Rewrite world translation augmentation, and re-implement CenterPoint with voxel_size=0.075 (#795)

* add cbgs_dyn_pp_centerpoint.yaml

* add cbgs_voxel01_res3d_centerpoint.yaml

* add support of centerpoint on Nuscenes in README

* add translation augmentation, re-implement the performance of CenterPoints with 0.075m voxels

* cover the original world translation augmentation

* modify random_translation_along_X

README.md

@@ -21,7 +21,8 @@ It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/18
 
 
 ## Changelog
-[2022-02-07] Added support for centerpoint models on Nuscenes Dataset.
+
+[2022-02-07] Added support for Centerpoint models on Nuscenes Dataset.
 
 [2022-01-14] Added support for dynamic pillar voxelization, following the implementation proposed in [H^23D R-CNN](https://arxiv.org/abs/2107.14391) with unique operation and [`torch_scatter`](https://github.com/rusty1s/pytorch_scatter) package.
 
@@ -183,7 +184,8 @@ All models are trained with 8 GTX 1080Ti GPUs and are available for download.
 | [PointPillar-MultiHead](tools/cfgs/nuscenes_models/cbgs_pp_multihead.yaml) | 33.87	| 26.00 | 32.07	| 28.74 | 20.15 | 44.63 | 58.23	 | [model-23M](https://drive.google.com/file/d/1p-501mTWsq0G9RzroTWSXreIMyTUUpBM/view?usp=sharing) | 
 | [SECOND-MultiHead (CBGS)](tools/cfgs/nuscenes_models/cbgs_second_multihead.yaml) | 31.15 |	25.51 |	26.64 | 26.26 | 20.46 | 50.59 | 62.29 | [model-35M](https://drive.google.com/file/d/1bNzcOnE3u9iooBFMk2xK7HqhdeQ_nwTq/view?usp=sharing) |
 | [CenterPoint-PointPillar](tools/cfgs/nuscenes_models/cbgs_dyn_pp_centerpoint.yaml) | 31.13 |	26.04 |	42.92 | 23.90 | 19.14 | 50.03 | 60.70 | [model-23M](https://drive.google.com/file/d/1UvGm6mROMyJzeSRu7OD1leU_YWoAZG7v/view?usp=sharing) |
-| [CenterPoint (voxel_size=0.1)](tools/cfgs/nuscenes_models/cbgs_dyn_pp_centerpoint.yaml) | 30.11 |	25.55 |	38.28 | 21.94 | 18.87 | 56.03 | 64.54 | [model-34M](https://drive.google.com/file/d/1Cz-J1c3dw7JAWc25KRG1XQj8yCaOlexQ/view?usp=sharing) |
+| [CenterPoint (voxel_size=0.1)](tools/cfgs/nuscenes_models/cbgs_voxel01_res3d_centerpoint.yaml) | 30.11 |	25.55 |	38.28 | 21.94 | 18.87 | 56.03 | 64.54 | [model-34M](https://drive.google.com/file/d/1Cz-J1c3dw7JAWc25KRG1XQj8yCaOlexQ/view?usp=sharing) |
+| [CenterPoint (voxel_size=0.075)](tools/cfgs/nuscenes_models/cbgs_voxel0075_res3d_centerpoint.yaml) | 28.80 |	25.43 |	37.27 | 21.55 | 18.24 | 59.22 | 66.48 | [model-34M](https://drive.google.com/file/d/1XOHAWm1MPkCKr1gqmc3TWi5AYZgPsgxU/view?usp=sharing) |
 
 
 ### Other datasets

pcdet/datasets/augmentor/augmentor_utils.py

@@ -121,15 +121,15 @@ def random_image_flip_horizontal(image, depth_map, gt_boxes, calib):
     return aug_image, aug_depth_map, aug_gt_boxes
 
