2026-02-05 03:59:46,513 - mmdet - INFO - Environment info: ------------------------------------------------------------ MMCV: 0.0.1 ------------------------------------------------------------ 2026-02-05 03:59:47,507 - mmdet - INFO - Distributed training: True 2026-02-05 03:59:48,516 - mmdet - INFO - Config: point_cloud_range = [-15.0, -30.0, -2.0, 15.0, 30.0, 2.0] class_names = [ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ] dataset_type = 'B2D_VAD_Dataset' data_root = 'data/bench2drive' input_modality = dict( use_lidar=False, use_camera=True, use_radar=False, use_map=False, use_external=True) file_client_args = dict(backend='disk') train_pipeline = [ dict(type='LoadMultiViewImageFromFiles', to_float32=True), dict(type='PhotoMetricDistortionMultiViewImage'), dict( type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=True), dict( type='VADObjectRangeFilter', point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0]), dict( type='VADObjectNameFilter', classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ]), dict( type='NormalizeMultiviewImage', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='RandomScaleImageMultiViewImage', scales=[0.8]), dict(type='PadMultiViewImage', size_divisor=32), dict( type='VADFormatBundle3D', class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], with_ego=True), dict( type='CustomCollect3D', keys=[ 'gt_bboxes_3d', 'gt_labels_3d', 'img', 'ego_his_trajs', 'gt_attr_labels', 'ego_fut_trajs', 'ego_fut_masks', 'ego_fut_cmd', 'ego_lcf_feat' ]) ] test_pipeline = [ dict(type='LoadMultiViewImageFromFiles', to_float32=True), dict( type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=True), dict( type='VADObjectRangeFilter', point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0]), dict( type='VADObjectNameFilter', classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ]), dict( type='NormalizeMultiviewImage', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict( type='MultiScaleFlipAug3D', img_scale=(1600, 900), pts_scale_ratio=1, flip=False, transforms=[ dict(type='RandomScaleImageMultiViewImage', scales=[0.8]), dict(type='PadMultiViewImage', size_divisor=32), dict( type='VADFormatBundle3D', class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], with_label=False, with_ego=True), dict( type='CustomCollect3D', keys=[ 'gt_bboxes_3d', 'gt_labels_3d', 'img', 'fut_valid_flag', 'ego_his_trajs', 'ego_fut_trajs', 'ego_fut_masks', 'ego_fut_cmd', 'ego_lcf_feat', 'gt_attr_labels' ]) ]) ] eval_pipeline = [ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=5, use_dim=5, file_client_args=dict(backend='disk')), dict( type='LoadPointsFromMultiSweeps', sweeps_num=10, file_client_args=dict(backend='disk')), dict( type='DefaultFormatBundle3D', class_names=[ 'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone', 'barrier' ], with_label=False), dict(type='Collect3D', keys=['points']) ] data = dict( samples_per_gpu=1, workers_per_gpu=4, train=dict( type='B2D_VAD_Dataset', data_root='data/bench2drive', ann_file='data/infos/b2d_infos_train.pkl', pipeline=[ dict(type='LoadMultiViewImageFromFiles', to_float32=True), dict(type='PhotoMetricDistortionMultiViewImage'), dict( type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=True), dict( type='VADObjectRangeFilter', point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0]), dict( type='VADObjectNameFilter', classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ]), dict( type='NormalizeMultiviewImage', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='RandomScaleImageMultiViewImage', scales=[0.8]), dict(type='PadMultiViewImage', size_divisor=32), dict( type='VADFormatBundle3D', class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], with_ego=True), dict( type='CustomCollect3D', keys=[ 'gt_bboxes_3d', 'gt_labels_3d', 'img', 'ego_his_trajs', 'gt_attr_labels', 'ego_fut_trajs', 'ego_fut_masks', 'ego_fut_cmd', 'ego_lcf_feat' ]) ], classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], modality=dict( use_lidar=False, use_camera=True, use_radar=False, use_map=False, use_external=True), test_mode=False, box_type_3d='LiDAR', name_mapping=dict({ 'vehicle.bh.crossbike': 'bicycle', 'vehicle.diamondback.century': 'bicycle', 'vehicle.gazelle.omafiets': 'bicycle', 'vehicle.chevrolet.impala': 'car', 'vehicle.dodge.charger_2020': 'car', 'vehicle.dodge.charger_police': 'car', 'vehicle.dodge.charger_police_2020': 'car', 'vehicle.lincoln.mkz_2017': 'car', 'vehicle.lincoln.mkz_2020': 'car', 'vehicle.mini.cooper_s_2021': 'car', 'vehicle.mercedes.coupe_2020': 'car', 'vehicle.ford.mustang': 'car', 'vehicle.nissan.patrol_2021': 'car', 'vehicle.audi.tt': 'car', 'vehicle.audi.etron': 'car', 'vehicle.ford.crown': 'car', 'vehicle.tesla.model3': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/FordCrown/SM_FordCrown_parked.SM_FordCrown_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Charger/SM_ChargerParked.SM_ChargerParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Lincoln/SM_LincolnParked.SM_LincolnParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/MercedesCCC/SM_MercedesCCC_Parked.SM_MercedesCCC_Parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Mini2021/SM_Mini2021_parked.SM_Mini2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/NissanPatrol2021/SM_NissanPatrol2021_parked.SM_NissanPatrol2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/TeslaM3/SM_TeslaM3_parked.SM_TeslaM3_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/VolkswagenT2/SM_VolkswagenT2_2021_Parked.SM_VolkswagenT2_2021_Parked': 'van', 'vehicle.ford.ambulance': 'van', 'vehicle.carlamotors.firetruck': 'truck', 'traffic.speed_limit.30': 'traffic_sign', 'traffic.speed_limit.40': 'traffic_sign', 'traffic.speed_limit.50': 'traffic_sign', 'traffic.speed_limit.60': 'traffic_sign', 'traffic.speed_limit.90': 'traffic_sign', 'traffic.speed_limit.120': 'traffic_sign', 'traffic.stop': 'traffic_sign', 'traffic.yield': 'traffic_sign', 'traffic.traffic_light': 'traffic_light', 'static.prop.warningconstruction': 'traffic_cone', 'static.prop.warningaccident': 'traffic_cone', 'static.prop.trafficwarning': 'traffic_cone', 'static.prop.constructioncone': 'traffic_cone', 'walker.pedestrian.0001': 'pedestrian', 'walker.pedestrian.0004': 'pedestrian', 'walker.pedestrian.0005': 'pedestrian', 'walker.pedestrian.0007': 'pedestrian', 'walker.pedestrian.0013': 'pedestrian', 'walker.pedestrian.0014': 'pedestrian', 'walker.pedestrian.0017': 'pedestrian', 'walker.pedestrian.0018': 'pedestrian', 'walker.pedestrian.0019': 'pedestrian', 'walker.pedestrian.0020': 'pedestrian', 'walker.pedestrian.0022': 'pedestrian', 'walker.pedestrian.0025': 'pedestrian', 'walker.pedestrian.0035': 'pedestrian', 'walker.pedestrian.0041': 'pedestrian', 'walker.pedestrian.0046': 'pedestrian', 'walker.pedestrian.0047': 'pedestrian', 'static.prop.dirtdebris01': 'others', 'static.prop.dirtdebris02': 'others' }), map_root='data/bench2drive/maps', map_file='data/infos/b2d_map_infos.pkl', bev_size=(100, 100), queue_length=3, past_frames=2, future_frames=6, point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], polyline_points_num=20), val=dict( type='B2D_VAD_Dataset', ann_file='data/infos/b2d_infos_val.pkl', pipeline=[ dict(type='LoadMultiViewImageFromFiles', to_float32=True), dict( type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=True), dict( type='VADObjectRangeFilter', point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0]), dict( type='VADObjectNameFilter', classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ]), dict( type='NormalizeMultiviewImage', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict( type='MultiScaleFlipAug3D', img_scale=(1600, 900), pts_scale_ratio=1, flip=False, transforms=[ dict(type='RandomScaleImageMultiViewImage', scales=[0.8]), dict(type='PadMultiViewImage', size_divisor=32), dict( type='VADFormatBundle3D', class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], with_label=False, with_ego=True), dict( type='CustomCollect3D', keys=[ 'gt_bboxes_3d', 'gt_labels_3d', 'img', 'fut_valid_flag', 'ego_his_trajs', 'ego_fut_trajs', 'ego_fut_masks', 'ego_fut_cmd', 'ego_lcf_feat', 'gt_attr_labels' ]) ]) ], classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], modality=dict( use_lidar=False, use_camera=True, use_radar=False, use_map=False, use_external=True), test_mode=True, box_type_3d='LiDAR', data_root='data/bench2drive', name_mapping=dict({ 'vehicle.bh.crossbike': 'bicycle', 'vehicle.diamondback.century': 'bicycle', 'vehicle.gazelle.omafiets': 'bicycle', 'vehicle.chevrolet.impala': 'car', 'vehicle.dodge.charger_2020': 'car', 'vehicle.dodge.charger_police': 'car', 'vehicle.dodge.charger_police_2020': 'car', 'vehicle.lincoln.mkz_2017': 'car', 'vehicle.lincoln.mkz_2020': 'car', 'vehicle.mini.cooper_s_2021': 'car', 'vehicle.mercedes.coupe_2020': 'car', 'vehicle.ford.mustang': 'car', 'vehicle.nissan.patrol_2021': 'car', 'vehicle.audi.tt': 'car', 'vehicle.audi.etron': 'car', 'vehicle.ford.crown': 'car', 'vehicle.tesla.model3': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/FordCrown/SM_FordCrown_parked.SM_FordCrown_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Charger/SM_ChargerParked.SM_ChargerParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Lincoln/SM_LincolnParked.SM_LincolnParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/MercedesCCC/SM_MercedesCCC_Parked.SM_MercedesCCC_Parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Mini2021/SM_Mini2021_parked.SM_Mini2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/NissanPatrol2021/SM_NissanPatrol2021_parked.SM_NissanPatrol2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/TeslaM3/SM_TeslaM3_parked.SM_TeslaM3_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/VolkswagenT2/SM_VolkswagenT2_2021_Parked.SM_VolkswagenT2_2021_Parked': 