Merge branch 'PCDet_configs' into 'master'

PCDet configs

See merge request open-mmlab/mmdet.3d!80

configs/benchmark/hv_PartA2_secfpn_2x8_cyclic_80e_pcdet_kitti-3d-3class.py

+# model settings
+voxel_size = [0.05, 0.05, 0.1]
+point_cloud_range = [0, -40, -3, 70.4, 40, 1]  # velodyne coordinates, x, y, z
+
+model = dict(
+    type='PartA2',
+    voxel_layer=dict(
+        max_num_points=5,  # max_points_per_voxel
+        point_cloud_range=point_cloud_range,
+        voxel_size=voxel_size,
+        max_voxels=(16000, 40000)  # (training, testing) max_coxels
+    ),
+    voxel_encoder=dict(type='HardSimpleVFE'),
+    middle_encoder=dict(
+        type='SparseUNet',
+        in_channels=4,
+        sparse_shape=[41, 1600, 1408],
+        order=('conv', 'norm', 'act')),
+    backbone=dict(
+        type='SECOND',
+        in_channels=256,
+        layer_nums=[5, 5],
+        layer_strides=[1, 2],
+        out_channels=[128, 256]),
+    neck=dict(
+        type='SECONDFPN',
+        in_channels=[128, 256],
+        upsample_strides=[1, 2],
+        out_channels=[256, 256]),
+    rpn_head=dict(
+        type='PartA2RPNHead',
+        num_classes=3,
+        in_channels=512,
+        feat_channels=512,
+        use_direction_classifier=True,
+        anchor_generator=dict(
+            type='Anchor3DRangeGenerator',
+            ranges=[[0, -40.0, -0.6, 70.4, 40.0, -0.6],
+                    [0, -40.0, -0.6, 70.4, 40.0, -0.6],
+                    [0, -40.0, -1.78, 70.4, 40.0, -1.78]],
+            sizes=[[0.6, 0.8, 1.73], [0.6, 1.76, 1.73], [1.6, 3.9, 1.56]],
+            rotations=[0, 1.57],
+            reshape_out=False),
+        diff_rad_by_sin=True,
+        assigner_per_size=True,
+        assign_per_class=True,
+        bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
+        loss_dir=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)),
+    roi_head=dict(
+        type='PartAggregationROIHead',
+        num_classes=3,
+        semantic_head=dict(
+            type='PointwiseSemanticHead',
+            in_channels=16,
+            extra_width=0.2,
+            seg_score_thr=0.3,
+            num_classes=3,
+            loss_seg=dict(
+                type='FocalLoss',
+                use_sigmoid=True,
+                reduction='sum',
+                gamma=2.0,
+                alpha=0.25,
+                loss_weight=1.0),
+            loss_part=dict(
+                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
+        seg_roi_extractor=dict(
+            type='Single3DRoIAwareExtractor',
+            roi_layer=dict(
+                type='RoIAwarePool3d',
+                out_size=14,
+                max_pts_per_voxel=128,
+                mode='max')),
+        part_roi_extractor=dict(
+            type='Single3DRoIAwareExtractor',
+            roi_layer=dict(
+                type='RoIAwarePool3d',
+                out_size=14,
+                max_pts_per_voxel=128,
+                mode='avg')),
+        bbox_head=dict(
+            type='PartA2BboxHead',
+            num_classes=3,
+            seg_in_channels=16,
+            part_in_channels=4,
+            seg_conv_channels=[64, 64],
+            part_conv_channels=[64, 64],
+            merge_conv_channels=[128, 128],
+            down_conv_channels=[128, 256],
+            bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
+            shared_fc_channels=[256, 512, 512, 512],
+            cls_channels=[256, 256],
+            reg_channels=[256, 256],
+            dropout_ratio=0.1,
+            roi_feat_size=14,
+            with_corner_loss=True,
+            loss_bbox=dict(
+                type='SmoothL1Loss',
+                beta=1.0 / 9.0,
+                reduction='sum',
+                loss_weight=1.0),
+            loss_cls=dict(
+                type='CrossEntropyLoss',
+                use_sigmoid=True,
+                reduction='sum',
+                loss_weight=1.0))))
+# model training and testing settings
+train_cfg = dict(
+    rpn=dict(
+        assigner=[
+            dict(  # for Pedestrian
+                type='MaxIoUAssigner',
+                iou_calculator=dict(type='BboxOverlapsNearest3D'),
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.35,
+                min_pos_iou=0.35,
+                ignore_iof_thr=-1),
+            dict(  # for Cyclist
+                type='MaxIoUAssigner',
+                iou_calculator=dict(type='BboxOverlapsNearest3D'),
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.35,
+                min_pos_iou=0.35,
+                ignore_iof_thr=-1),
+            dict(  # for Car
+                type='MaxIoUAssigner',
+                iou_calculator=dict(type='BboxOverlapsNearest3D'),
+                pos_iou_thr=0.6,
+                neg_iou_thr=0.45,
