| _dim_ = 256 |
| _ffn_dim_ = 512 |
| _num_levels_ = 1 |
| _pos_dim_ = 128 |
| auto_scale_lr = dict(base_batch_size=16, enable=False) |
| bev_h_ = 50 |
| bev_w_ = 50 |
| by_epoch = False |
| class_names = [ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ] |
| custom_hooks = [ |
| dict( |
| by_epoch=False, |
| clean_local=False, |
| interval=250, |
| repo_id='5421Project', |
| type='CheckpointUploader'), |
| dict(repo_id='5421Project', resume_type='last', type='CheckpointResumer'), |
| ] |
| data = dict( |
| nonshuffler_sampler=dict(type='DistributedSampler'), |
| samples_per_gpu=1, |
| shuffler_sampler=dict(type='DistributedGroupSampler'), |
| test=dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_val.pkl', |
| bev_size=( |
| 50, |
| 50, |
| ), |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| data_root='data/nuscenes/v1.0-mini/', |
| frame=[ |
| -3, |
| -2, |
| -1, |
| ], |
| modality=dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False), |
| pipeline=[ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict( |
| flip=False, |
| img_scale=( |
| 800, |
| 450, |
| ), |
| pts_scale_ratio=[ |
| 1.0, |
| ], |
| transforms=[ |
| dict( |
| scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict(keys=[ |
| 'img', |
| ], type='CustomCollect3D'), |
| ], |
| type='MultiScaleFlipAug3D'), |
| ], |
| test_mode=True, |
| type='CustomNuScenesDataset'), |
| train=dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_train.pkl', |
| bev_size=( |
| 50, |
| 50, |
| ), |
| box_type_3d='LiDAR', |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| data_root='data/nuscenes/v1.0-mini/', |
| modality=dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False), |
| pipeline=[ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict( |
| type='LoadAnnotations3D', |
| with_bbox_3d=True, |
| with_label_3d=True), |
| dict( |
| point_cloud_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| type='ObjectRangeFilter'), |
| dict( |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='ObjectNameFilter'), |
| dict(type='PhotoMetricDistortionMultiViewImage'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict(scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict( |
| keys=[ |
| 'gt_bboxes_3d', |
| 'gt_labels_3d', |
| 'img', |
| ], |
| type='CustomCollect3D'), |
| dict(type='TypeConverter'), |
| ], |
| queue_length=4, |
| test_mode=False, |
| type='CustomNuScenesDataset', |
| use_valid_flag=True), |
| val=dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_val.pkl', |
| bev_size=( |
| 50, |
| 50, |
| ), |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| data_root='data/nuscenes/v1.0-mini/', |
| frame=(), |
| frames=[ |
| -3, |
| -2, |
| -1, |
| ], |
| modality=dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False), |
| pipeline=[ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict( |
| flip=False, |
| img_scale=( |
| 800, |
| 450, |
| ), |
| pts_scale_ratio=[ |
| 1.0, |
| ], |
| transforms=[ |
| dict( |
| scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict(keys=[ |
| 'img', |
| ], type='CustomCollect3D'), |
| ], |
| type='MultiScaleFlipAug3D'), |
| ], |
| samples_per_gpu=1, |
| test_mode=True, |
| type='CustomNuScenesDataset'), |
| workers_per_gpu=4) |
| data_root = 'data/nuscenes/v1.0-mini/' |
| dataset_type = 'CustomNuScenesDataset' |
| decoder = dict( |
| num_layers=6, |
| return_intermediate=True, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict( |
| dropout=0.1, |
| embed_dims=256, |
| num_heads=8, |
| type='MultiheadAttention'), |
| dict( |
| embed_dims=256, |
| num_levels=1, |
| type='CustomMSDeformableAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, ffn_drop=0.1, num_fcs=2, type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='DetrTransformerDecoderLayer'), |
