V1.0.0.dev0

.github/workflows/build.yml

@@ -41,22 +41,22 @@ jobs:
         torch: [1.5.0+cu101, 1.6.0+cu101, 1.7.0+cu101, 1.8.0+cu101]
         include:
           - torch: 1.5.0+cu101
-            torch_version: torch1.5.0
+            torch_version: torch1.5
             torchvision: 0.6.0+cu101
             mmcv_link: "torch1.5.0"
             cuda_arch: "7.0"
           - torch: 1.6.0+cu101
-            torch_version: torch1.6.0
+            torch_version: torch1.6
             mmcv_link: "torch1.6.0"
             torchvision: 0.7.0+cu101
             cuda_arch: "7.0"
           - torch: 1.7.0+cu101
-            torch_version: torch1.7.0
+            torch_version: torch1.7
             mmcv_link: "torch1.7.0"
             torchvision: 0.8.1+cu101
             cuda_arch: "7.0"
           - torch: 1.8.0+cu101
-            torch_version: torch1.8.0
+            torch_version: torch1.8
             mmcv_link: "torch1.8.0"
             torchvision: 0.9.0+cu101
             cuda_arch: "7.0"

.pre-commit-config.yaml

@@ -40,7 +40,7 @@ repos:
       - id: docformatter
         args: ["--in-place", "--wrap-descriptions", "79"]
   - repo: https://github.com/open-mmlab/pre-commit-hooks
-    rev: master  # Use the ref you want to point at
+    rev: v0.2.0  # Use the ref you want to point at
     hooks:
       - id: check-algo-readme
       - id: check-copyright

README.md

@@ -1,5 +1,22 @@
 <div align="center">
   <img src="resources/mmdet3d-logo.png" width="600"/>
+  <div>&nbsp;</div>
+  <div align="center">
+    <b><font size="5">OpenMMLab website</font></b>
+    <sup>
+      <a href="https://openmmlab.com">
+        <i><font size="4">HOT</font></i>
+      </a>
+    </sup>
+    &nbsp;&nbsp;&nbsp;&nbsp;
+    <b><font size="5">OpenMMLab platform</font></b>
+    <sup>
+      <a href="https://platform.openmmlab.com">
+        <i><font size="4">TRY IT OUT</font></i>
+      </a>
+    </sup>
+  </div>
+  <div>&nbsp;</div>
 </div>
 
 [![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdetection3d.readthedocs.io/en/latest/)
@@ -8,16 +25,12 @@
 [![license](https://img.shields.io/github/license/open-mmlab/mmdetection3d.svg)](https://github.com/open-mmlab/mmdetection3d/blob/master/LICENSE)
 
 
-**News**: We released the codebase v0.17.3.
+**News**: We released the codebase v1.0.0rc0.
 
-In addition, we have preliminarily supported several new models on the [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) branch, including [DGCNN](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/dgcnn/README.md), [SMOKE](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/smoke/README.md) and [PGD](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/pgd/README.md).
-
-Note: We are going through large refactoring to provide simpler and more unified usage of many modules. Thus, few features will be added to the master branch in the following months.
+Note: We are going through large refactoring to provide simpler and more unified usage of many modules.
 
 The compatibilities of models are broken due to the unification and simplification of coordinate systems. For now, most models are benchmarked with similar performance, though few models are still being benchmarked.
 
-You can start experiments with [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) if you are interested. Please note that our new features will only be supported in v1.0.0 branch afterward.
-
 In the [nuScenes 3D detection challenge](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any) of the 5th AI Driving Olympics in NeurIPS 2020, we obtained the best PKL award and the second runner-up by multi-modality entry, and the best vision-only results.
 
 Code and models for the best vision-only method, [FCOS3D](https://arxiv.org/abs/2104.10956), have been released. Please stay tuned for [MoCa](https://arxiv.org/abs/2012.12741).
@@ -70,11 +83,9 @@ This project is released under the [Apache 2.0 license](LICENSE).
 
 ## Changelog
 
-v0.17.3 was released in 1/12/2021.
+v1.0.0rc0 was released in 18/2/2022.
 Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
 
-For branch v1.0.0.dev0, please refer to [changelog_v1.0.md](https://github.com/Tai-Wang/mmdetection3d/blob/v1.0.0.dev0-changelog/docs/changelog_v1.0.md) for our latest features and more details.
-
 ## Benchmark and model zoo
 
 Supported methods and backbones are shown in the below table.
@@ -104,7 +115,7 @@ Support methods
 - [x] [FCOS3D (ICCVW'2021)](configs/fcos3d/README.md)
 - [x] [PointNet++ (NeurIPS'2017)](configs/pointnet2/README.md)
 - [x] [Group-Free-3D (ICCV'2021)](configs/groupfree3d/README.md)
-- [x] [ImVoxelNet (Arxiv'2021)](configs/imvoxelnet/README.md)
+- [x] [ImVoxelNet (WACV'2022)](configs/imvoxelnet/README.md)
 - [x] [PAConv (CVPR'2021)](configs/paconv/README.md)
 - [x] [DGCNN (TOG'2019)](configs/dgcnn/README.md)
 - [x] [SMOKE (CVPRW'2020)](configs/smoke/README.md)