 
-def random_translation_along_x(gt_boxes, points, offset_range):
+def random_translation_along_x(gt_boxes, points, offset_std):
     """
     Args:
         gt_boxes: (N, 7), [x, y, z, dx, dy, dz, heading, [vx], [vy]]
         points: (M, 3 + C),
-        offset_range: [min max]]
+        offset_std: float
     Returns:
     """
-    offset = np.random.uniform(offset_range[0], offset_range[1])
+    offset = np.random.normal(0, offset_std, 1)
 
     points[:, 0] += offset
     gt_boxes[:, 0] += offset
@@ -140,15 +140,15 @@ def random_translation_along_x(gt_boxes, points, offset_range):
     return gt_boxes, points
 
 
-def random_translation_along_y(gt_boxes, points, offset_range):
+def random_translation_along_y(gt_boxes, points, offset_std):
     """
     Args:
         gt_boxes: (N, 7), [x, y, z, dx, dy, dz, heading, [vx], [vy]]
         points: (M, 3 + C),
-        offset_range: [min max]]
+        offset_std: float
     Returns:
     """
-    offset = np.random.uniform(offset_range[0], offset_range[1])
+    offset = np.random.normal(0, offset_std, 1)
 
     points[:, 1] += offset
     gt_boxes[:, 1] += offset
@@ -159,15 +159,15 @@ def random_translation_along_y(gt_boxes, points, offset_range):
     return gt_boxes, points
 
 
-def random_translation_along_z(gt_boxes, points, offset_range):
+def random_translation_along_z(gt_boxes, points, offset_std):
     """
     Args:
         gt_boxes: (N, 7), [x, y, z, dx, dy, dz, heading, [vx], [vy]]
         points: (M, 3 + C),
-        offset_range: [min max]]
+        offset_std: float
     Returns:
     """
-    offset = np.random.uniform(offset_range[0], offset_range[1])
+    offset = np.random.normal(0, offset_std, 1)
     
     points[:, 2] += offset
     gt_boxes[:, 2] += offset

pcdet/datasets/augmentor/data_augmentor.py

@@ -99,17 +99,16 @@ class DataAugmentor(object):
         return data_dict
     
     def random_world_translation(self, data_dict=None, config=None):
-        """
-        Please check the correctness of it before using.
-        """
         if data_dict is None:
-            return partial(self.random_world_translation, config=config)
-        offset_range = config['WORLD_TRANSLATION_RANGE']
+            return partial(self.random_world_translation_v2, config=config)
+        noise_translate_std = config['NOISE_TRANSLATE_STD']
+        if noise_translate_std == 0:
+            return data_dict
         gt_boxes, points = data_dict['gt_boxes'], data_dict['points']
         for cur_axis in config['ALONG_AXIS_LIST']:
             assert cur_axis in ['x', 'y', 'z']
             gt_boxes, points = getattr(augmentor_utils, 'random_translation_along_%s' % cur_axis)(
-                gt_boxes, points, offset_range,
+                gt_boxes, points, noise_translate_std,
             )
 