+                min_pos_iou=0.45,
+                ignore_iof_thr=-1)
+        ],
+        allowed_border=0,
+        pos_weight=-1,
+        debug=False),
+    rpn_proposal=dict(
+        nms_pre=9000,
+        nms_post=512,
+        max_num=512,
+        nms_thr=0.8,
+        score_thr=0,
+        use_rotate_nms=False),
+    rcnn=dict(
+        assigner=[
+            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),
+            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),
+            dict(  # for Car
+                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)
+        ],
+        sampler=dict(
+            type='IoUNegPiecewiseSampler',
+            num=128,
+            pos_fraction=0.55,
+            neg_piece_fractions=[0.8, 0.2],
+            neg_iou_piece_thrs=[0.55, 0.1],
+            neg_pos_ub=-1,
+            add_gt_as_proposals=False,
+            return_iou=True),
+        cls_pos_thr=0.75,
+        cls_neg_thr=0.25))
+test_cfg = dict(
+    rpn=dict(
+        nms_pre=1024,
+        nms_post=100,
+        max_num=100,
+        nms_thr=0.7,
+        score_thr=0,
+        use_rotate_nms=True),
+    rcnn=dict(
+        use_rotate_nms=True, use_raw_score=True, nms_thr=0.01, score_thr=0.3))
+
+# dataset settings
+dataset_type = 'KittiDataset'
+data_root = 'data/kitti/'
+class_names = ['Pedestrian', 'Cyclist', 'Car']
+input_modality = dict(use_lidar=True, use_camera=False)
+db_sampler = dict(
+    data_root=data_root,
+    info_path=data_root + 'kitti_dbinfos_train.pkl',
+    rate=1.0,
+    object_rot_range=[0.0, 0.0],
+    prepare=dict(
+        filter_by_difficulty=[-1],
+        filter_by_min_points=dict(Car=5, Pedestrian=5, Cyclist=5)),
+    classes=class_names,
+    sample_groups=dict(Car=15, Pedestrian=10, Cyclist=10))
+train_pipeline = [
+    dict(type='LoadPointsFromFile', 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=[1.0, 1.0, 0.5],
+        global_rot_range=[0.0, 0.0],
+        rot_range=[-0.78539816, 0.78539816]),
+    dict(type='RandomFlip3D', flip_ratio=0.5),
+    dict(
+        type='GlobalRotScaleTrans',
+        rot_range=[-0.78539816, 0.78539816],
+        scale_ratio_range=[0.95, 1.05]),
+    dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectNameFilter', classes=class_names),
+    dict(type='PointShuffle'),
+    dict(type='DefaultFormatBundle3D', class_names=class_names),
+    dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+test_pipeline = [
+    dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
+    dict(
+        type='MultiScaleFlipAug3D',
+        img_scale=(1333, 800),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            dict(
+                type='GlobalRotScaleTrans',
+                rot_range=[0, 0],
+                scale_ratio_range=[1., 1.],
+                translation_std=[0, 0, 0]),
+            dict(type='RandomFlip3D'),
+            dict(
+                type='PointsRangeFilter', point_cloud_range=point_cloud_range),
+            dict(
+                type='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='Collect3D', keys=['points'])
+        ])
+]
+
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(
+        type='RepeatDataset',
+        times=2,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file=data_root + 'kitti_infos_train.pkl',
+            split='training',
+            pts_prefix='velodyne_reduced',
+            pipeline=train_pipeline,
+            modality=input_modality,
+            classes=class_names,
+            test_mode=False)),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'kitti_infos_val.pkl',
+        split='training',
+        pts_prefix='velodyne_reduced',
+        pipeline=test_pipeline,
+        modality=input_modality,
+        classes=class_names,
+        test_mode=True),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'kitti_infos_val.pkl',
+        split='training',
+        pts_prefix='velodyne_reduced',
+        pipeline=test_pipeline,
+        modality=input_modality,
+        classes=class_names,
+        test_mode=True))
+# optimizer
+lr = 0.001  # max learning rate
+optimizer = dict(type='AdamW', lr=lr, betas=(0.95, 0.99), weight_decay=0.01)
+optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
+lr_config = dict(
+    policy='cyclic',
+    target_ratio=(10, 1e-4),
+    cyclic_times=1,
+    step_ratio_up=0.4)
+momentum_config = dict(
+    policy='cyclic',
+    target_ratio=(0.85 / 0.95, 1),
+    cyclic_times=1,
+    step_ratio_up=0.4)
+checkpoint_config = dict(interval=1)
+evaluation = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 40
+dist_params = dict(backend='nccl', port=29506)
+log_level = 'INFO'
+find_unused_parameters = True
+work_dir = './work_dirs/parta2_secfpn_80e'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]