2024-09-21 17:32:30,446 - mmdet - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.8.19 (default, Mar 20 2024, 19:58:24) [GCC 11.2.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: NVIDIA RTX A5000 CUDA_HOME: /data/home/hanbo/cuda-11.6 NVCC: Cuda compilation tools, release 11.6, V11.6.55 GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0 PyTorch: 1.12.1+cu116 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.6 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.3.2 (built against CUDA 11.5) - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.13.1+cu116 OpenCV: 4.10.0 MMCV: 1.7.2 MMCV Compiler: GCC 9.3 MMCV CUDA Compiler: 11.6 MMDetection: 2.28.2+d592e33 ------------------------------------------------------------ 2024-09-21 17:32:31,819 - mmdet - INFO - Distributed training: True 2024-09-21 17:32:33,172 - mmdet - INFO - Config: norm_cfg = dict( type='BN', requires_grad=False, mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True) model = dict( type='FasterRCNNRelAfford', backbone=dict( type='mmdet.ResNet', depth=101, num_stages=3, strides=(1, 2, 2), dilations=(1, 1, 1), out_indices=(2, ), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, style='caffe', init_cfg=dict( type='Pretrained', checkpoint='open-mmlab://detectron2/resnet101_caffe')), rpn_head=dict( type='mmdet.RPNHead', in_channels=1024, feat_channels=1024, anchor_generator=dict( type='AnchorGenerator', scales=[8, 16, 32], ratios=[0.33, 0.5, 1.0, 2.0, 3.0], strides=[16]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='mmdet.CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type='mmdet.L1Loss', loss_weight=1.0)), roi_head=None, child_head=dict( type='invigorate.PairedRoIHead', shared_head=dict( type='invigorate.PairedResLayer', depth=50, stage=3, stride=1, style='caffe', norm_eval=False, share_weights=False), paired_roi_extractor=dict( type='invigorate.VMRNPairedRoIExtractor', roi_layer=dict(type='RoIPool', output_size=7), out_channels=1024, featmap_strides=[16]), relation_head=dict( type='invigorate.BBoxPairHead', with_avg_pool=True, roi_feat_size=7, in_channels=2048, num_relations=1, loss_cls=dict( type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0))), leaf_head=dict( type='mmdet.StandardRoIHead', shared_head=dict( type='mmdet.ResLayer', depth=50, stage=3, stride=1, style='caffe', norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True), bbox_roi_extractor=dict( type='mmdet.SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=1024, featmap_strides=[16]), bbox_head=dict( type='mmdet.BBoxHead', with_avg_pool=True, with_reg=False, roi_feat_size=7, in_channels=2048, num_classes=2, loss_cls=dict( type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0))), train_cfg=dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=256, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=False), allowed_border=0, pos_weight=-1, debug=False), rpn_proposal=dict( nms_pre=12000, max_per_img=2000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.5, match_low_quality=False, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=256, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False), child_head=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.5, min_pos_iou=0.7, match_low_quality=False, ignore_iof_thr=-1), relation_sampler=dict( type='RandomRelationSampler', num=32, pos_fraction=0.5, cls_ratio_ub=1.0, add_gt_as_proposals=True, num_relation_cls=1, neg_id=0), pos_weight=-1, online_data=True, online_start_iteration=0), leaf_head=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.5, match_low_quality=False, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=64, pos_fraction=0.25, neg_pos_ub=3.0, add_gt_as_proposals=True), pos_weight=-1, debug=False)), test_cfg=dict( rpn=dict( nms_pre=6000, max_per_img=300, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_threshold=0.3), max_per_img=100), child_head=dict( bbox_score_thr=0.5, verbose_relation=False, average_scores=False), leaf_head=dict(score_thr=0.5, nms=None, max_per_img=100))) dataset_type = 'REGRADAffordDataset' data_root = 'data/regrad/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=['gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict(type='RandomFlip', flip_ratio=0.5), dict(type='PhotoMetricDistortion'), dict( type='RandomCrop', crop_type='random_keep', allow_negative_crop=False), dict(type='Expand', mean=[123.675, 116.28, 103.53], ratio_range=(1, 2)), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict( type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ] data = dict( train=dict( _delete_=True, type='ConcatDataset', datasets=[ dict( type='REGRADAffordDataset', data_root='data/regrad/', meta_info_file='dataset_train_5k/meta_infos.json', ann_file='dataset_train_5k/objects.json', img_prefix='dataset_train_5k/RGBImages', seg_prefix='dataset_train_5k/SegmentationImages', depth_prefix='dataset_train_5k/DepthImages', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=[ 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict(type='RandomFlip', flip_ratio=0.5), dict(type='PhotoMetricDistortion'), dict( type='RandomCrop', crop_type='random_keep', allow_negative_crop=False), dict(type='Expand', mean=[123.675, 116.28, 