         data_dict['gt_boxes'] = gt_boxes

tools/cfgs/nuscenes_models/cbgs_voxel0075_res3d_centerpoint.yaml

+CLASS_NAMES: ['car','truck', 'construction_vehicle', 'bus', 'trailer',
+              'barrier', 'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone']
+
+DATA_CONFIG:
+    _BASE_CONFIG_: cfgs/dataset_configs/nuscenes_dataset.yaml
+    POINT_CLOUD_RANGE: [-54.0, -54.0, -5.0, 54.0, 54.0, 3.0]
+
+    DATA_AUGMENTOR:
+        DISABLE_AUG_LIST: ['placeholder']
+        AUG_CONFIG_LIST:
+            - NAME: gt_sampling
+              DB_INFO_PATH:
+                - nuscenes_dbinfos_10sweeps_withvelo.pkl
+              PREPARE: {
+                filter_by_min_points: [
+                    'car:5','truck:5', 'construction_vehicle:5', 'bus:5', 'trailer:5',
+                    'barrier:5', 'motorcycle:5', 'bicycle:5', 'pedestrian:5', 'traffic_cone:5'
+                ],
+              }
+
+              SAMPLE_GROUPS: [
+                'car:2','truck:3', 'construction_vehicle:7', 'bus:4', 'trailer:6',
+                'barrier:2', 'motorcycle:6', 'bicycle:6', 'pedestrian:2', 'traffic_cone:2'
+              ]
+
+              NUM_POINT_FEATURES: 5
+              DATABASE_WITH_FAKELIDAR: False
+              REMOVE_EXTRA_WIDTH: [0.0, 0.0, 0.0]
+              LIMIT_WHOLE_SCENE: True
+
+            - NAME: random_world_flip
+              ALONG_AXIS_LIST: ['x', 'y']
+
+            - NAME: random_world_rotation
+              WORLD_ROT_ANGLE: [-0.78539816, 0.78539816]
+
+            - NAME: random_world_scaling
+              WORLD_SCALE_RANGE: [0.9, 1.1]
+            
+            - NAME: random_world_translation
+              NOISE_TRANSLATE_STD: 0.5
+              ALONG_AXIS_LIST: ['x', 'y', 'z']
+
+
+    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: [0.075, 0.075, 0.2]
+          MAX_POINTS_PER_VOXEL: 10
+          MAX_NUMBER_OF_VOXELS: {
+            'train': 120000,
+            'test': 160000
+          }
+
+
+MODEL:
+    NAME: CenterPoint
+
+    VFE:
+        NAME: MeanVFE
+
+    BACKBONE_3D:
+        NAME: VoxelResBackBone8x
+
+    MAP_TO_BEV:
+        NAME: HeightCompression
+        NUM_BEV_FEATURES: 256
+
+    BACKBONE_2D:
+        NAME: BaseBEVBackbone
+
+        LAYER_NUMS: [5, 5]
+        LAYER_STRIDES: [1, 2]
+        NUM_FILTERS: [128, 256]
+        UPSAMPLE_STRIDES: [1, 2]
+        NUM_UPSAMPLE_FILTERS: [256, 256]
+
+    DENSE_HEAD:
+        NAME: CenterHead
+        CLASS_AGNOSTIC: False
+
+        CLASS_NAMES_EACH_HEAD: [
+            ['car'], 
+            ['truck', 'construction_vehicle'],
+            ['bus', 'trailer'],
+            ['barrier'],
+            ['motorcycle', 'bicycle'],
+            ['pedestrian', 'traffic_cone'],
+        ]
+
+        SHARED_CONV_CHANNEL: 64
+        USE_BIAS_BEFORE_NORM: True
+        NUM_HM_CONV: 2
+        SEPARATE_HEAD_CFG:
+            HEAD_ORDER: ['center', 'center_z', 'dim', 'rot', 'vel']
+            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},
+                'vel': {'out_channels': 2, 'num_conv': 2},
+            }
+
+        TARGET_ASSIGNER_CONFIG:
+            FEATURE_MAP_STRIDE: 8
+            NUM_MAX_OBJS: 500
+            GAUSSIAN_OVERLAP: 0.1
+            MIN_RADIUS: 2
+
+        LOSS_CONFIG:
+            LOSS_WEIGHTS: {
+                'cls_weight': 1.0,
+                'loc_weight': 0.25,
+                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2, 1.0, 1.0]
+            }
+
+        POST_PROCESSING:
+            SCORE_THRESH: 0.1
+            POST_CENTER_LIMIT_RANGE: [-61.2, -61.2, -10.0, 61.2, 61.2, 10.0]
+            MAX_OBJ_PER_SAMPLE: 500
+            NMS_CONFIG:
+                NMS_TYPE: nms_gpu
+                NMS_THRESH: 0.2
+                NMS_PRE_MAXSIZE: 1000
+                NMS_POST_MAXSIZE: 83
+
+    POST_PROCESSING:
+        RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
+
+        EVAL_METRIC: kitti
+
+
+
+OPTIMIZATION:
+    BATCH_SIZE_PER_GPU: 4
+    NUM_EPOCHS: 20
+
+    OPTIMIZER: adam_onecycle
+    LR: 0.001
+    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