'van', 'vehicle.ford.ambulance': 'van', 'vehicle.carlamotors.firetruck': 'truck', 'traffic.speed_limit.30': 'traffic_sign', 'traffic.speed_limit.40': 'traffic_sign', 'traffic.speed_limit.50': 'traffic_sign', 'traffic.speed_limit.60': 'traffic_sign', 'traffic.speed_limit.90': 'traffic_sign', 'traffic.speed_limit.120': 'traffic_sign', 'traffic.stop': 'traffic_sign', 'traffic.yield': 'traffic_sign', 'traffic.traffic_light': 'traffic_light', 'static.prop.warningconstruction': 'traffic_cone', 'static.prop.warningaccident': 'traffic_cone', 'static.prop.trafficwarning': 'traffic_cone', 'static.prop.constructioncone': 'traffic_cone', 'walker.pedestrian.0001': 'pedestrian', 'walker.pedestrian.0004': 'pedestrian', 'walker.pedestrian.0005': 'pedestrian', 'walker.pedestrian.0007': 'pedestrian', 'walker.pedestrian.0013': 'pedestrian', 'walker.pedestrian.0014': 'pedestrian', 'walker.pedestrian.0017': 'pedestrian', 'walker.pedestrian.0018': 'pedestrian', 'walker.pedestrian.0019': 'pedestrian', 'walker.pedestrian.0020': 'pedestrian', 'walker.pedestrian.0022': 'pedestrian', 'walker.pedestrian.0025': 'pedestrian', 'walker.pedestrian.0035': 'pedestrian', 'walker.pedestrian.0041': 'pedestrian', 'walker.pedestrian.0046': 'pedestrian', 'walker.pedestrian.0047': 'pedestrian', 'static.prop.dirtdebris01': 'others', 'static.prop.dirtdebris02': 'others' }), map_root='data/bench2drive/maps', map_file='data/infos/b2d_map_infos.pkl', bev_size=(100, 100), queue_length=3, past_frames=2, future_frames=6, point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], polyline_points_num=20, eval_cfg=dict( dist_ths=[0.5, 1.0, 2.0, 4.0], dist_th_tp=2.0, min_recall=0.1, min_precision=0.1, mean_ap_weight=5, class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian' ], tp_metrics=['trans_err', 'scale_err', 'orient_err', 'vel_err'], err_name_maping=dict( trans_err='mATE', scale_err='mASE', orient_err='mAOE', vel_err='mAVE', attr_err='mAAE'), class_range=dict( car=(50, 50), van=(50, 50), truck=(50, 50), bicycle=(40, 40), traffic_sign=(30, 30), traffic_cone=(30, 30), traffic_light=(30, 30), pedestrian=(40, 40)))), test=dict( type='B2D_VAD_Dataset', data_root='data/bench2drive', ann_file='data/infos/b2d_infos_val.pkl', pipeline=[ dict(type='LoadMultiViewImageFromFiles', to_float32=True), dict( type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=True), dict( type='VADObjectRangeFilter', point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0]), dict( type='VADObjectNameFilter', classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ]), dict( type='NormalizeMultiviewImage', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict( type='MultiScaleFlipAug3D', img_scale=(1600, 900), pts_scale_ratio=1, flip=False, transforms=[ dict(type='RandomScaleImageMultiViewImage', scales=[0.8]), dict(type='PadMultiViewImage', size_divisor=32), dict( type='VADFormatBundle3D', class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], with_label=False, with_ego=True), dict( type='CustomCollect3D', keys=[ 'gt_bboxes_3d', 'gt_labels_3d', 'img', 'fut_valid_flag', 'ego_his_trajs', 'ego_fut_trajs', 'ego_fut_masks', 'ego_fut_cmd', 'ego_lcf_feat', 'gt_attr_labels' ]) ]) ], classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], modality=dict( use_lidar=False, use_camera=True, use_radar=False, use_map=False, use_external=True), test_mode=True, box_type_3d='LiDAR', name_mapping=dict({ 'vehicle.bh.crossbike': 'bicycle', 'vehicle.diamondback.century': 'bicycle', 'vehicle.gazelle.omafiets': 'bicycle', 'vehicle.chevrolet.impala': 'car', 'vehicle.dodge.charger_2020': 'car', 'vehicle.dodge.charger_police': 'car', 'vehicle.dodge.charger_police_2020': 'car', 'vehicle.lincoln.mkz_2017': 'car', 'vehicle.lincoln.mkz_2020': 'car', 'vehicle.mini.cooper_s_2021': 'car', 'vehicle.mercedes.coupe_2020': 'car', 'vehicle.ford.mustang': 'car', 'vehicle.nissan.patrol_2021': 'car', 'vehicle.audi.tt': 'car', 'vehicle.audi.etron': 'car', 'vehicle.ford.crown': 'car', 'vehicle.tesla.model3': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/FordCrown/SM_FordCrown_parked.SM_FordCrown_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Charger/SM_ChargerParked.SM_ChargerParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Lincoln/SM_LincolnParked.SM_LincolnParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/MercedesCCC/SM_MercedesCCC_Parked.SM_MercedesCCC_Parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Mini2021/SM_Mini2021_parked.SM_Mini2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/NissanPatrol2021/SM_NissanPatrol2021_parked.SM_NissanPatrol2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/TeslaM3/SM_TeslaM3_parked.SM_TeslaM3_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/VolkswagenT2/SM_VolkswagenT2_2021_Parked.SM_VolkswagenT2_2021_Parked': 'van', 'vehicle.ford.ambulance': 'van', 'vehicle.carlamotors.firetruck': 'truck', 'traffic.speed_limit.30': 'traffic_sign', 'traffic.speed_limit.40': 'traffic_sign', 'traffic.speed_limit.50': 'traffic_sign', 'traffic.speed_limit.60': 'traffic_sign', 'traffic.speed_limit.90': 'traffic_sign', 'traffic.speed_limit.120': 'traffic_sign', 'traffic.stop': 'traffic_sign', 'traffic.yield': 'traffic_sign', 'traffic.traffic_light': 'traffic_light', 'static.prop.warningconstruction': 'traffic_cone', 'static.prop.warningaccident': 'traffic_cone', 'static.prop.trafficwarning': 'traffic_cone', 'static.prop.constructioncone': 'traffic_cone', 'walker.pedestrian.0001': 'pedestrian', 'walker.pedestrian.0004': 'pedestrian', 'walker.pedestrian.0005': 'pedestrian', 'walker.pedestrian.0007': 'pedestrian', 'walker.pedestrian.0013': 'pedestrian', 'walker.pedestrian.0014': 'pedestrian', 'walker.pedestrian.0017': 'pedestrian', 'walker.pedestrian.0018': 'pedestrian', 'walker.pedestrian.0019': 'pedestrian', 'walker.pedestrian.0020': 'pedestrian', 'walker.pedestrian.0022': 'pedestrian', 'walker.pedestrian.0025': 'pedestrian', 'walker.pedestrian.0035': 'pedestrian', 'walker.pedestrian.0041': 'pedestrian', 'walker.pedestrian.0046': 'pedestrian', 'walker.pedestrian.0047': 'pedestrian', 'static.prop.dirtdebris01': 'others', 'static.prop.dirtdebris02': 'others' }), map_root='data/bench2drive/maps', map_file='data/infos/b2d_map_infos.pkl', bev_size=(100, 100), queue_length=3, past_frames=2, future_frames=6, point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], polyline_points_num=20, eval_cfg=dict( dist_ths=[0.5, 1.0, 2.0, 4.0], dist_th_tp=2.0, min_recall=0.1, min_precision=0.1, mean_ap_weight=5, class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian' ], tp_metrics=['trans_err', 'scale_err', 'orient_err', 'vel_err'], err_name_maping=dict( trans_err='mATE', scale_err='mASE', orient_err='mAOE', vel_err='mAVE', attr_err='mAAE'), class_range=dict( car=(50, 50), van=(50, 50), truck=(50, 50), bicycle=(40, 40), traffic_sign=(30, 30), traffic_cone=(30, 30), traffic_light=(30, 30), pedestrian=(40, 40)))), shuffler_sampler=dict(type='DistributedGroupSampler'), nonshuffler_sampler=dict(type='DistributedSampler')) evaluation = dict( interval=6, pipeline=[ dict(type='LoadMultiViewImageFromFiles', to_float32=True), dict( type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=True), dict( type='VADObjectRangeFilter', point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0]), dict( type='VADObjectNameFilter', classes=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ]), dict( type='NormalizeMultiviewImage', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict( type='MultiScaleFlipAug3D', img_scale=(1600, 900), pts_scale_ratio=1, flip=False, transforms=[ dict(type='RandomScaleImageMultiViewImage', scales=[0.8]), dict(type='PadMultiViewImage', size_divisor=32), dict( type='VADFormatBundle3D', class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], with_label=False, with_ego=True), dict( type='CustomCollect3D', keys=[ 'gt_bboxes_3d', 'gt_labels_3d', 'img', 'fut_valid_flag', 'ego_his_trajs', 'ego_fut_trajs', 'ego_fut_masks', 'ego_fut_cmd', 'ego_lcf_feat', 'gt_attr_labels' ]) ]) ], metric='bbox', map_metric='chamfer') checkpoint_config = dict(interval=1, max_keep_ckpts=6) log_config = dict( interval=50, hooks=[dict(type='TextLoggerHook'), dict(type='TensorboardLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' work_dir = './work_dirs/GenAD_config_b2d' load_from = None resume_from = None workflow = [('train', 1)] voxel_size = [0.15, 0.15, 4] img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) NameMapping = dict({ 'vehicle.bh.crossbike': 'bicycle', 'vehicle.diamondback.century': 'bicycle', 'vehicle.gazelle.omafiets': 'bicycle', 'vehicle.chevrolet.impala': 'car', 'vehicle.dodge.charger_2020': 'car', 'vehicle.dodge.charger_police': 'car', 'vehicle.dodge.charger_police_2020': 'car', 'vehicle.lincoln.mkz_2017': 'car', 'vehicle.lincoln.mkz_2020': 'car', 'vehicle.mini.cooper_s_2021': 'car', 'vehicle.mercedes.coupe_2020': 'car', 'vehicle.ford.mustang': 'car', 'vehicle.nissan.patrol_2021': 'car', 'vehicle.audi.tt': 'car', 'vehicle.audi.etron': 'car', 'vehicle.ford.crown': 'car', 'vehicle.tesla.model3': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/FordCrown/SM_FordCrown_parked.SM_FordCrown_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Charger/SM_ChargerParked.SM_ChargerParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Lincoln/SM_LincolnParked.SM_LincolnParked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/MercedesCCC/SM_MercedesCCC_Parked.SM_MercedesCCC_Parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/Mini2021/SM_Mini2021_parked.SM_Mini2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/NissanPatrol2021/SM_NissanPatrol2021_parked.SM_NissanPatrol2021_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/TeslaM3/SM_TeslaM3_parked.SM_TeslaM3_parked': 