| type='DetectionTransformerDecoder') |
| default_hooks = dict( |
| checkpoint=dict( |
| by_epoch=False, |
| interval=250, |
| max_keep_ckpts=1, |
| save_best=[ |
| 'loss', |
| 'mAP', |
| 'NDS', |
| ], |
| type='CheckpointHookV2'), |
| logger=dict( |
| interval=50, |
| interval_exp_name=1000, |
| log_metric_by_epoch=False, |
| type='LoggerHook'), |
| param_scheduler=dict(type='ParamSchedulerHook'), |
| runtime_info=dict(type='RuntimeInfoHook'), |
| sampler_seed=dict(type='DistSamplerSeedHook'), |
| timer=dict(type='IterTimerHook')) |
| encoder = dict( |
| num_layers=3, |
| num_points_in_pillar=8, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| return_intermediate=False, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict(embed_dims=256, num_levels=1, type='TemporalSelfAttention'), |
| dict( |
| deformable_attention=dict( |
| embed_dims=256, |
| num_levels=1, |
| num_points=8, |
| type='MSDeformableAttention3D'), |
| embed_dims=256, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| type='SpatialCrossAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, ffn_drop=0.1, num_fcs=2, type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='BEVFormerLayer'), |
| type='BEVFormerEncoder') |
| env_cfg = dict(dist_cfg=dict(backend='nccl')) |
| experiment_name = 'baseline-v0.1' |
| file_client_args = dict(backend='disk') |
| frames = [ |
| -3, |
| -2, |
| -1, |
| ] |
| gpu_ids = range(0, 1) |
| img_norm_cfg = dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True) |
| input_modality = dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False) |
| interval = 250 |
| launcher = 'none' |
| load_from = None |
| log_interval = 50 |
| log_processor = dict(window_size=20) |
| lr_config = dict( |
| min_lr_ratio=0.001, |
| policy='CosineAnnealing', |
| warmup='linear', |
| warmup_iters=500, |
| warmup_ratio=0.3333333333333333) |
| max_epochs = 5 |
| max_iters = 4000 |
| model = dict( |
| img_backbone=dict( |
| depth=50, |
| frozen_stages=1, |
| norm_cfg=dict(requires_grad=False, type='BN'), |
| norm_eval=True, |
| num_stages=4, |
| out_indices=(3, ), |
| style='pytorch', |
| type='ResNet'), |
| img_neck=dict( |
| add_extra_convs='on_output', |
| in_channels=[ |
| 2048, |
| ], |
| num_outs=1, |
| out_channels=256, |
| relu_before_extra_convs=True, |
| start_level=0, |
| type='FPN'), |
| pretrained=dict(img='torchvision://resnet50'), |
| pts_bbox_head=dict( |
| as_two_stage=False, |
| bbox_coder=dict( |
| max_num=300, |
| num_classes=10, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| post_center_range=[ |
| -61.2, |
| -61.2, |
| -10.0, |
| 61.2, |
| 61.2, |
| 10.0, |
| ], |
| type='NMSFreeCoder', |
| voxel_size=[ |
| 0.2, |
| 0.2, |
| 8, |
| ]), |
| bev_h=50, |
| bev_w=50, |
| in_channels=256, |
| loss_bbox=dict(loss_weight=0.5, type='L1Loss'), |
| loss_cls=dict( |
| alpha=0.25, |
| gamma=2.0, |
| loss_weight=2.0, |
| type='FocalLoss', |
| use_sigmoid=True), |
| loss_iou=dict(loss_weight=0.25, type='GIoULoss'), |
| num_classes=10, |
| num_query=900, |
| positional_encoding=dict( |
| col_num_embed=50, |
| num_feats=128, |
| row_num_embed=50, |
| type='LearnedPositionalEncoding'), |
| sync_cls_avg_factor=True, |
| transformer=dict( |
| decoder=dict( |
| num_layers=6, |
| return_intermediate=True, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict( |
| dropout=0.1, |
| embed_dims=256, |
| num_heads=8, |
| type='MultiheadAttention'), |
| dict( |
| embed_dims=256, |
| num_levels=1, |
| type='CustomMSDeformableAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, |
| ffn_drop=0.1, |
| num_fcs=2, |
| type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='DetrTransformerDecoderLayer'), |
| type='DetectionTransformerDecoder'), |
| embed_dims=256, |
