update OpenPCDet to v0.5.1 (#706)

* support PointPillar (anchor-based, anchor-free) for WOD datasets * update OpenPCDet to v0.5.1

update OpenPCDet to v0.5.1 (#706)
* support PointPillar (anchor-based, anchor-free) for WOD datasets * update OpenPCDet to v0.5.1
76279ff2 · Shaoshuai Shi · GitHub · 63ffbac9 · 76279ff2 · 76279ff2
Unverified Commit 76279ff2 authored Dec 09, 2021 by Shaoshuai Shi Committed by GitHub Dec 09, 2021
5 changed files
--- a/README.md
+++ b/README.md
@@ -19,6 +19,11 @@ It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/18
 ## Changelog
+[2021-12-09] **NEW:**  Update `OpenPCDet` to v0.5.1:
+* Add PointPillar related baseline configs/results on [Waymo Open Dataset](#waymo-open-dataset-baselines).
+* Support Pandaset dataloader, see the pull request [here](https://github.com/open-mmlab/OpenPCDet/pull/396).
+* Support a set of new augmentations, see the pull request [here](https://github.com/open-mmlab/OpenPCDet/pull/653).
 [2021-12-01] **NEW:** `OpenPCDet` v0.5.0 is released with the following features:
 * Improve the performance of all models on [Waymo Open Dataset](#waymo-open-dataset-baselines). Note that you need to re-prepare the training/validation data and ground-truth database of Waymo Open Dataset (see [GETTING_STARTED.md](docs/GETTING_STARTED.md)). 
 * Support anchor-free [CenterHead](pcdet/models/dense_heads/center_head.py), add configs of `CenterPoint` and `PV-RCNN with CenterHead`.
@@ -129,7 +134,9 @@ By default, all models are trained with **20% data (~32k frames)** of all the tr
 |    Performance@(train with 20\% Data)            | Vec_L1 | Vec_L2 | Ped_L1 | Ped_L2 | Cyc_L1 | Cyc_L2 |  
 |---------------------------------------------|----------:|:-------:|:-------:|:-------:|:-------:|:-------:|
 | [SECOND](tools/cfgs/waymo_models/second.yaml) | 70.96/70.34|62.58/62.02|65.23/54.24	|57.22/47.49|	57.13/55.62 |	54.97/53.53 | 
-| [CenterPoint](tools/cfgs/waymo_models/centerpoint_without_resnet.yaml)| 71.33/70.76|63.16/62.65|	72.09/65.49	|64.27/58.23|	68.68/67.39	|66.11/64.87|
+| [PointPillar](tools/cfgs/waymo_models/pointpillar_1x.yaml) | 70.43/69.83 |	62.18/61.64 | 66.21/46.32|58.18/40.64|55.26/51.75|53.18/49.80 |
+[CenterPoint-Pillar](tools/cfgs/waymo_models/centerpoint_pillar_1x.yaml)| 70.50/69.96|62.18/61.69|73.11/61.97|65.06/55.00|65.44/63.85|62.98/61.46| 
+[CenterPoint](tools/cfgs/waymo_models/centerpoint_without_resnet.yaml)| 71.33/70.76|63.16/62.65|	72.09/65.49	|64.27/58.23|	68.68/67.39	|66.11/64.87|
 | [CenterPoint (ResNet)](tools/cfgs/waymo_models/centerpoint.yaml)|72.76/72.23|64.91/64.42	|74.19/67.96	|66.03/60.34|	71.04/69.79	|68.49/67.28 |
 | [Part-A2-Anchor](tools/cfgs/waymo_models/PartA2.yaml) | 74.66/74.12	|65.82/65.32	|71.71/62.24	|62.46/54.06	|66.53/65.18	|64.05/62.75 |
 | [PV-RCNN (AnchorHead)](tools/cfgs/waymo_models/pv_rcnn.yaml) | 75.41/74.74	|67.44/66.80	|71.98/61.24	|63.70/53.95	|65.88/64.25	|63.39/61.82 | 

--- a/pcdet/models/dense_heads/target_assigner/axis_aligned_target_assigner.py