'car', '/Game/Carla/Static/Car/4Wheeled/ParkedVehicles/VolkswagenT2/SM_VolkswagenT2_2021_Parked.SM_VolkswagenT2_2021_Parked': 'van', 'vehicle.ford.ambulance': 'van', 'vehicle.carlamotors.firetruck': 'truck', 'traffic.speed_limit.30': 'traffic_sign', 'traffic.speed_limit.40': 'traffic_sign', 'traffic.speed_limit.50': 'traffic_sign', 'traffic.speed_limit.60': 'traffic_sign', 'traffic.speed_limit.90': 'traffic_sign', 'traffic.speed_limit.120': 'traffic_sign', 'traffic.stop': 'traffic_sign', 'traffic.yield': 'traffic_sign', 'traffic.traffic_light': 'traffic_light', 'static.prop.warningconstruction': 'traffic_cone', 'static.prop.warningaccident': 'traffic_cone', 'static.prop.trafficwarning': 'traffic_cone', 'static.prop.constructioncone': 'traffic_cone', 'walker.pedestrian.0001': 'pedestrian', 'walker.pedestrian.0004': 'pedestrian', 'walker.pedestrian.0005': 'pedestrian', 'walker.pedestrian.0007': 'pedestrian', 'walker.pedestrian.0013': 'pedestrian', 'walker.pedestrian.0014': 'pedestrian', 'walker.pedestrian.0017': 'pedestrian', 'walker.pedestrian.0018': 'pedestrian', 'walker.pedestrian.0019': 'pedestrian', 'walker.pedestrian.0020': 'pedestrian', 'walker.pedestrian.0022': 'pedestrian', 'walker.pedestrian.0025': 'pedestrian', 'walker.pedestrian.0035': 'pedestrian', 'walker.pedestrian.0041': 'pedestrian', 'walker.pedestrian.0046': 'pedestrian', 'walker.pedestrian.0047': 'pedestrian', 'static.prop.dirtdebris01': 'others', 'static.prop.dirtdebris02': 'others' }) eval_cfg = dict( dist_ths=[0.5, 1.0, 2.0, 4.0], dist_th_tp=2.0, min_recall=0.1, min_precision=0.1, mean_ap_weight=5, class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian' ], tp_metrics=['trans_err', 'scale_err', 'orient_err', 'vel_err'], err_name_maping=dict( trans_err='mATE', scale_err='mASE', orient_err='mAOE', vel_err='mAVE', attr_err='mAAE'), class_range=dict( car=(50, 50), van=(50, 50), truck=(50, 50), bicycle=(40, 40), traffic_sign=(30, 30), traffic_cone=(30, 30), traffic_light=(30, 30), pedestrian=(40, 40))) num_classes = 9 map_classes = [ 'Broken', 'Solid', 'SolidSolid', 'Center', 'TrafficLight', 'StopSign' ] map_num_vec = 100 map_fixed_ptsnum_per_gt_line = 20 map_fixed_ptsnum_per_pred_line = 20 map_eval_use_same_gt_sample_num_flag = True map_num_classes = 6 past_frames = 2 future_frames = 6 _dim_ = 256 _pos_dim_ = 128 _ffn_dim_ = 512 _num_levels_ = 1 bev_h_ = 100 bev_w_ = 100 queue_length = 3 total_epochs = 6 model = dict( type='GenAD', use_grid_mask=True, video_test_mode=True, pretrained=dict(img='ckpts/resnet50-19c8e357.pth'), img_backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(3, ), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, style='pytorch'), img_neck=dict( type='FPN', in_channels=[2048], out_channels=256, start_level=0, add_extra_convs='on_output', num_outs=1, relu_before_extra_convs=True), pts_bbox_head=dict( type='GenADHead', map_thresh=0.5, dis_thresh=0.2, pe_normalization=True, tot_epoch=6, use_traj_lr_warmup=False, query_thresh=0.0, query_use_fix_pad=False, ego_his_encoder=None, ego_lcf_feat_idx=None, valid_fut_ts=6, ego_fut_mode=6, agent_dim=300, ego_agent_decoder=dict( type='CustomTransformerDecoder', num_layers=1, return_intermediate=False, transformerlayers=dict( type='BaseTransformerLayer', attn_cfgs=[ dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.0) ], feedforward_channels=512, ffn_dropout=0.0, operation_order=('cross_attn', 'norm', 'ffn', 'norm'))), ego_map_decoder=dict( type='CustomTransformerDecoder', num_layers=1, return_intermediate=False, transformerlayers=dict( type='BaseTransformerLayer', attn_cfgs=[ dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.0) ], feedforward_channels=512, ffn_dropout=0.0, operation_order=('cross_attn', 'norm', 'ffn', 'norm'))), motion_decoder=dict( type='CustomTransformerDecoder', num_layers=1, return_intermediate=False, transformerlayers=dict( type='BaseTransformerLayer', attn_cfgs=[ dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.0) ], feedforward_channels=512, ffn_dropout=0.0, operation_order=('cross_attn', 'norm', 'ffn', 'norm'))), motion_map_decoder=dict( type='CustomTransformerDecoder', num_layers=1, return_intermediate=False, transformerlayers=dict( type='BaseTransformerLayer', attn_cfgs=[ dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.0) ], feedforward_channels=512, ffn_dropout=0.0, operation_order=('cross_attn', 'norm', 'ffn', 'norm'))), use_pe=True, bev_h=100, bev_w=100, num_query=300, num_classes=9, in_channels=256, sync_cls_avg_factor=True, with_box_refine=True, as_two_stage=False, map_num_vec=100, map_num_classes=6, map_num_pts_per_vec=20, map_num_pts_per_gt_vec=20, map_query_embed_type='instance_pts', map_transform_method='minmax', map_gt_shift_pts_pattern='v2', map_dir_interval=1, map_code_size=2, map_code_weights=[1.0, 1.0, 1.0, 1.0], transformer=dict( type='VADPerceptionTransformer', map_num_vec=100, map_num_pts_per_vec=20, rotate_prev_bev=True, use_shift=True, use_can_bus=True, embed_dims=256, encoder=dict( type='BEVFormerEncoder', num_layers=3, pc_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], num_points_in_pillar=4, return_intermediate=False, transformerlayers=dict( type='BEVFormerLayer', attn_cfgs=[ dict( type='TemporalSelfAttention', embed_dims=256, num_levels=1), dict( type='SpatialCrossAttention', pc_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], deformable_attention=dict( type='MSDeformableAttention3D', embed_dims=256, num_points=8, num_levels=1), embed_dims=256) ], feedforward_channels=512, ffn_dropout=0.0, operation_order=('self_attn', 'norm', 'cross_attn', 'norm', 'ffn', 'norm'))), decoder=dict( type='DetectionTransformerDecoder', num_layers=3, return_intermediate=True, transformerlayers=dict( type='DetrTransformerDecoderLayer', attn_cfgs=[ dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.0), dict( type='CustomMSDeformableAttention', embed_dims=256, num_levels=1) ], feedforward_channels=512, ffn_dropout=0.0, operation_order=('self_attn', 'norm', 'cross_attn', 'norm', 'ffn', 'norm'))), map_decoder=dict( type='MapDetectionTransformerDecoder', num_layers=3, return_intermediate=True, transformerlayers=dict( type='DetrTransformerDecoderLayer', attn_cfgs=[ dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.0), dict( type='CustomMSDeformableAttention', embed_dims=256, num_levels=1) ], feedforward_channels=512, ffn_dropout=0.0, operation_order=('self_attn', 'norm', 'cross_attn', 'norm', 'ffn', 'norm')))), bbox_coder=dict( type='CustomNMSFreeCoder', post_center_range=[-20, -35, -10.0, 20, 35, 10.0], pc_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], max_num=100, voxel_size=[0.15, 0.15, 4], num_classes=9), map_bbox_coder=dict( type='MapNMSFreeCoder', post_center_range=[-20, -35, -20, -35, 20, 35, 20, 35], pc_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], max_num=50, voxel_size=[0.15, 0.15, 4], num_classes=6), positional_encoding=dict( type='LearnedPositionalEncoding', num_feats=128, row_num_embed=100, col_num_embed=100), loss_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=2.0), loss_bbox=dict(type='L1Loss', loss_weight=0.25), loss_traj=dict(type='L1Loss', loss_weight=0.2), loss_traj_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=0.2), loss_iou=dict(type='GIoULoss', loss_weight=0.0), loss_map_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=2.0), loss_map_bbox=dict(type='L1Loss', loss_weight=0.0), loss_map_iou=dict(type='GIoULoss', loss_weight=0.0), loss_map_pts=dict(type='PtsL1Loss', loss_weight=1.0), loss_map_dir=dict(type='PtsDirCosLoss', loss_weight=0.005), loss_plan_reg=dict(type='L1Loss', loss_weight=1.0), loss_plan_bound=dict( type='PlanMapBoundLoss', loss_weight=1.0, dis_thresh=1.0), loss_plan_col=dict(type='PlanCollisionLoss', loss_weight=1.0), loss_plan_dir=dict(type='PlanMapDirectionLoss', loss_weight=0.5), loss_vae_gen=dict(type='ProbabilisticLoss', loss_weight=1.0)), train_cfg=dict( pts=dict( grid_size=[512, 512, 1], voxel_size=[0.15, 0.15, 4], point_cloud_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0], out_size_factor=4, assigner=dict( type='HungarianAssigner3D', cls_cost=dict(type='FocalLossCost', weight=2.0), reg_cost=dict(type='BBox3DL1Cost', weight=0.25), iou_cost=dict(type='IoUCost', weight=0.0), pc_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0]), map_assigner=dict( type='MapHungarianAssigner3D', cls_cost=dict(type='FocalLossCost', weight=2.0), reg_cost=dict( type='BBoxL1Cost', weight=0.0, box_format='xywh'), iou_cost=dict(type='IoUCost', iou_mode='giou', weight=0.0), pts_cost=dict(type='OrderedPtsL1Cost', weight=1.0), pc_range=[-15.0, -30.0, -2.0, 15.0, 30.0, 2.0])))) info_root = 'data/infos' map_root = 'data/bench2drive/maps' map_file = 'data/infos/b2d_map_infos.pkl' ann_file_train = 'data/infos/b2d_infos_train.pkl' ann_file_val = 'data/infos/b2d_infos_val.pkl' ann_file_test = 'data/infos/b2d_infos_val.pkl' inference_only_pipeline = [ dict(type='LoadMultiViewImageFromFiles', to_float32=True), dict( type='NormalizeMultiviewImage', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='PadMultiViewImage', size_divisor=32), dict( type='MultiScaleFlipAug3D', img_scale=(1600, 900), pts_scale_ratio=1, flip=False, transforms=[ dict(type='RandomScaleImageMultiViewImage', scales=[0.8]), dict(type='PadMultiViewImage', size_divisor=32), dict( type='VADFormatBundle3D', class_names=[ 'car', 'van', 'truck', 'bicycle', 'traffic_sign', 'traffic_cone', 'traffic_light', 'pedestrian', 'others' ], with_label=False, with_ego=True), dict(type='CustomCollect3D', keys=['img', 'ego_fut_cmd']) ]) ] optimizer = dict( type='AdamW', lr=0.0002, paramwise_cfg=dict(custom_keys=dict(img_backbone=dict(lr_mult=0.1))), weight_decay=0.01) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) lr_config = dict( by_epoch=False, policy='CosineAnnealing', warmup='linear', warmup_iters=500, warmup_ratio=0.3333333333333333, min_lr_ratio=0.001) runner = dict(type='EpochBasedRunner', max_epochs=6) find_unused_parameters = True custom_hooks = [dict(type='CustomSetEpochInfoHook')] gpu_ids = range(0, 1) 2026-02-05 03:59:48,517 - mmdet - INFO - Set random seed to 0, deterministic: True 2026-02-05 03:59:49,019 - mmdet - INFO - initialize ResNet with init_cfg {'type': 'Pretrained', 'checkpoint': 'ckpts/resnet50-19c8e357.pth'} 2026-02-05 03:59:49,236 - mmdet - INFO - initialize FPN with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} Name of parameter - Initialization information pts_bbox_head.code_weights - torch.Size([10]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_code_weights - torch.Size([4]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.positional_encoding.row_embed.weight - torch.Size([100, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.positional_encoding.col_embed.weight - torch.Size([100, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.level_embeds - torch.Size([4, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.cams_embeds - torch.Size([6, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.0.attentions.0.sampling_offsets.weight - torch.Size([128, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.0.