------: | :------------: | :--: | :--: | :----------------------: |
+| :---------------------------------------------------------------------------: | :-----: | :------: | :------------: | :--: | :--: | :----------------------: |
-| [petr_vovnet_gridmask_p4_800x320](projects/PETR/configs/petr/petr_vovnet_gridmask_p4_800x320.py) |   1x    |   7.62   |      18.7      | 38.3 | 43.5 | [model](<>) \| [log](<>) |
+| [petr_vovnet_gridmask_p4_800x320](configs/petr_vovnet_gridmask_p4_800x320.py) |   1x    |   7.62   |      18.7      | 38.3 | 43.5 | [model](<>) \| [log](<>) |
 ```
 mAP: 0.3830

--- a/projects/PETR/config/petr/petr_vovnet_gridmask_p4_800x320.py
+++ b/projects/PETR/config/petr/petr_vovnet_gridmask_p4_800x320.py