103.53]), dict( type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], min_pos_relation=1, class_agnostic=True), dict( type='MetaGraspNetAffordDataset', data_root='data/metagraspnet/sim/', meta_info_file='meta_infos_train.json', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=[ 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict(type='RandomFlip', flip_ratio=0.5), dict(type='PhotoMetricDistortion'), dict( type='RandomCrop', crop_type='random_keep', allow_negative_crop=False), dict( type='Expand', mean=[123.675, 116.28, 103.53], ratio_range=(1, 2)), dict( type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], min_pos_relation=1, class_agnostic=True), dict( type='VMRDAffordDataset', ann_file='data/vmrd/ImageSets/Main/trainval.txt', img_prefix='data/vmrd/', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=[ 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict(type='RandomFlip', flip_ratio=0.5), dict(type='PhotoMetricDistortion'), dict(type='Expand', mean=[123.675, 116.28, 103.53]), dict( type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], class_agnostic=True), dict( type='VRDAffordDataset', data_root='data/vrd/', ann_file='sg_dataset/sg_train_annotations.json', img_prefix='sg_dataset/sg_train_images/', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=[ 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], class_agnostic=True), dict( type='VGAffordDataset', data_root='data/vg/downloads', ann_file='relationships.json', img_prefix='', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=[ 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], class_agnostic=True) ], separate_eval=True, class_agnostic=True), val=dict( _delete_=True, type='ConcatDataset', datasets=[ dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='dataset_seen_val_1k/meta_infos.json', ann_file='dataset_seen_val_1k/objects.json', img_prefix='dataset_seen_val_1k/RGBImages', seg_prefix='dataset_seen_val_1k/SegmentationImages', depth_prefix='dataset_seen_val_1k/DepthImages', test_mode=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict( type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True, max_sample_num=1000), dict( type='VMRDAffordDataset', ann_file='data/vmrd/ImageSets/Main/test.txt', img_prefix='data/vmrd/', using_gt_proposals=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict( type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True) ], separate_eval=True, class_agnostic=True), test=dict( _delete_=True, type='ConcatDataset', datasets=[ dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='dataset_seen_val_1k/meta_infos.json', ann_file='dataset_seen_val_1k/objects.json', img_prefix='dataset_seen_val_1k/RGBImages', seg_prefix='dataset_seen_val_1k/SegmentationImages', depth_prefix='dataset_seen_val_1k/DepthImages', test_mode=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict( type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True, max_sample_num=1000), dict( type='VMRDAffordDataset', ann_file='data/vmrd/ImageSets/Main/test.txt', img_prefix='data/vmrd/', using_gt_proposals=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict( type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True) ], separate_eval=True, class_agnostic=True), samples_per_gpu=4, workers_per_gpu=2) evaluation = dict(interval=1, metric=['mAP', 'ImgAcc']) optimizer = dict(type='SGD', lr=0.005, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=100, norm_type=2)) lr_config = dict( policy='step', warmup='linear', warmup_iters=4000, warmup_ratio=0.001, step=[12, 18]) runner = dict(type='EpochBasedRunner', max_epochs=20) checkpoint_config = dict(interval=1, max_keep_ckpts=5) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] opencv_num_threads = 0 mp_start_method = 'fork' auto_scale_lr = dict(enable=False, base_batch_size=16) mmdet = None mmdet_root = '/data/home/hanbo/projects/cloud_services/service/vmrn/vmrn_models/mmdetection/mmdet' test_with_object_detector = False test_crop_config = (174, 79, 462, 372) kinect_img_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='FixedCrop', crop_type='absolute', top_left=(174, 79), bottom_right=(462, 372)), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ] seen_val_dataset = dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='dataset_seen_val_1k/meta_infos.json', ann_file='dataset_seen_val_1k/objects.json', img_prefix='dataset_seen_val_1k/RGBImages', seg_prefix='dataset_seen_val_1k/SegmentationImages', depth_prefix='dataset_seen_val_1k/DepthImages', test_mode=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True, max_sample_num=1000) unseen_val_dataset = dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='dataset_unseen_val_1k/meta_infos.json', ann_file='dataset_unseen_val_1k/objects.json', img_prefix='dataset_unseen_val_1k/RGBImages', seg_prefix='dataset_unseen_val_1k/SegmentationImages', depth_prefix='dataset_unseen_val_1k/DepthImages', test_mode=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True, max_sample_num=1000) real_val_dataset = dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='real/meta_infos.json', ann_file='real/objects.json', img_prefix='real/RGBImages', img_suffix='png', depth_prefix='real/DepthImages', test_mode=True, test_gt_bbox_offset=(174, 79), pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='FixedCrop', crop_type='absolute', top_left=(174, 