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.0.attention_weights.weight - torch.Size([64, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.0.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.0.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.0.attentions.0.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.0.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.0.attentions.0.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.1.deformable_attention.sampling_offsets.weight - torch.Size([128, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.1.deformable_attention.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.1.deformable_attention.attention_weights.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.1.deformable_attention.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.1.deformable_attention.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.0.attentions.1.deformable_attention.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.0.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.0.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.0.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.0.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.0.sampling_offsets.weight - torch.Size([128, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.0.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.0.attention_weights.weight - torch.Size([64, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.0.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.0.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.1.attentions.0.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.0.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.1.attentions.0.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.1.deformable_attention.sampling_offsets.weight - torch.Size([128, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.1.deformable_attention.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.1.deformable_attention.attention_weights.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.1.deformable_attention.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.1.deformable_attention.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.1.attentions.1.deformable_attention.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.1.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.1.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.1.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.1.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.0.sampling_offsets.weight - torch.Size([128, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.0.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.0.attention_weights.weight - torch.Size([64, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.0.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.0.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.2.attentions.0.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.0.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.2.attentions.0.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.1.deformable_attention.sampling_offsets.weight - torch.Size([128, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.1.deformable_attention.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.1.deformable_attention.attention_weights.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.1.deformable_attention.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.1.deformable_attention.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.2.attentions.1.deformable_attention.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.2.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.2.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.encoder.layers.2.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.encoder.layers.2.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.0.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.0.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.1.sampling_offsets.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.1.sampling_offsets.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.1.attention_weights.weight - torch.Size([32, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.1.attention_weights.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.1.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.0.attentions.1.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.0.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.0.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.0.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.0.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.1.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.1.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.1.sampling_offsets.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.1.sampling_offsets.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.1.attention_weights.weight - torch.Size([32, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.1.attention_weights.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.1.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.1.attentions.1.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.1.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.1.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.1.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.1.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.2.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.2.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.1.sampling_offsets.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.1.sampling_offsets.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.1.attention_weights.weight - torch.Size([32, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.1.attention_weights.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.1.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.2.attentions.1.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.2.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.2.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.decoder.layers.2.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.decoder.layers.2.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.0.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.0.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.sampling_offsets.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.sampling_offsets.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.attention_weights.weight - torch.Size([32, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.attention_weights.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.0.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.0.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.0.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.0.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.1.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.1.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.sampling_offsets.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.sampling_offsets.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.attention_weights.weight - torch.Size([32, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.attention_weights.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.1.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.1.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.1.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.1.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.2.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.2.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.sampling_offsets.weight - torch.Size([64, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.sampling_offsets.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.attention_weights.weight - torch.Size([32, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.attention_weights.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.value_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.value_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.output_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.2.attentions.1.output_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.2.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_decoder.layers.2.