[Benchmark]Add PV RCNN benchmark

configs/pv_rcnn/README.md

@@ -0,0 +1,42 @@
+# PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
+
+> [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://arxiv.org/abs/1912.13192)
+
+<!-- [ALGORITHM] -->
+
+## Introduction
+
+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.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/88368822/202114244-ccf52f56-b8c9-4f1b-9cc2-80c7a9952c99.png" width="800"/>
+</div>
+
+## Results and models
+
+### KITTI
+
+|                    Backbone                     |  Class  |  Lr schd   | Mem (GB) | Inf time (fps) |  mAP  |                                                                                                                                                                    Download                                                                                                                                                                    |
+| :---------------------------------------------: | :-----: | :--------: | :------: | :------------: | :---: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [SECFPN](./pv_rcnn_8xb2-80e_kitti-3d-3class.py) | 3 Class | cyclic 80e |   5.4    |                | 72.28 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class/pv_rcnn_8xb2-80e_kitti-3d-3class_20221117_234428-b384d22f.pth) \\ [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class/pv_rcnn_8xb2-80e_kitti-3d-3class_20221117_234428.json) |
+
+Note: mAP represents AP11 results on 3 Class under the moderate setting.
+
+Detailed performance on KITTI 3D detection (3D) is as follows, evaluated by AP11 metric:
+
+|            | Easy  | Moderate | Hard  |
+| ---------- | :---: | :------: | :---: |
+| Car        | 89.20 |  83.72   | 78.79 |
+| Pedestrian | 66.64 |  59.84   | 55.33 |
+| Cyclist    | 87.25 |  73.27   | 69.61 |
+
+## Citation
+
+```latex
+@article{ShaoshuaiShi2020PVRCNNPF,
+  title={PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection},
+  author={Shaoshuai Shi and Chaoxu Guo and Li Jiang and Zhe Wang and Jianping Shi and Xiaogang Wang and Hongsheng Li},
+  journal={computer vision and pattern recognition},
+  year={2020}
+}
+```

configs/pv_rcnn/metafile.yml

@@ -0,0 +1,29 @@
+Collections:
+  - Name: PV-RCNN
+    Metadata:
+      Training Data: KITTI
+      Training Techniques:
+        - AdamW
+      Training Resources: 8x A100 GPUs
+      Architecture:
+        - Feature Pyramid Network
+    Paper:
+      URL: https://arxiv.org/abs/1912.13192
+      Title: 'PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection'
+    README: configs/pv_rcnn/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/mmdet3d/models/detectors/pv_rcnn.py#L12
+      Version: v1.1.0rc2
+
+Models:
+  - Name: pv_rcnn_8xb2-80e_kitti-3d-3class
+    In Collection: PV_RCNN
+    Config: configs/pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class.py
+    Metadata:
+      Training Memory (GB): 5.4
+    Results:
+      - Task: 3D Object Detection
+        Dataset: KITTI
+        Metrics:
+          mAP: 72.28
+    Weights: <https://download.openmmlab.com/mmdetection3d/v1.1.0_models/pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class/pv_rcnn_8xb2-80e_kitti-3d-3class_20221117_234428-b384d22f.pth

mmdet3d/models/layers/pointnet_modules/stack_point_sa_module.py

@@ -57,10 +57,11 @@ def forward(self,
             'new_xyz: str(new_xyz.shape), new_xyz_batch_cnt: ' \
             'str(new_xyz_batch_cnt)'
 
-        # idx: (M1 + M2 ..., nsample), empty_ball_mask: (M1 + M2 ...)
-        idx, empty_ball_mask = ball_query(0, self.radius, self.sample_nums,
-                                          xyz, new_xyz, xyz_batch_cnt,
-                                          new_xyz_batch_cnt)
+        # idx: (M1 + M2 ..., nsample)
+        idx = ball_query(0, self.radius, self.sample_nums, xyz, new_xyz,
+                         xyz_batch_cnt, new_xyz_batch_cnt)
+        empty_ball_mask = (idx[:, 0] == -1)
+        idx[empty_ball_mask] = 0
         grouped_xyz = grouping_operation(
             xyz, idx, xyz_batch_cnt,
             new_xyz_batch_cnt)  # (M1 + M2, 3, nsample)

mmdet3d/models/roi_heads/bbox_heads/pv_rcnn_bbox_head.py

@@ -4,6 +4,8 @@
 import numpy as np
 import torch
 from mmcv.cnn import ConvModule
+from mmdet.models.task_modules.samplers import SamplingResult
+from mmdet.models.utils import multi_apply
 from mmengine.model import BaseModule
 from mmengine.structures import InstanceData
 from torch import nn as nn
@@ -14,8 +16,6 @@
 from mmdet3d.structures.bbox_3d import (LiDARInstance3DBoxes,
                                         rotation_3d_in_axis, xywhr2xyxyr)
 from mmdet3d.utils import InstanceList
-from mmdet.models.task_modules.samplers import SamplingResult
-from mmdet.models.utils import multi_apply
 
 
 @MODELS.register_module()
@@ -440,21 +440,21 @@ def get_results(self,
         # post processing
         result_list = []
         for batch_id in range(batch_size):
-            cls_preds = cls_preds[roi_batch_id == batch_id]
+            cur_cls_preds = cls_preds[roi_batch_id == batch_id]
             box_preds = batch_box_preds[roi_batch_id == batch_id]
             label_preds = class_labels[batch_id]
 
-            cls_preds = cls_preds.sigmoid()
-            cls_preds, _ = torch.max(cls_preds, dim=-1)
+            cur_cls_preds = cur_cls_preds.sigmoid()
+            cur_cls_preds, _ = torch.max(cur_cls_preds, dim=-1)
             selected = self.class_agnostic_nms(
-                scores=cls_preds,
+                scores=cur_cls_preds,
                 bbox_preds=box_preds,
                 input_meta=input_metas[batch_id],
                 nms_cfg=test_cfg)
 
             selected_bboxes = box_preds[selected]
             selected_label_preds = label_preds[selected]
-            selected_scores = cls_preds[selected]
+            selected_scores = cur_cls_preds[selected]
 
             results = InstanceData()
             results.bboxes_3d = input_metas[batch_id]['box_type_3d'](

tests/test_models/test_detectors/test_pvrcnn.py

@@ -17,7 +17,7 @@ def test_pvrcnn(self):
         DefaultScope.get_instance('test_pvrcnn', scope_name='mmdet3d')
         _setup_seed(0)
         pvrcnn_cfg = _get_detector_cfg(
-            'pvrcnn/pvrcnn_8xb2-80e_kitti-3d-3class.py')
+            'pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class.py')
         model = MODELS.build(pvrcnn_cfg)
         num_gt_instance = 2
         packed_inputs = _create_detector_inputs(