| encoder=dict( |
| num_layers=3, |
| num_points_in_pillar=8, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| return_intermediate=False, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict( |
| embed_dims=256, |
| num_levels=1, |
| type='TemporalSelfAttention'), |
| dict( |
| deformable_attention=dict( |
| embed_dims=256, |
| num_levels=1, |
| num_points=8, |
| type='MSDeformableAttention3D'), |
| embed_dims=256, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| type='SpatialCrossAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, |
| ffn_drop=0.1, |
| num_fcs=2, |
| type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='BEVFormerLayer'), |
| type='BEVFormerEncoder'), |
| num_cams=6, |
| num_feature_levels=1, |
| rotate_prev_bev=True, |
| type='PerceptionTransformer', |
| use_can_bus=True, |
| use_shift=True), |
| type='BEVFormerHead', |
| with_box_refine=True), |
| train_cfg=dict( |
| pts=dict( |
| assigner=dict( |
| cls_cost=dict(type='FocalCost', weight=2.0), |
| iou_cost=dict(type='SmoothL1Cost', weight=0.25), |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| reg_cost=dict(type='BBox3DL1Cost', weight=0.25), |
| type='HungarianAssigner3D'), |
| grid_size=[ |
| 512, |
| 512, |
| 1, |
| ], |
| out_size_factor=4, |
| point_cloud_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| voxel_size=[ |
| 0.2, |
| 0.2, |
| 8, |
| ])), |
| type='BEVFormerDetector', |
| use_grid_mask=True, |
| video_test_mode=True) |
| optim_wrapper = dict( |
| optimizer=dict(lr=0.0001, type='AdamW', weight_decay=0.01), |
| type='OptimWrapper') |
| optimizer = dict(lr=0.0001, type='AdamW', weight_decay=0.01) |
| param_scheduler = dict( |
| milestones=[ |
| 1, |
| 2, |
| ], type='MultiStepLR') |
| point_cloud_range = [ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ] |
| pts_bbox_head = dict( |
| as_two_stage=False, |
| bbox_coder=dict( |
| max_num=300, |
| num_classes=10, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| post_center_range=[ |
| -61.2, |
| -61.2, |
| -10.0, |
| 61.2, |
| 61.2, |
| 10.0, |
| ], |
| type='NMSFreeCoder', |
| voxel_size=[ |
| 0.2, |
| 0.2, |
| 8, |
| ]), |
| bev_h=50, |
| bev_w=50, |
| in_channels=256, |
| loss_bbox=dict(loss_weight=0.5, type='L1Loss'), |
| loss_cls=dict( |
| alpha=0.25, |
| gamma=2.0, |
| loss_weight=2.0, |
| type='FocalLoss', |
| use_sigmoid=True), |
| loss_iou=dict(loss_weight=0.25, type='GIoULoss'), |
| num_classes=10, |
| num_query=900, |
| positional_encoding=dict( |
| col_num_embed=50, |
| num_feats=128, |
| row_num_embed=50, |
| type='LearnedPositionalEncoding'), |
| sync_cls_avg_factor=True, |
| transformer=dict( |
| decoder=dict( |
| num_layers=6, |
| return_intermediate=True, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict( |
| dropout=0.1, |
| embed_dims=256, |
| num_heads=8, |
| type='MultiheadAttention'), |
| dict( |
| embed_dims=256, |
| num_levels=1, |
| type='CustomMSDeformableAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, |
| ffn_drop=0.1, |
| num_fcs=2, |
| type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='DetrTransformerDecoderLayer'), |
| type='DetectionTransformerDecoder'), |
| embed_dims=256, |
| encoder=dict( |
| num_layers=3, |
| num_points_in_pillar=8, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| return_intermediate=False, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict( |
| embed_dims=256, |
| num_levels=1, |
| type='TemporalSelfAttention'), |
| dict( |
| deformable_attention=dict( |
| embed_dims=256, |
| num_levels=1, |
| num_points=8, |
| type='MSDeformableAttention3D'), |
| embed_dims=256, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| type='SpatialCrossAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, |
| ffn_drop=0.1, |
| num_fcs=2, |