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.map_decoder.layers.2.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.reference_points.weight - torch.Size([3, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.reference_points.bias - torch.Size([3]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_reference_points.weight - torch.Size([2, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.map_reference_points.bias - torch.Size([2]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.can_bus_mlp.0.weight - torch.Size([128, 18]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.can_bus_mlp.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.can_bus_mlp.2.weight - torch.Size([256, 128]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.transformer.can_bus_mlp.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.can_bus_mlp.norm.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.transformer.can_bus_mlp.norm.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.3.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.6.weight - torch.Size([9, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.0.6.bias - torch.Size([9]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.cls_branches.1.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.3.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.6.weight - torch.Size([9, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.1.6.bias - torch.Size([9]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.cls_branches.2.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.3.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.6.weight - torch.Size([9, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.cls_branches.2.6.bias - torch.Size([9]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.reg_branches.0.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.0.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.0.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.0.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.0.4.weight - torch.Size([10, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.0.4.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.1.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.1.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.1.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.1.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.1.4.weight - torch.Size([10, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.1.4.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.2.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.2.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.2.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.2.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.2.4.weight - torch.Size([10, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.reg_branches.2.4.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches.0.0.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches.0.0.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches.0.2.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches.0.2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches.0.4.weight - torch.Size([2, 1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches.0.4.bias - torch.Size([2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.0.weight - torch.Size([512, 3584]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.3.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.4.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.4.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.6.weight - torch.Size([1, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches.0.6.bias - torch.Size([1]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.map_cls_branches.0.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.3.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.6.weight - torch.Size([6, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.0.6.bias - torch.Size([6]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.map_cls_branches.1.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.3.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.6.weight - torch.Size([6, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.1.6.bias - torch.Size([6]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.map_cls_branches.2.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.3.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.6.weight - torch.Size([6, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_cls_branches.2.6.bias - torch.Size([6]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.map_reg_branches.0.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.0.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.0.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.0.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.0.4.weight - torch.Size([2, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.0.4.bias - torch.Size([2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.1.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.1.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.1.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.1.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.1.4.weight - torch.Size([2, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.1.4.bias - torch.Size([2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.2.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.2.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.2.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.2.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.2.4.weight - torch.Size([2, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_reg_branches.2.4.bias - torch.Size([2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.bev_embedding.weight - torch.Size([10000, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.query_embedding.weight - torch.Size([300, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_instance_embedding.weight - torch.Size([100, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.map_pts_embedding.weight - torch.Size([20, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_decoder.layers.0.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_decoder.layers.0.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_decoder.layers.0.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_decoder.layers.0.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_decoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_mode_query.weight - torch.Size([6, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.pos_mlp_sa.weight - torch.Size([256, 2]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.pos_mlp_sa.bias - torch.Size([256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.lane_encoder.layer_seq.lmlp_0.mlp.0.weight - torch.Size([128, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.lane_encoder.layer_seq.lmlp_0.mlp.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_0.mlp.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_0.mlp.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_1.mlp.0.weight - torch.Size([128, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.lane_encoder.layer_seq.lmlp_1.mlp.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_1.mlp.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_1.mlp.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_2.mlp.0.weight - torch.Size([128, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.lane_encoder.layer_seq.lmlp_2.mlp.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_2.mlp.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.lane_encoder.layer_seq.lmlp_2.mlp.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_map_decoder.layers.0.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_map_decoder.layers.0.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_map_decoder.layers.0.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.motion_map_decoder.layers.0.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_map_decoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.pos_mlp.weight - torch.Size([256, 2]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.pos_mlp.bias - torch.Size([256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_query.weight - torch.Size([1, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_agent_decoder.layers.0.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_agent_decoder.layers.0.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_agent_decoder.layers.0.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_agent_decoder.layers.0.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_decoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_pos_mlp.weight - torch.Size([256, 2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_agent_pos_mlp.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.attentions.0.attn.in_proj_weight - torch.Size([768, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_map_decoder.layers.0.attentions.0.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.attentions.0.attn.out_proj.weight - torch.Size([256, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_map_decoder.layers.0.attentions.0.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.ffns.0.layers.0.0.weight - torch.Size([512, 256]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_map_decoder.layers.0.ffns.0.layers.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.ffns.0.layers.1.weight - torch.Size([256, 512]): Initialized by user-defined `init_weights` in GenADHead pts_bbox_head.ego_map_decoder.layers.0.ffns.0.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_decoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_pos_mlp.weight - torch.Size([256, 2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_map_pos_mlp.