+++ b/pcdet/models/dense_heads/target_assigner/axis_aligned_target_assigner.py
@@ -141,12 +141,13 @@ class AxisAlignedTargetAssigner(object):
            anchor_by_gt_overlap = iou3d_nms_utils.boxes_iou3d_gpu(anchors[:, 0:7], gt_boxes[:, 0:7]) \
                if self.match_height else box_utils.boxes3d_nearest_bev_iou(anchors[:, 0:7], gt_boxes[:, 0:7])
-            anchor_to_gt_argmax = torch.from_numpy(anchor_by_gt_overlap.cpu().numpy().argmax(axis=1)).cuda()
+            # NOTE: The speed of these two versions depends the environment and the number of anchors
-            anchor_to_gt_max = anchor_by_gt_overlap[
+            # anchor_to_gt_argmax = torch.from_numpy(anchor_by_gt_overlap.cpu().numpy().argmax(axis=1)).cuda()
-                torch.arange(num_anchors, device=anchors.device), anchor_to_gt_argmax
+            anchor_to_gt_argmax = anchor_by_gt_overlap.argmax(dim=1)
-            ]
+            anchor_to_gt_max = anchor_by_gt_overlap[torch.arange(num_anchors, device=anchors.device), anchor_to_gt_argmax]
-            gt_to_anchor_argmax = torch.from_numpy(anchor_by_gt_overlap.cpu().numpy().argmax(axis=0)).cuda()
+            # gt_to_anchor_argmax = torch.from_numpy(anchor_by_gt_overlap.cpu().numpy().argmax(axis=0)).cuda()
+            gt_to_anchor_argmax = anchor_by_gt_overlap.argmax(dim=0)
            gt_to_anchor_max = anchor_by_gt_overlap[gt_to_anchor_argmax, torch.arange(num_gt, device=anchors.device)]
            empty_gt_mask = gt_to_anchor_max == 0
            gt_to_anchor_max[empty_gt_mask] = -1

--- a/setup.py
+++ b/setup.py
@@ -28,7 +28,7 @@ def write_version_to_file(version, target_file):
 if __name__ == '__main__':
-    version = '0.5.0+%s' % get_git_commit_number()
+    version = '0.5.1+%s' % get_git_commit_number()
    write_version_to_file(version, 'pcdet/version.py')
    setup(

--- a/tools/cfgs/waymo_models/centerpoint_pillar_1x.yaml
+++ b/tools/cfgs/waymo_models/centerpoint_pillar_1x.yaml
+CLASS_NAMES: ['Vehicle', 'Pedestrian', 'Cyclist']
+DATA_CONFIG:
+    _BASE_CONFIG_: cfgs/dataset_configs/waymo_dataset.yaml
+    POINT_CLOUD_RANGE: [-74.88, -74.88, -2, 74.88, 74.88, 4.0]
+    DATA_PROCESSOR:
+        -   NAME: mask_points_and_boxes_outside_range
+            REMOVE_OUTSIDE_BOXES: True
+        -   NAME: shuffle_points
+            SHUFFLE_ENABLED: {
+                'train': True,
+                'test': True
+            }
+        -   NAME: transform_points_to_voxels
+            VOXEL_SIZE: [ 0.32, 0.32, 6.0 ]
+            MAX_POINTS_PER_VOXEL: 20
+            MAX_NUMBER_OF_VOXELS: {
+                'train': 150000,
+                'test': 150000
+            }
+MODEL:
+    NAME: CenterPoint
+    VFE:
+        NAME: PillarVFE
+        WITH_DISTANCE: False
+        USE_ABSLOTE_XYZ: True
+        USE_NORM: True
+        NUM_FILTERS: [ 64, 64 ]
+    MAP_TO_BEV:
+        NAME: PointPillarScatter
+        NUM_BEV_FEATURES: 64
+    BACKBONE_2D:
+        NAME: BaseBEVBackbone