| type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='BEVFormerLayer'), |
| type='BEVFormerEncoder'), |
| num_cams=6, |
| num_feature_levels=1, |
| rotate_prev_bev=True, |
| type='PerceptionTransformer', |
| use_can_bus=True, |
| use_shift=True), |
| type='BEVFormerHead', |
| with_box_refine=True) |
| queue_length = 4 |
| resume = True |
| scales = [ |
| 0.5, |
| ] |
| test_cfg = dict(max_iters=1) |
| test_dataloader = dict( |
| batch_size=1, |
| collate_fn=dict(type='test_collate'), |
| dataset=dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_val.pkl', |
| bev_size=( |
| 50, |
| 50, |
| ), |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| data_root='data/nuscenes/v1.0-mini/', |
| frame=[ |
| -3, |
| -2, |
| -1, |
| ], |
| modality=dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False), |
| pipeline=[ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict( |
| flip=False, |
| img_scale=( |
| 800, |
| 450, |
| ), |
| pts_scale_ratio=[ |
| 1.0, |
| ], |
| transforms=[ |
| dict( |
| scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict(keys=[ |
| 'img', |
| ], type='CustomCollect3D'), |
| ], |
| type='MultiScaleFlipAug3D'), |
| ], |
| test_mode=True, |
| type='CustomNuScenesDataset'), |
| num_workers=0, |
| sampler=dict(shuffle=True, type='DefaultSampler')) |
| test_evaluator = dict(metrics=[ |
| dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_val.pkl', |
| data_root='data/nuscenes/v1.0-mini/', |
| type='src.NuScenesMetric', |
| version='v1.0-mini'), |
| ]) |
| test_max_iters = 1 |
| test_pipeline = [ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict( |
| flip=False, |
| img_scale=( |
| 800, |
| 450, |
| ), |
| pts_scale_ratio=[ |
| 1.0, |
| ], |
| transforms=[ |
| dict(scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict(keys=[ |
| 'img', |
| ], type='CustomCollect3D'), |
| ], |
| type='MultiScaleFlipAug3D'), |
| ] |
| train_cfg = dict( |
| by_epoch=False, max_epochs=5, max_iters=4000, val_interval=250) |
| train_dataloader = dict( |
| batch_size=1, |
| collate_fn=dict(type='train_collate'), |
| dataset=dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_train.pkl', |
| bev_size=( |
| 50, |
| 50, |
| ), |
| box_type_3d='LiDAR', |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| data_root='data/nuscenes/v1.0-mini/', |
| modality=dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False), |
| pipeline=[ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict( |
| type='LoadAnnotations3D', |
| with_bbox_3d=True, |
| with_label_3d=True), |
| dict( |
| point_cloud_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| type='ObjectRangeFilter'), |
| dict( |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='ObjectNameFilter'), |
| dict(type='PhotoMetricDistortionMultiViewImage'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict(scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict( |
| keys=[ |
| 'gt_bboxes_3d', |
| 'gt_labels_3d', |
| 'img', |
| ], |
| type='CustomCollect3D'), |
| dict(type='TypeConverter'), |
| ], |
| queue_length=4, |
| test_mode=False, |
| type='CustomNuScenesDataset', |
| use_valid_flag=True), |
| num_workers=0, |
| sampler=dict(shuffle=True, type='DefaultSampler')) |
| train_pipeline = [ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True), |
| dict( |
| point_cloud_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| type='ObjectRangeFilter'), |
| dict( |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='ObjectNameFilter'), |
| dict(type='PhotoMetricDistortionMultiViewImage'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict(scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict( |
| keys=[ |
| 'gt_bboxes_3d', |
| 'gt_labels_3d', |
| 'img', |
| ], type='CustomCollect3D'), |
| dict(type='TypeConverter'), |