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder.0.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder.0.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder.2.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder.2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder.4.weight - torch.Size([12, 1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder.4.bias - torch.Size([12]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.agent_fus_mlp.0.weight - torch.Size([256, 3072]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.agent_fus_mlp.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.agent_fus_mlp.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.agent_fus_mlp.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.agent_fus_mlp.3.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.agent_fus_mlp.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_coord_mlp.weight - torch.Size([2, 2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_coord_mlp.bias - torch.Size([2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_ih_l0 - torch.Size([1536, 32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_hh_l0 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_ih_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_hh_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_ih_l1 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_hh_l1 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_ih_l1 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_hh_l1 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_ih_l2 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_hh_l2 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_ih_l2 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_hh_l2 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_ih_l3 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.weight_hh_l3 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_ih_l3 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.state_gru.bias_hh_l3 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_ih_l0 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_hh_l0 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_ih_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_hh_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_ih_l1 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_hh_l1 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_ih_l1 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_hh_l1 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_ih_l2 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_hh_l2 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_ih_l2 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_hh_l2 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_ih_l3 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.weight_hh_l3 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_ih_l3 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_gru.bias_hh_l3 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_ih_l0 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_hh_l0 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_ih_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_hh_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_ih_l1 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_hh_l1 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_ih_l1 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_hh_l1 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_ih_l2 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_hh_l2 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_ih_l2 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_hh_l2 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_ih_l3 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.weight_hh_l3 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_ih_l3 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.motion_gru.bias_hh_l3 - torch.Size([1536]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches_ar.0.0.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches_ar.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches_ar.0.2.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches_ar.0.2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches_ar.0.4.weight - torch.Size([2, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_branches_ar.0.4.bias - torch.Size([2]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.0.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.3.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.4.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.4.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.6.weight - torch.Size([1, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.traj_cls_branches_ar.0.6.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder_ar.0.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder_ar.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder_ar.2.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder_ar.2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder_ar.4.weight - torch.Size([12, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.ego_fut_decoder_ar.4.bias - torch.Size([12]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.encoder.conv1.weight - torch.Size([1024, 512, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.encoder.conv1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.encoder.conv2.weight - torch.Size([1024, 1024, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.encoder.conv2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.encoder.conv3.weight - torch.Size([256, 1024, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.encoder.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.last_conv.1.weight - torch.Size([64, 256, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.present_distribution.last_conv.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.encoder.conv1.weight - torch.Size([1048, 524, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.encoder.conv1.bias - torch.Size([1048]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.encoder.conv2.weight - torch.Size([1048, 1048, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.encoder.conv2.bias - torch.Size([1048]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.encoder.conv3.weight - torch.Size([262, 1048, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.encoder.conv3.bias - torch.Size([262]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.last_conv.1.weight - torch.Size([64, 262, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_distribution.last_conv.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.0.conv_update.weight - torch.Size([512, 544, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.0.conv_update.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.0.conv_reset.weight - torch.Size([512, 544, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.0.conv_reset.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.0.conv_state_tilde.conv.weight - torch.Size([512, 544, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.0.conv_state_tilde.norm.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.0.conv_state_tilde.norm.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.1.conv_update.weight - torch.Size([512, 1024, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.1.conv_update.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.1.conv_reset.weight - torch.Size([512, 1024, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.1.conv_reset.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.1.conv_state_tilde.conv.weight - torch.Size([512, 1024, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.1.conv_state_tilde.norm.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.1.conv_state_tilde.norm.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.2.conv_update.weight - torch.Size([512, 1024, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.2.conv_update.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.2.conv_reset.weight - torch.Size([512, 1024, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.2.conv_reset.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.2.conv_state_tilde.conv.weight - torch.Size([512, 1024, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.2.conv_state_tilde.norm.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.spatial_grus.2.conv_state_tilde.norm.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.0.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.1.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.0.2.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.0.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.1.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.1.2.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.0.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.1.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.conv_down_project.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.abn_down_project.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.abn_down_project.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.abn.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.abn.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.conv_up_project.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.abn_up_project.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.future_prediction.res_blocks.2.2.layers.abn_up_project.