+        LAYER_NUMS: [ 3, 5, 5 ]
+        LAYER_STRIDES: [ 1, 2, 2 ]
+        NUM_FILTERS: [ 64, 128, 256 ]
+        UPSAMPLE_STRIDES: [ 1, 2, 4 ]
+        NUM_UPSAMPLE_FILTERS: [ 128, 128, 128 ]
+    DENSE_HEAD:
+        NAME: CenterHead
+        CLASS_AGNOSTIC: False
+        CLASS_NAMES_EACH_HEAD: [
+            ['Vehicle', 'Pedestrian', 'Cyclist']
+        ]
+        SHARED_CONV_CHANNEL: 64
+        USE_BIAS_BEFORE_NORM: True
+        NUM_HM_CONV: 2
+        SEPARATE_HEAD_CFG:
+            HEAD_ORDER: ['center', 'center_z', 'dim', 'rot']
+            HEAD_DICT: {
+                'center': {'out_channels': 2, 'num_conv': 2},
+                'center_z': {'out_channels': 1, 'num_conv': 2},
+                'dim': {'out_channels': 3, 'num_conv': 2},
+                'rot': {'out_channels': 2, 'num_conv': 2},
+            }
+        TARGET_ASSIGNER_CONFIG:
+            FEATURE_MAP_STRIDE: 1
+            NUM_MAX_OBJS: 500
+            GAUSSIAN_OVERLAP: 0.1
+            MIN_RADIUS: 2
+        LOSS_CONFIG:
+            LOSS_WEIGHTS: {
+                'cls_weight': 1.0,
+                'loc_weight': 2.0,
+                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
+            }
+        POST_PROCESSING:
+            SCORE_THRESH: 0.1
+            POST_CENTER_LIMIT_RANGE: [-80, -80, -10.0, 80, 80, 10.0]
+            MAX_OBJ_PER_SAMPLE: 500
+            NMS_CONFIG:
+                NMS_TYPE: nms_gpu
+                NMS_THRESH: 0.7
+                NMS_PRE_MAXSIZE: 4096
+                NMS_POST_MAXSIZE: 500
+    POST_PROCESSING:
+        RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
+        EVAL_METRIC: waymo
+OPTIMIZATION:
+    BATCH_SIZE_PER_GPU: 2
+    NUM_EPOCHS: 30
+    OPTIMIZER: adam_onecycle
+    LR: 0.003
+    WEIGHT_DECAY: 0.01
+    MOMENTUM: 0.9
+    MOMS: [0.95, 0.85]
+    PCT_START: 0.4
+    DIV_FACTOR: 10
+    DECAY_STEP_LIST: [35, 45]
+    LR_DECAY: 0.1
+    LR_CLIP: 0.0000001
+    LR_WARMUP: False
+    WARMUP_EPOCH: 1
+    GRAD_NORM_CLIP: 10
--- a/tools/cfgs/waymo_models/pointpillar_1x.yaml
+++ b/tools/cfgs/waymo_models/pointpillar_1x.yaml
+CLASS_NAMES: ['Vehicle', 'Pedestrian', 'Cyclist']
+DATA_CONFIG:
+    _BASE_CONFIG_: cfgs/dataset_configs/waymo_dataset.yaml
+    POINT_CLOUD_RANGE: [-74.88, -74.88, -2, 74.88, 74.88, 4.0]
+    DATA_PROCESSOR:
+        -   NAME: mask_points_and_boxes_outside_range
+            REMOVE_OUTSIDE_BOXES: True
+        -   NAME: shuffle_points
+            SHUFFLE_ENABLED: {
+                'train': True,
+                'test': True
+            }
+        -   NAME: transform_points_to_voxels
+            VOXEL_SIZE: [ 0.32, 0.32, 6.0 ]
+            MAX_POINTS_PER_VOXEL: 20
+            MAX_NUMBER_OF_VOXELS: {
+                'train': 150000,
+                'test': 150000
+            }
+MODEL:
+    NAME: PointPillar
+    VFE:
+        NAME: PillarVFE
+        WITH_DISTANCE: False
+        USE_ABSLOTE_XYZ: True
+        USE_NORM: True
+        NUM_FILTERS: [ 64, 64 ]
+    MAP_TO_BEV:
+        NAME: PointPillarScatter
+        NUM_BEV_FEATURES: 64
+    BACKBONE_2D:
+        NAME: BaseBEVBackbone
+        LAYER_NUMS: [ 3, 5, 5 ]
+        LAYER_STRIDES: [ 1, 2, 2 ]
+        NUM_FILTERS: [ 64, 128, 256 ]
+        UPSAMPLE_STRIDES: [ 1, 2, 4 ]
+        NUM_UPSAMPLE_FILTERS: [ 128, 128, 128 ]
+    DENSE_HEAD:
+        NAME: AnchorHeadSingle
+        CLASS_AGNOSTIC: False
+        USE_DIRECTION_CLASSIFIER: True
+        DIR_OFFSET: 0.78539
+        DIR_LIMIT_OFFSET: 0.0
+        NUM_DIR_BINS: 2
+        ANCHOR_GENERATOR_CONFIG: [
+            {
+                'class_name': 'Vehicle',
+                'anchor_sizes': [ [ 4.7, 2.1, 1.7 ] ],
+                'anchor_rotations': [ 0, 1.57 ],
+                'anchor_bottom_heights': [ 0 ],
+                'align_center': False,
+                'feature_map_stride': 1,
+                'matched_threshold': 0.55,
+                'unmatched_threshold': 0.4
+            },
+            {
+                'class_name': 'Pedestrian',
+                'anchor_sizes': [ [ 0.91, 0.86, 1.73 ] ],
+                'anchor_rotations': [ 0, 1.57 ],
+                'anchor_bottom_heights': [ 0 ],
+                'align_center': False,
+                'feature_map_stride': 1,
+                'matched_threshold': 0.5,
+                'unmatched_threshold': 0.35
+            },
+            {
+                'class_name': 'Cyclist',
+                'anchor_sizes': [ [ 1.78, 0.84, 1.78 ] ],
+                'anchor_rotations': [ 0, 1.57 ],
+                'anchor_bottom_heights': [ 0 ],
+                'align_center': False,
+                'feature_map_stride': 1,
+                'matched_threshold': 0.5,
+                'unmatched_threshold': 0.35
+            }
+        ]
+        TARGET_ASSIGNER_CONFIG:
+            NAME: AxisAlignedTargetAssigner
+            POS_FRACTION: -1.0
+            SAMPLE_SIZE: 512
+            NORM_BY_NUM_EXAMPLES: False
+            MATCH_HEIGHT: False
+            BOX_CODER: ResidualCoder
+        LOSS_CONFIG:
+            LOSS_WEIGHTS: {
+                'cls_weight': 1.0,
+                'loc_weight': 2.0,
+                'dir_weight': 0.2,
+                'code_weights': [ 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ]
+            }
+    POST_PROCESSING:
+        RECALL_THRESH_LIST: [ 0.3, 0.5, 0.7 ]
+        SCORE_THRESH: 0.1
+        OUTPUT_RAW_SCORE: False
+        EVAL_METRIC: waymo
+        NMS_CONFIG:
+            MULTI_CLASSES_NMS: False
+            NMS_TYPE: nms_gpu
+            NMS_THRESH: 0.7
+            NMS_PRE_MAXSIZE: 4096
+            NMS_POST_MAXSIZE: 500
+OPTIMIZATION:
+    BATCH_SIZE_PER_GPU: 2
+    NUM_EPOCHS: 30
+    OPTIMIZER: adam_onecycle
+    LR: 0.003
+    WEIGHT_DECAY: 0.01
+    MOMENTUM: 0.9
+    MOMS: [0.95, 0.85]
+    PCT_START: 0.4
+    DIV_FACTOR: 10
+    DECAY_STEP_LIST: [35, 45]
+    LR_DECAY: 0.1
+    LR_CLIP: 0.0000001
+    LR_WARMUP: False
+    WARMUP_EPOCH: 1
+    GRAD_NORM_CLIP: 10