79), bottom_right=(462, 372)), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True) regrad_datatype = 'REGRADAffordDataset' regrad_root = 'data/regrad/' vmrd_datatype = 'VMRDAffordDataset' vmrd_root = 'data/vmrd/' vmrd_train = dict( type='VMRDAffordDataset', ann_file='data/vmrd/ImageSets/Main/trainval.txt', img_prefix='data/vmrd/', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=['gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict(type='RandomFlip', flip_ratio=0.5), dict(type='PhotoMetricDistortion'), dict(type='Expand', mean=[123.675, 116.28, 103.53]), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], class_agnostic=True) regrad_train = dict( type='REGRADAffordDataset', data_root='data/regrad/', meta_info_file='dataset_train_5k/meta_infos.json', ann_file='dataset_train_5k/objects.json', img_prefix='dataset_train_5k/RGBImages', seg_prefix='dataset_train_5k/SegmentationImages', depth_prefix='dataset_train_5k/DepthImages', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=['gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict(type='RandomFlip', flip_ratio=0.5), dict(type='PhotoMetricDistortion'), dict( type='RandomCrop', crop_type='random_keep', allow_negative_crop=False), dict(type='Expand', mean=[123.675, 116.28, 103.53]), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], min_pos_relation=1, class_agnostic=True) metagraspnet_sim_train = dict( type='MetaGraspNetAffordDataset', data_root='data/metagraspnet/sim/', meta_info_file='meta_infos_train.json', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=['gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict(type='RandomFlip', flip_ratio=0.5), dict(type='PhotoMetricDistortion'), dict( type='RandomCrop', crop_type='random_keep', allow_negative_crop=False), dict( type='Expand', mean=[123.675, 116.28, 103.53], ratio_range=(1, 2)), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], min_pos_relation=1, class_agnostic=True) vgvrd_train_pipeline = [ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=['gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict(type='RandomFlip', flip_ratio=0.5), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict( type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']) ] vrd_train = dict( type='VRDAffordDataset', data_root='data/vrd/', ann_file='sg_dataset/sg_train_annotations.json', img_prefix='sg_dataset/sg_train_images/', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=['gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict(type='RandomFlip', flip_ratio=0.5), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], class_agnostic=True) vg_train = dict( type='VGAffordDataset', data_root='data/vg/downloads', ann_file='relationships.json', img_prefix='', pipeline=[ dict(type='LoadImageFromFile', to_float32=True), dict( type='LoadAnnotationsCustom', keys=['gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves']), dict(type='RandomFlip', flip_ratio=0.5), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict( type='DefaultFormatBundleCustom', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_relchilds', 'gt_relleaves' ]) ], class_agnostic=True) real_test_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='FixedCrop', crop_type='absolute', top_left=(174, 79), bottom_right=(462, 372)), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ] regrad_seen_val_dataset = dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='dataset_seen_val_1k/meta_infos.json', ann_file='dataset_seen_val_1k/objects.json', img_prefix='dataset_seen_val_1k/RGBImages', seg_prefix='dataset_seen_val_1k/SegmentationImages', depth_prefix='dataset_seen_val_1k/DepthImages', test_mode=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True, max_sample_num=1000) regrad_unseen_val_dataset = dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='dataset_unseen_val_1k/meta_infos.json', ann_file='dataset_unseen_val_1k/objects.json', img_prefix='dataset_unseen_val_1k/RGBImages', seg_prefix='dataset_unseen_val_1k/SegmentationImages', depth_prefix='dataset_unseen_val_1k/DepthImages', test_mode=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True, max_sample_num=1000) regrad_real_val_dataset = dict( type='REGRADAffordDataset', data_root='data/regrad/', using_depth=False, using_gt_proposals=True, meta_info_file='real/meta_infos.json', ann_file='real/objects.json', img_prefix='real/RGBImages', img_suffix='png', depth_prefix='real/DepthImages', test_mode=True, test_gt_bbox_offset=(174, 79), pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='FixedCrop', crop_type='absolute', top_left=(174, 79), bottom_right=(462, 372)), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True) vmrd_val_dataset = dict( type='VMRDAffordDataset', ann_file='data/vmrd/ImageSets/Main/test.txt', img_prefix='data/vmrd/', using_gt_proposals=True, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadRelationProposals'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img', 'relation_proposals']) ]) ], class_agnostic=True) train_sampler = dict( type='DistributedWeightedSampler', weights=[0.1, 0.1, 0.05, 0.05, 0.7], sample_per_epoch=150000, shuffle=True) work_dir = './work_dirs/relation_afford_r101_caffe_c4_1x_regrad_vmrd_metagraspnet_vrd_vg_class_agnostic' gpu_ids = range(0, 8)