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_ih_l0 - torch.Size([384, 32]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_hh_l0 - torch.Size([384, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_ih_l0 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_hh_l0 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_ih_l1 - torch.Size([384, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_hh_l1 - torch.Size([384, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_ih_l1 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_hh_l1 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_ih_l2 - torch.Size([384, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_hh_l2 - torch.Size([384, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_ih_l2 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_hh_l2 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_ih_l3 - torch.Size([384, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.weight_hh_l3 - torch.Size([384, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_ih_l3 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.gru.bias_hh_l3 - torch.Size([384]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.linear1.weight - torch.Size([256, 128]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.linear1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.linear2.weight - torch.Size([512, 256]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.linear2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.linear3.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of GenAD pts_bbox_head.predict_model.linear3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of GenAD img_backbone.conv1.weight - torch.Size([64, 3, 7, 7]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.downsample.1.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.0.downsample.1.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.downsample.1.weight - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.0.downsample.1.bias - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.downsample.1.weight - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.0.downsample.1.bias - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from ckpts/resnet50-19c8e357.pth img_neck.lateral_convs.0.conv.weight - torch.Size([256, 2048, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 img_neck.lateral_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD img_neck.fpn_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 img_neck.fpn_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of GenAD 2026-02-05 03:59:49,245 - mmdet - INFO - Model: GenAD( (pts_bbox_head): GenADHead( (loss_cls): FocalLoss() (loss_bbox): L1Loss() (loss_iou): GIoULoss() (activate): ReLU(inplace=True) (positional_encoding): LearnedPositionalEncoding(num_feats=128, row_num_embed=100, col_num_embed=100) (transformer): VADPerceptionTransformer( (encoder): BEVFormerEncoder( (layers): ModuleList( (0-2): 3 x BEVFormerLayer( (attentions): ModuleList( (0): TemporalSelfAttention( (dropout): Dropout(p=0.1, inplace=False) (sampling_offsets): Linear(in_features=512, out_features=128, bias=True) (attention_weights): Linear(in_features=512, out_features=64, bias=True) (value_proj): Linear(in_features=256, out_features=256, bias=True) (output_proj): Linear(in_features=256, out_features=256, bias=True) ) (1): SpatialCrossAttention( (dropout): Dropout(p=0.1, inplace=False) (deformable_attention): MSDeformableAttention3D( (sampling_offsets): Linear(in_features=256, out_features=128, bias=True) (attention_weights): Linear(in_features=256, out_features=64, bias=True) (value_proj): Linear(in_features=256, out_features=256, bias=True) ) (output_proj): Linear(in_features=256, out_features=256, bias=True) ) ) (ffns): ModuleList( (0): FFN( (activate): ReLU(inplace=True) (layers): Sequential( (0): Sequential( (0): Linear(in_features=256, out_features=512, bias=True) (1): ReLU(inplace=True) (2): Dropout(p=0.0, inplace=False) ) (1): Linear(in_features=512, out_features=256, bias=True) (2): Dropout(p=0.0, inplace=False) ) (dropout_layer): Identity() ) ) (norms): ModuleList( (0-2): 3 x LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) ) (decoder): DetectionTransformerDecoder( (layers): ModuleList( (0-2): 3 x DetrTransformerDecoderLayer( (attentions): ModuleList( (0): MultiheadAttention( (attn): MultiheadAttention( (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True) ) (proj_drop): Dropout(p=0.0, inplace=False) (dropout_layer): Dropout(p=0.0, inplace=False) ) (1): CustomMSDeformableAttention( (dropout): Dropout(p=0.1, inplace=False) (sampling_offsets): Linear(in_features=256, out_features=64, bias=True) (attention_weights): Linear(in_features=256, out_features=32, bias=True) (value_proj): Linear(in_features=256, out_features=256, bias=True) (output_proj): Linear(in_features=256, out_features=256, bias=True) ) ) (ffns): ModuleList( (0): FFN( (activate): ReLU(inplace=True) (layers): Sequential( (0): Sequential( (0): Linear(in_features=256, out_features=512, bias=True) (1): ReLU(inplace=True) (2): Dropout(p=0.0, inplace=False) ) (1): Linear(in_features=512, out_features=256, bias=True) (2): Dropout(p=0.0, inplace=False) ) (dropout_layer): Identity() ) ) (norms): ModuleList( (0-2): 3 x LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) ) (map_decoder): MapDetectionTransformerDecoder( (layers): ModuleList( (0-2): 3 x DetrTransformerDecoderLayer( (attentions): ModuleList( (0): MultiheadAttention( (attn): MultiheadAttention( (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True) ) (proj_drop): Dropout(p=0.0, inplace=False) (dropout_layer): Dropout(p=0.0, inplace=False) ) (1): CustomMSDeformableAttention( (dropout): Dropout(p=0.1, inplace=False) (sampling_offsets): Linear(in_features=256, out_features=64, bias=True) (attention_weights): Linear(in_features=256, out_features=32, bias=True) (value_proj): Linear(in_features=256, out_features=256, bias=True) (output_proj): Linear(in_features=256, out_features=256, bias=True) ) ) (ffns): ModuleList( (0): FFN( (activate): ReLU(inplace=True) (layers): Sequential( (0): Sequential( (0): Linear(in_features=256, out_features=512, bias=True) (1): ReLU(inplace=True) (2): Dropout(p=0.0, inplace=False) ) (1): Linear(in_features=512, out_features=256, bias=True) (2): Dropout(p=0.0, inplace=False) ) (dropout_layer): Identity() ) ) (norms): ModuleList( (0-2): 3 x LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) ) (reference_points): Linear(in_features=256, out_features=3, bias=True) (map_reference_points): Linear(in_features=256, out_features=2, bias=True) (can_bus_mlp): Sequential( (0): Linear(in_features=18, out_features=128, bias=True) (1): ReLU(inplace=True) (2): Linear(in_features=128, out_features=256, bias=True) (3): ReLU(inplace=True) (norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) (cls_branches): ModuleList( (0-2): 3 x Sequential( (0): Linear(in_features=256, out_features=256, bias=True) (1): LayerNorm((256,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=256, out_features=256, bias=True) (4): LayerNorm((256,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) (6): Linear(in_features=256, out_features=9, bias=True) ) ) (reg_branches): ModuleList( (0-2): 3 x Sequential( (0): Linear(in_features=256, out_features=256, bias=True) (1): ReLU() (2): Linear(in_features=256, out_features=256, bias=True) (3): ReLU() (4): Linear(in_features=256, out_features=10, bias=True) ) ) (traj_branches): ModuleList( (0): Sequential( (0): Linear(in_features=1024, out_features=1024, bias=True) (1): ReLU() (2): Linear(in_features=1024, out_features=1024, bias=True) (3): ReLU() (4): Linear(in_features=1024, out_features=2, bias=True) ) ) (traj_cls_branches): ModuleList( (0): Sequential( (0): Linear(in_features=3584, out_features=512, bias=True) (1): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=512, out_features=512, bias=True) (4): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) (6): Linear(in_features=512, out_features=1, bias=True) ) ) (map_cls_branches): ModuleList( (0-2): 3 x Sequential( (0): Linear(in_features=256, out_features=256, bias=True) (1): LayerNorm((256,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=256, out_features=256, bias=True) (4): LayerNorm((256,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) (6): Linear(in_features=256, out_features=6, bias=True) ) ) (map_reg_branches): ModuleList( (0-2): 3 x Sequential( (0): Linear(in_features=256, out_features=256, bias=True) (1): ReLU() (2): Linear(in_features=256, out_features=256, bias=True) (3): ReLU() (4): Linear(in_features=256, out_features=2, bias=True) ) ) (bev_embedding): Embedding(10000, 256) (query_embedding): Embedding(300, 512) (map_instance_embedding): Embedding(100, 512) (map_pts_embedding): Embedding(20, 512) (motion_decoder): CustomTransformerDecoder( (layers): ModuleList( (0): BaseTransformerLayer( (attentions): ModuleList( (0): MultiheadAttention( (attn): MultiheadAttention( (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True) ) (proj_drop): Dropout(p=0.0, inplace=False) (dropout_layer): Dropout(p=0.0, inplace=False) ) ) (ffns): ModuleList( (0): FFN( (activate): ReLU(inplace=True) (layers): Sequential( (0): Sequential( (0): Linear(in_features=256, out_features=512, bias=True) (1): ReLU(inplace=True) (2): Dropout(p=0.0, inplace=False) ) (1): Linear(in_features=512, out_features=256, bias=True) (2): Dropout(p=0.0, inplace=False) ) (dropout_layer): Identity() ) ) (norms): ModuleList( (0-1): 2 x LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) ) (motion_mode_query): Embedding(6, 