[Fix] Fix #460 and simplify configs

configs/3dssd/3dssd_kitti-3d-car.py

@@ -108,7 +108,7 @@
 optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
 lr_config = dict(policy='step', warmup=None, step=[80, 120])
 # runtime settings
-runner = dict(max_epochs=150)
+runner = dict(type='EpochBasedRunner', max_epochs=150)
 
 # yapf:disable
 log_config = dict(

configs/_base_/models/3dssd.py

@@ -75,13 +75,3 @@
  score_thr=0.0,
  per_class_proposal=True,
  max_output_num=100))
-
-# optimizer
-# This schedule is mainly used by models on indoor dataset,
-# e.g., VoteNet on SUNRGBD and ScanNet
-lr = 0.002 # max learning rate
-optimizer = dict(type='AdamW', lr=lr, weight_decay=0)
-optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
-lr_config = dict(policy='step', warmup=None, step=[80, 120])
-# runtime settings
-runner = dict(max_epochs=150)

configs/_base_/models/hv_pointpillars_secfpn_kitti.py

@@ -1,11 +1,13 @@
 voxel_size = [0.16, 0.16, 4]
+
 model = dict(
  type='VoxelNet',
  voxel_layer=dict(
- max_num_points=32,
+ max_num_points=32, # max_points_per_voxel
  point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1],
  voxel_size=voxel_size,
- max_voxels=(16000, 40000)),
+ max_voxels=(16000, 40000) # (training, testing) max_voxels
+ ),
  voxel_encoder=dict(
  type='PillarFeatureNet',
  in_channels=4,

configs/_base_/models/hv_second_secfpn_kitti.py

@@ -1,9 +1,11 @@
+voxel_size = [0.05, 0.05, 0.1]
+
 model = dict(
  type='VoxelNet',
  voxel_layer=dict(
  max_num_points=5,
  point_cloud_range=[0, -40, -3, 70.4, 40, 1],
- voxel_size=[0.05, 0.05, 0.1],
+ voxel_size=voxel_size,
  max_voxels=(16000, 40000)),
  voxel_encoder=dict(type='HardSimpleVFE'),
  middle_encoder=dict(

configs/_base_/models/parta2.py

@@ -0,0 +1,201 @@
+# model settings
+voxel_size = [0.05, 0.05, 0.1]
+point_cloud_range = [0, -40, -3, 70.4, 40, 1]
+
+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_voxels
+ ),
+ 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=0.1)))

configs/_base_/schedules/cosine.py

@@ -0,0 +1,20 @@
+# This schedule is mainly used by models with dynamic voxelization
+# optimizer
+lr = 0.003 # max learning rate
+optimizer = dict(
+ type='AdamW',
+ lr=lr,
+ betas=(0.95, 0.99), # the momentum is change during training
+ weight_decay=0.001)
+optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
+
+lr_config = dict(
+ policy='CosineAnnealing',
+ warmup='linear',
+ warmup_iters=1000,
+ warmup_ratio=1.0 / 10,
+ min_lr_ratio=1e-5)
+
+momentum_config = None
+
+runner = dict(type='EpochBasedRunner', max_epochs=40)

configs/benchmark/hv_PartA2_secfpn_4x8_cyclic_80e_pcdet_kitti-3d-3class.py

@@ -322,7 +322,7 @@
  ])
 # yapf:enable
 # runtime settings
-runner = dict(max_epochs=80)
+runner = dict(type='EpochBasedRunner', max_epochs=80)
 dist_params = dict(backend='nccl', port=29506)
 log_level = 'INFO'
 find_unused_parameters = True

configs/benchmark/hv_pointpillars_secfpn_3x8_100e_det3d_kitti-3d-car.py

@@ -192,7 +192,7 @@
  ])
 # yapf:enable
 # runtime settings
-runner = dict(max_epochs=50)
+runner = dict(type='EpochBasedRunner', max_epochs=50)
 dist_params = dict(backend='nccl')
 log_level = 'INFO'
 work_dir = './work_dirs/pp_secfpn_100e'

configs/benchmark/hv_pointpillars_secfpn_4x8_80e_pcdet_kitti-3d-3class.py

@@ -235,7 +235,7 @@
  ])
 # yapf:enable
 # runtime settings
-runner = dict(max_epochs=80)
+runner = dict(type='EpochBasedRunner', max_epochs=80)
 dist_params = dict(backend='nccl')
 log_level = 'INFO'
 work_dir = './work_dirs/pp_secfpn_80e'

configs/benchmark/hv_second_secfpn_4x8_80e_pcdet_kitti-3d-3class.py

@@ -242,7 +242,7 @@
  ])
 # yapf:enable
 # runtime settings
-runner = dict(max_epochs=80)
+runner = dict(type='EpochBasedRunner', max_epochs=80)
 dist_params = dict(backend='nccl')
 log_level = 'INFO'
 work_dir = './work_dirs/sec_secfpn_80e'

configs/dynamic_voxelization/dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py

@@ -1,4 +1,8 @@
-_base_ = '../second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py'
+_base_ = [
+ '../_base_/models/hv_second_secfpn_kitti.py',
+ '../_base_/datasets/kitti-3d-3class.py', '../_base_/schedules/cosine.py',
+ '../_base_/default_runtime.py'
+]
 
 point_cloud_range = [0, -40, -3, 70.4, 40, 1]
 voxel_size = [0.05, 0.05, 0.1]
@@ -16,20 +20,3 @@
  type='DynamicSimpleVFE',
  voxel_size=voxel_size,
  point_cloud_range=point_cloud_range))
-
-# optimizer
-lr = 0.003 # max learning rate
-optimizer = dict(
- _delete_=True,
- type='AdamW',
- lr=lr,
- betas=(0.95, 0.99), # the momentum is change during training
- weight_decay=0.001)
-lr_config = dict(
- _delete_=True,
- policy='CosineAnnealing',
- warmup='linear',
- warmup_iters=1000,
- warmup_ratio=1.0 / 10,
- min_lr_ratio=1e-5)
-momentum_config = None

configs/h3dnet/h3dnet_3x8_scannet-3d-18class.py

@@ -59,12 +59,6 @@
 
 data = dict(samples_per_gpu=3, workers_per_gpu=2)
 
-# optimizer
 # yapf:disable
-log_config = dict(
- interval=30,
- hooks=[
- dict(type='TextLoggerHook'),
- dict(type='TensorboardLoggerHook')
- ])
+log_config = dict(interval=30)
 # yapf:enable

configs/imvotenet/imvotenet_faster_rcnn_r50_fpn_2x4_sunrgbd-3d-10class.py

@@ -53,6 +53,6 @@
  warmup_iters=500,
  warmup_ratio=0.001,
  step=[6])
-runner = dict(max_epochs=8)
+runner = dict(type='EpochBasedRunner', max_epochs=8)
 
 load_from = 'http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth' # noqa