README_zh-CN.md

@@ -1,5 +1,22 @@
 <div align="center">
   <img src="resources/mmdet3d-logo.png" width="600"/>
+  <div>&nbsp;</div>
+  <div align="center">
+    <b><font size="5">OpenMMLab 官网</font></b>
+    <sup>
+      <a href="https://openmmlab.com">
+        <i><font size="4">HOT</font></i>
+      </a>
+    </sup>
+    &nbsp;&nbsp;&nbsp;&nbsp;
+    <b><font size="5">OpenMMLab 开放平台</font></b>
+    <sup>
+      <a href="https://platform.openmmlab.com">
+        <i><font size="4">TRY IT OUT</font></i>
+      </a>
+    </sup>
+  </div>
+  <div>&nbsp;</div>
 </div>
 
 [![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdetection3d.readthedocs.io/en/latest/)
@@ -8,16 +25,12 @@
 [![license](https://img.shields.io/github/license/open-mmlab/mmdetection3d.svg)](https://github.com/open-mmlab/mmdetection3d/blob/master/LICENSE)
 
 
-**新闻**: 我们发布了版本 v0.17.3.
+**新闻**: 我们发布了版本 v1.0.0rc0.
 
-另外，我们在 [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) 分支初步支持了多个新模型，包括 [DGCNN](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/dgcnn/README.md), [SMOKE](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/smoke/README.md) 和 [PGD](https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/configs/pgd/README.md)。
-
-说明：我们正在进行大规模的重构，以提供对许多模块更简单、更统一的使用。因此，在接下来的几个月里，很少有功能会添加到主分支中。
+说明：我们正在进行大规模的重构，以提供对许多模块更简单、更统一的使用。
 
 由于坐标系的统一和简化，模型的兼容性会受到影响。目前，大多数模型都以类似的性能对齐了精度，但仍有少数模型在进行基准测试。
 
-如果您感兴趣，可以开始使用 [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) 分支进行实验。请注意，我们的新功能将只支持在 v1.0.0 分支。
-
 在第三届 [nuScenes 3D 检测挑战赛](https://www.nuscenes.org/object-detection?externalData=all&mapData=all&modalities=Any)（第五届 AI Driving Olympics, NeurIPS 2020）中，我们获得了最佳 PKL 奖、第三名和最好的纯视觉的结果，相关的代码和模型将会在不久后发布。
 
 最好的纯视觉方法 [FCOS3D](https://arxiv.org/abs/2104.10956) 的代码和模型已经发布。请继续关注我们的多模态检测器 [MoCa](https://arxiv.org/abs/2012.12741)。
@@ -70,11 +83,9 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
 
 ## 更新日志
 
-最新的版本 v0.17.3 在 2021.12.01 发布。
+最新的版本 v1.0.0rc0 在 2022.2.18 发布。
 如果想了解更多版本更新细节和历史信息，请阅读[更新日志](docs/zh_cn/changelog.md)。
 
-对于分支 [v1.0.0.dev0](https://github.com/open-mmlab/mmdetection3d/tree/v1.0.0.dev0) ，请参考 [v1.0 更新日志](https://github.com/Tai-Wang/mmdetection3d/blob/v1.0.0.dev0-changelog/docs/changelog_v1.0.md) 来了解我们的最新功能和更多细节。
-
 ## 基准测试和模型库
 
 测试结果和模型可以在[模型库](docs/zh_cn/model_zoo.md)中找到。
@@ -103,7 +114,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
 - [x] [FCOS3D (ICCVW'2021)](configs/fcos3d/README.md)
 - [x] [PointNet++ (NeurIPS'2017)](configs/pointnet2/README.md)
 - [x] [Group-Free-3D (ICCV'2021)](configs/groupfree3d/README.md)
-- [x] [ImVoxelNet (Arxiv'2021)](configs/imvoxelnet/README.md)
+- [x] [ImVoxelNet (WACV'2022)](configs/imvoxelnet/README.md)
 - [x] [PAConv (CVPR'2021)](configs/paconv/README.md)
 - [x] [DGCNN (TOG'2019)](configs/dgcnn/README.md)
 - [x] [SMOKE (CVPRW'2020)](configs/smoke/README.md)

configs/_base_/models/hv_pointpillars_secfpn_kitti.py

@@ -34,12 +34,13 @@
         in_channels=384,
         feat_channels=384,
         use_direction_classifier=True,
+        assign_per_class=True,
         anchor_generator=dict(
-            type='Anchor3DRangeGenerator',
+            type='AlignedAnchor3DRangeGenerator',
             ranges=[
-                [0, -39.68, -0.6, 70.4, 39.68, -0.6],
-                [0, -39.68, -0.6, 70.4, 39.68, -0.6],
-                [0, -39.68, -1.78, 70.4, 39.68, -1.78],
+                [0, -39.68, -0.6, 69.12, 39.68, -0.6],
+                [0, -39.68, -0.6, 69.12, 39.68, -0.6],
+                [0, -39.68, -1.78, 69.12, 39.68, -1.78],
             ],
             sizes=[[0.8, 0.6, 1.73], [1.76, 0.6, 1.73], [3.9, 1.6, 1.56]],
             rotations=[0, 1.57],