256) (pos_mlp_sa): Linear(in_features=2, out_features=256, bias=True) (lane_encoder): LaneNet( (layer_seq): Sequential( (lmlp_0): MLP( (mlp): Sequential( (0): Linear(in_features=256, out_features=128, bias=True) (1): LayerNorm((128,), eps=1e-05, elementwise_affine=True) (2): ReLU() ) ) (lmlp_1): MLP( (mlp): Sequential( (0): Linear(in_features=256, out_features=128, bias=True) (1): LayerNorm((128,), eps=1e-05, elementwise_affine=True) (2): ReLU() ) ) (lmlp_2): MLP( (mlp): Sequential( (0): Linear(in_features=256, out_features=128, bias=True) (1): LayerNorm((128,), eps=1e-05, elementwise_affine=True) (2): ReLU() ) ) ) ) (motion_map_decoder): CustomTransformerDecoder( (layers): ModuleList( (0): BaseTransformerLayer( (attentions): ModuleList( (0): MultiheadAttention( (attn): MultiheadAttention( (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True) ) (proj_drop): Dropout(p=0.0, inplace=False) (dropout_layer): Dropout(p=0.0, inplace=False) ) ) (ffns): ModuleList( (0): FFN( (activate): ReLU(inplace=True) (layers): Sequential( (0): Sequential( (0): Linear(in_features=256, out_features=512, bias=True) (1): ReLU(inplace=True) (2): Dropout(p=0.0, inplace=False) ) (1): Linear(in_features=512, out_features=256, bias=True) (2): Dropout(p=0.0, inplace=False) ) (dropout_layer): Identity() ) ) (norms): ModuleList( (0-1): 2 x LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) ) (pos_mlp): Linear(in_features=2, out_features=256, bias=True) (ego_query): Embedding(1, 256) (ego_agent_decoder): CustomTransformerDecoder( (layers): ModuleList( (0): BaseTransformerLayer( (attentions): ModuleList( (0): MultiheadAttention( (attn): MultiheadAttention( (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True) ) (proj_drop): Dropout(p=0.0, inplace=False) (dropout_layer): Dropout(p=0.0, inplace=False) ) ) (ffns): ModuleList( (0): FFN( (activate): ReLU(inplace=True) (layers): Sequential( (0): Sequential( (0): Linear(in_features=256, out_features=512, bias=True) (1): ReLU(inplace=True) (2): Dropout(p=0.0, inplace=False) ) (1): Linear(in_features=512, out_features=256, bias=True) (2): Dropout(p=0.0, inplace=False) ) (dropout_layer): Identity() ) ) (norms): ModuleList( (0-1): 2 x LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) ) (ego_agent_pos_mlp): Linear(in_features=2, out_features=256, bias=True) (ego_map_decoder): CustomTransformerDecoder( (layers): ModuleList( (0): BaseTransformerLayer( (attentions): ModuleList( (0): MultiheadAttention( (attn): MultiheadAttention( (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True) ) (proj_drop): Dropout(p=0.0, inplace=False) (dropout_layer): Dropout(p=0.0, inplace=False) ) ) (ffns): ModuleList( (0): FFN( (activate): ReLU(inplace=True) (layers): Sequential( (0): Sequential( (0): Linear(in_features=256, out_features=512, bias=True) (1): ReLU(inplace=True) (2): Dropout(p=0.0, inplace=False) ) (1): Linear(in_features=512, out_features=256, bias=True) (2): Dropout(p=0.0, inplace=False) ) (dropout_layer): Identity() ) ) (norms): ModuleList( (0-1): 2 x LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) ) (ego_map_pos_mlp): Linear(in_features=2, out_features=256, bias=True) (ego_fut_decoder): Sequential( (0): Linear(in_features=1024, out_features=1024, bias=True) (1): ReLU() (2): Linear(in_features=1024, out_features=1024, bias=True) (3): ReLU() (4): Linear(in_features=1024, out_features=12, bias=True) ) (agent_fus_mlp): Sequential( (0): Linear(in_features=3072, out_features=256, bias=True) (1): LayerNorm((256,), eps=1e-05, elementwise_affine=True) (2): ReLU() (3): Linear(in_features=256, out_features=256, bias=True) ) (ego_coord_mlp): Linear(in_features=2, out_features=2, bias=True) (state_gru): GRU(32, 512, num_layers=4) (ego_gru): GRU(512, 512, num_layers=4) (motion_gru): GRU(512, 512, num_layers=4) (traj_branches_ar): ModuleList( (0): Sequential( (0): Linear(in_features=512, out_features=512, bias=True) (1): ReLU() (2): Linear(in_features=512, out_features=512, bias=True) (3): ReLU() (4): Linear(in_features=512, out_features=2, bias=True) ) ) (traj_cls_branches_ar): ModuleList( (0): Sequential( (0): Linear(in_features=512, out_features=512, bias=True) (1): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=512, out_features=512, bias=True) (4): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) (6): Linear(in_features=512, out_features=1, bias=True) ) ) (ego_fut_decoder_ar): Sequential( (0): Linear(in_features=512, out_features=512, bias=True) (1): ReLU() (2): Linear(in_features=512, out_features=512, bias=True) (3): ReLU() (4): Linear(in_features=512, out_features=12, bias=True) ) (present_distribution): DistributionModule( (encoder): DistributionEncoder1DV2( (conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,)) (conv2): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,)) (conv3): Conv1d(1024, 256, kernel_size=(1,), stride=(1,)) (relu): ReLU(inplace=True) ) (last_conv): Sequential( (0): AdaptiveAvgPool1d(output_size=1) (1): Conv1d(256, 64, kernel_size=(1,), stride=(1,)) ) ) (future_distribution): DistributionModule( (encoder): DistributionEncoder1DV2( (conv1): Conv1d(524, 1048, kernel_size=(1,), stride=(1,)) (conv2): Conv1d(1048, 1048, kernel_size=(1,), stride=(1,)) (conv3): Conv1d(1048, 262, kernel_size=(1,), stride=(1,)) (relu): ReLU(inplace=True) ) (last_conv): Sequential( (0): AdaptiveAvgPool1d(output_size=1) (1): Conv1d(262, 64, kernel_size=(1,), stride=(1,)) ) ) (future_prediction): FuturePrediction( (spatial_grus): ModuleList( (0): SpatialGRU( (conv_update): Conv2d(544, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_reset): Conv2d(544, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_state_tilde): ConvBlock( (conv): Conv2d(544, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activation): ReLU(inplace=True) ) ) (1-2): 2 x SpatialGRU( (conv_update): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_reset): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_state_tilde): ConvBlock( (conv): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activation): ReLU(inplace=True) ) ) ) (res_blocks): ModuleList( (0-2): 3 x Sequential( (0): Bottleneck( (layers): Sequential( (conv_down_project): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (abn_down_project): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (abn): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (conv_up_project): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (abn_up_project): Sequential( (0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (dropout): Dropout2d(p=0.0, inplace=False) ) ) (1): Bottleneck( (layers): Sequential( (conv_down_project): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (abn_down_project): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (abn): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (conv_up_project): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (abn_up_project): Sequential( (0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (dropout): Dropout2d(p=0.0, inplace=False) ) ) (2): Bottleneck( (layers): Sequential( (conv_down_project): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (abn_down_project): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (abn): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (conv_up_project): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (abn_up_project): Sequential( (0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace=True) ) (dropout): Dropout2d(p=0.0, inplace=False) ) ) ) ) ) (predict_model): PredictModel( (gru): GRU(32, 128, num_layers=4) (linear1): Linear(in_features=128, out_features=256, bias=True) (linear2): Linear(in_features=256, out_features=512, bias=True) (linear3): Linear(in_features=512, out_features=512, bias=True) (relu): ReLU(inplace=True) ) (loss_traj): L1Loss() (loss_traj_cls): FocalLoss() (loss_map_bbox): L1Loss() (loss_map_cls): FocalLoss() (loss_map_iou): GIoULoss() (loss_map_pts): PtsL1Loss() (loss_map_dir): PtsDirCosLoss() (loss_plan_reg): L1Loss() (loss_plan_bound): PlanMapBoundLoss() (loss_plan_col): PlanCollisionLoss() (loss_plan_dir): PlanMapDirectionLoss() (loss_vae_gen): ProbabilisticLoss() ) (img_backbone): ResNet( (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) (layer1): ResLayer( (0): Bottleneck( (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (downsample): Sequential( (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (1): Bottleneck( (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (2): Bottleneck( (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} ) (layer2): ResLayer( (0): Bottleneck( (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (downsample): Sequential( (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (1): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (2): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (3): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} ) (layer3): ResLayer( (0): Bottleneck( (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (downsample): Sequential( (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (1): Bottleneck( (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (2): Bottleneck( (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (3): Bottleneck( (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (4): Bottleneck( (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (5): Bottleneck( (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} ) (layer4): ResLayer( (0): Bottleneck( (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (downsample): Sequential( (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (1): Bottleneck( (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} (2): Bottleneck( (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}} ) ) init_cfg={'type': 'Pretrained', 'checkpoint': 'ckpts/resnet50-19c8e357.pth'} (img_neck): FPN( (lateral_convs): ModuleList( (0): ConvModule( (conv): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1)) ) ) (fpn_convs): ModuleList( (0): ConvModule( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) ) init_cfg={'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} (grid_mask): GridMask() )