| ] |
| transformer = dict( |
| decoder=dict( |
| num_layers=6, |
| return_intermediate=True, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict( |
| dropout=0.1, |
| embed_dims=256, |
| num_heads=8, |
| type='MultiheadAttention'), |
| dict( |
| embed_dims=256, |
| num_levels=1, |
| type='CustomMSDeformableAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, ffn_drop=0.1, num_fcs=2, type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='DetrTransformerDecoderLayer'), |
| type='DetectionTransformerDecoder'), |
| embed_dims=256, |
| encoder=dict( |
| num_layers=3, |
| num_points_in_pillar=8, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| return_intermediate=False, |
| transformerlayers=dict( |
| attn_cfgs=[ |
| dict( |
| embed_dims=256, num_levels=1, |
| type='TemporalSelfAttention'), |
| dict( |
| deformable_attention=dict( |
| embed_dims=256, |
| num_levels=1, |
| num_points=8, |
| type='MSDeformableAttention3D'), |
| embed_dims=256, |
| pc_range=[ |
| -51.2, |
| -51.2, |
| -5.0, |
| 51.2, |
| 51.2, |
| 3.0, |
| ], |
| type='SpatialCrossAttention'), |
| ], |
| ffn_cfgs=dict( |
| feedforward_channels=512, ffn_drop=0.1, num_fcs=2, type='FFN'), |
| operation_order=( |
| 'self_attn', |
| 'norm', |
| 'cross_attn', |
| 'norm', |
| 'ffn', |
| 'norm', |
| ), |
| type='BEVFormerLayer'), |
| type='BEVFormerEncoder'), |
| num_cams=6, |
| num_feature_levels=1, |
| rotate_prev_bev=True, |
| type='PerceptionTransformer', |
| use_can_bus=True, |
| use_shift=True) |
| val_cfg = dict(max_iters=1) |
| val_dataloader = dict( |
| batch_size=1, |
| collate_fn=dict(type='test_collate'), |
| dataset=dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_val.pkl', |
| bev_size=( |
| 50, |
| 50, |
| ), |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| data_root='data/nuscenes/v1.0-mini/', |
| frame=(), |
| frames=[ |
| -3, |
| -2, |
| -1, |
| ], |
| modality=dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False), |
| pipeline=[ |
| dict(to_float32=True, type='LoadMultiViewImageFromFiles'), |
| dict( |
| mean=[ |
| 123.675, |
| 116.28, |
| 103.53, |
| ], |
| std=[ |
| 58.395, |
| 57.12, |
| 57.375, |
| ], |
| to_rgb=True, |
| type='NormalizeMultiviewImage'), |
| dict( |
| flip=False, |
| img_scale=( |
| 800, |
| 450, |
| ), |
| pts_scale_ratio=[ |
| 1.0, |
| ], |
| transforms=[ |
| dict( |
| scales=[ |
| 0.5, |
| ], type='RandomScaleImageMultiViewImage'), |
| dict(size_divisor=32, type='PadMultiViewImage'), |
| dict( |
| class_names=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| type='CustomDefaultFormatBundle3D'), |
| dict(keys=[ |
| 'img', |
| ], type='CustomCollect3D'), |
| ], |
| type='MultiScaleFlipAug3D'), |
| ], |
| samples_per_gpu=1, |
| test_mode=True, |
| type='CustomNuScenesDataset'), |
| num_workers=0, |
| sampler=dict(shuffle=True, type='DefaultSampler')) |
| val_evaluator = dict(metrics=[ |
| dict( |
| ann_file='data/nuscenes/v1.0-mini/nuscenes_infos_temporal_val.pkl', |
| classes=[ |
| 'car', |
| 'truck', |
| 'construction_vehicle', |
| 'bus', |
| 'trailer', |
| 'barrier', |
| 'motorcycle', |
| 'bicycle', |
| 'pedestrian', |
| 'traffic_cone', |
| ], |
| data_root='data/nuscenes/v1.0-mini/', |
| jsonfile_prefix='results', |
| modality=dict( |
| use_camera=True, |
| use_external=False, |
| use_lidar=False, |
| use_map=False, |
| use_radar=False), |
| plot_every_run=True, |
| plot_examples=1, |
| type='src.NuScenesMetric', |
| version='v1.0-mini'), |
| ]) |
| val_interval = 250 |
| val_max_iters = 1 |
| version = 'v1.0-mini' |
| visualizer = dict( |
| type='Visualizer', |
| vis_backends=[ |
| dict(type='LocalVisBackend'), |
| dict(type='TensorboardVisBackend'), |
| ]) |
| voxel_size = [ |
| 0.2, |
| 0.2, |
| 8, |
| ] |
| work_dir = 'experiment' |
|
|