configs/_base_/models/point_rcnn.py

@@ -91,23 +91,26 @@
                     pos_iou_thr=0.55,
                     neg_iou_thr=0.55,
                     min_pos_iou=0.55,
-                    ignore_iof_thr=-1),
+                    ignore_iof_thr=-1,
+                    match_low_quality=False),
                 dict(  # for Pedestrian
                     type='MaxIoUAssigner',
                     iou_calculator=dict(
                         type='BboxOverlaps3D', coordinate='lidar'),
                     pos_iou_thr=0.55,
                     neg_iou_thr=0.55,
                     min_pos_iou=0.55,
-                    ignore_iof_thr=-1),
+                    ignore_iof_thr=-1,
+                    match_low_quality=False),
                 dict(  # for Cyclist
                     type='MaxIoUAssigner',
                     iou_calculator=dict(
                         type='BboxOverlaps3D', coordinate='lidar'),
                     pos_iou_thr=0.55,
                     neg_iou_thr=0.55,
                     min_pos_iou=0.55,
-                    ignore_iof_thr=-1)
+                    ignore_iof_thr=-1,
+                    match_low_quality=False)
             ],
             sampler=dict(
                 type='IoUNegPiecewiseSampler',

configs/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py

@@ -15,21 +15,15 @@
     rate=1.0,
     prepare=dict(
         filter_by_difficulty=[-1],
-        filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
+        filter_by_min_points=dict(Car=5, Pedestrian=5, Cyclist=5)),
     classes=class_names,
-    sample_groups=dict(Car=15, Pedestrian=10, Cyclist=10))
+    sample_groups=dict(Car=15, Pedestrian=15, Cyclist=15))
 
 # PointPillars uses different augmentation hyper parameters
 train_pipeline = [
     dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4),
     dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
-    dict(type='ObjectSample', db_sampler=db_sampler),
-    dict(
-        type='ObjectNoise',
-        num_try=100,
-        translation_std=[0.25, 0.25, 0.25],
-        global_rot_range=[0.0, 0.0],
-        rot_range=[-0.15707963267, 0.15707963267]),
+    dict(type='ObjectSample', db_sampler=db_sampler, use_ground_plane=False),
     dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
     dict(
         type='GlobalRotScaleTrans',

demo/inference_demo.ipynb

@@ -3,74 +3,74 @@
   {
    "cell_type": "code",
    "execution_count": 7,
+   "source": [
+    "from mmdet3d.apis import init_model, inference_detector, show_result_meshlab"
+   ],
+   "outputs": [],
    "metadata": {
     "pycharm": {
      "is_executing": false
     }
-   },
-   "outputs": [],
-   "source": [
-    "from mmdet3d.apis import init_detector, inference_detector, show_result_meshlab"
-   ]
+   }
   },
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {
-    "pycharm": {
-     "is_executing": false
-    }
-   },
-   "outputs": [],
    "source": [
     "config_file = '../configs/second/hv_second_secfpn_6x8_80e_kitti-3d-car.py'\n",
     "# download the checkpoint from model zoo and put it in `checkpoints/`\n",
     "checkpoint_file = '../work_dirs/second/epoch_40.pth'"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {
+    "pycharm": {
+     "is_executing": false
+    }
+   }
   },
   {
    "cell_type": "code",
    "execution_count": 9,
+   "source": [
+    "# build the model from a config file and a checkpoint file\n",
+    "model = init_model(config_file, checkpoint_file, device='cuda:0')"
+   ],
+   "outputs": [],
    "metadata": {
     "pycharm": {
      "is_executing": false
     }
-   },
-   "outputs": [],
-   "source": [
-    "# build the model from a config file and a checkpoint file\n",
-    "model = init_detector(config_file, checkpoint_file, device='cuda:0')"
-   ]
+   }
   },
   {
    "cell_type": "code",
    "execution_count": 10,
-   "metadata": {
-    "pycharm": {
-     "is_executing": false
-    }
-   },
-   "outputs": [],
    "source": [
     "# test a single sample\n",
     "pcd = 'kitti_000008.bin'\n",
     "result, data = inference_detector(model, pcd)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
+   ],
+   "outputs": [],
    "metadata": {
     "pycharm": {
      "is_executing": false
     }
-   },
-   "outputs": [],
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
    "source": [
     "# show the results\n",
     "out_dir = './'\n",
     "show_result_meshlab(data, result, out_dir)"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {
+    "pycharm": {
+     "is_executing": false
+    }
+   }
   }
  ],
  "metadata": {