train_dataset_type = 'MultiViewCocoDataset' test_dataset_type = 'CocoDataset' data_root = 'data/coco/' classes = ['selective_search'] img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) load_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=False) ] train_pipeline1 = [ dict( type='Resize', img_scale=[(1600, 400), (1600, 1400)], multiscale_mode='range', keep_ratio=True), dict(type='FilterAnnotations', min_gt_bbox_wh=(0.01, 0.01)), dict(type='Pad', size_divisor=32), dict(type='RandFlip', flip_ratio=0.5), dict( type='OneOf', transforms=[ dict(type='Identity'), dict(type='AutoContrast'), dict(type='RandEqualize'), dict(type='RandSolarize'), dict(type='RandColor'), dict(type='RandContrast'), dict(type='RandBrightness'), dict(type='RandSharpness'), dict(type='RandPosterize') ]), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] train_pipeline2 = [ dict( type='Resize', img_scale=[(1600, 400), (1600, 1400)], multiscale_mode='range', keep_ratio=True), dict(type='FilterAnnotations', min_gt_bbox_wh=(0.01, 0.01)), dict(type='Pad', size_divisor=32), dict(type='RandFlip', flip_ratio=0.5), dict( type='OneOf', transforms=[ dict(type='Identity'), dict(type='AutoContrast'), dict(type='RandEqualize'), dict(type='RandSolarize'), dict(type='RandColor'), dict(type='RandContrast'), dict(type='RandBrightness'), dict(type='RandSharpness'), dict(type='RandPosterize') ]), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=2, workers_per_gpu=2, train=dict( type='MultiViewCocoDataset', dataset=dict( type='CocoDataset', classes=['selective_search'], ann_file= 'data/coco/filtered_proposals/train2017_ratio3size0008@0.5.json', img_prefix='data/coco/train2017/', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=False) ]), num_views=2, pipelines=[[{ 'type': 'Resize', 'img_scale': [(1600, 400), (1600, 1400)], 'multiscale_mode': 'range', 'keep_ratio': True }, { 'type': 'FilterAnnotations', 'min_gt_bbox_wh': (0.01, 0.01) }, { 'type': 'Pad', 'size_divisor': 32 }, { 'type': 'RandFlip', 'flip_ratio': 0.5 }, { 'type': 'OneOf', 'transforms': [{ 'type': 'Identity' }, { 'type': 'AutoContrast' }, { 'type': 'RandEqualize' }, { 'type': 'RandSolarize' }, { 'type': 'RandColor' }, { 'type': 'RandContrast' }, { 'type': 'RandBrightness' }, { 'type': 'RandSharpness' }, { 'type': 'RandPosterize' }] }, { 'type': 'Normalize', 'mean': [123.675, 116.28, 103.53], 'std': [58.395, 57.12, 57.375], 'to_rgb': True }, { 'type': 'DefaultFormatBundle' }, { 'type': 'Collect', 'keys': ['img', 'gt_bboxes', 'gt_labels'] }], [{ 'type': 'Resize', 'img_scale': [(1600, 400), (1600, 1400)], 'multiscale_mode': 'range', 'keep_ratio': True }, { 'type': 'FilterAnnotations', 'min_gt_bbox_wh': (0.01, 0.01) }, { 'type': 'Pad', 'size_divisor': 32 }, { 'type': 'RandFlip', 'flip_ratio': 0.5 }, { 'type': 'OneOf', 'transforms': [{ 'type': 'Identity' }, { 'type': 'AutoContrast' }, { 'type': 'RandEqualize' }, { 'type': 'RandSolarize' }, { 'type': 'RandColor' }, { 'type': 'RandContrast' }, { 'type': 'RandBrightness' }, { 'type': 'RandSharpness' }, { 'type': 'RandPosterize' }] }, { 'type': 'Normalize', 'mean': [123.675, 116.28, 103.53], 'std': [58.395, 57.12, 57.375], 'to_rgb': True }, { 'type': 'DefaultFormatBundle' }, { 'type': 'Collect', 'keys': ['img', 'gt_bboxes', 'gt_labels'] }]]), val=dict( type='CocoDataset', classes=['selective_search'], ann_file='data/coco/annotations/instances_val2017.json', img_prefix='data/coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( type='CocoDataset', classes=['selective_search'], ann_file='data/coco/annotations/instances_val2017.json', img_prefix='data/coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) evaluation = dict(interval=65535, gpu_collect=True) optimizer = dict( type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05, paramwise_cfg=dict( custom_keys=dict( absolute_pos_embed=dict(decay_mult=0.0), relative_position_bias_table=dict(decay_mult=0.0), norm=dict(decay_mult=0.0)))) optimizer_config = dict(grad_clip=None) lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.001, step=[8, 11]) runner = dict(type='EpochBasedRunner', max_epochs=12) checkpoint_config = dict(interval=1) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) custom_hooks = [ dict(type='MomentumUpdateHook'), dict( type='MMDetWandbHook', init_kwargs=dict(project='I2B', group='pretrain'), interval=50, num_eval_images=0, log_checkpoint=False) ] 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=True, base_batch_size=16) custom_imports = dict( imports=[ 'mmselfsup.datasets.pipelines', 'selfsup.core.hook.momentum_update_hook', 'selfsup.datasets.pipelines.selfsup_pipelines', 'selfsup.datasets.pipelines.rand_aug', 'selfsup.datasets.single_view_coco', 'selfsup.datasets.multi_view_coco', 'selfsup.models.losses.contrastive_loss', 'selfsup.models.dense_heads.fcos_head', 'selfsup.models.dense_heads.retina_head', 'selfsup.models.dense_heads.detr_head', 'selfsup.models.dense_heads.deformable_detr_head', 'selfsup.models.roi_heads.bbox_heads.convfc_bbox_head', 'selfsup.models.roi_heads.standard_roi_head', 'selfsup.models.roi_heads.htc_roi_head', 'selfsup.models.roi_heads.cbv2_roi_head', 'selfsup.models.necks.cb_fpn', 'selfsup.models.backbones.cbv2', 'selfsup.models.backbones.swinv1', 'selfsup.models.detectors.selfsup_detector', 'selfsup.models.detectors.selfsup_fcos', 'selfsup.models.detectors.selfsup_detr', 'selfsup.models.detectors.selfsup_deformable_detr', 'selfsup.models.detectors.selfsup_retinanet', 'selfsup.models.detectors.selfsup_mask_rcnn', 'selfsup.models.detectors.selfsup_htc', 'selfsup.models.detectors.selfsup_cbv2', 'selfsup.models.detectors.cbv2', 'selfsup.core.bbox.assigners.hungarian_assigner', 'selfsup.core.bbox.assigners.pseudo_hungarian_assigner', 'selfsup.core.bbox.match_costs.match_cost' ], allow_failed_imports=False) model = dict( type='SelfSupDetector', backbone=dict( type='SelfSupCBv2', backbone=dict( type='CBSwinTransformer', embed_dim=192, depths=[2, 2, 18, 2], num_heads=[6, 12, 24, 48], window_size=7, mlp_ratio=4.0, qkv_bias=True, qk_scale=None, drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.2, ape=False, patch_norm=True, out_indices=(0, 1, 2, 3), pretrained= 'https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22k.pth', use_checkpoint=False), neck=dict( type='CBFPN', in_channels=[192, 384, 768, 1536], out_channels=256, num_outs=5), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[8], ratios=[0.5, 1.0, 2.0], strides=[4, 8, 16, 32, 64]), 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='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict( type='SmoothL1Loss', beta=0.1111111111111111, loss_weight=1.0)), roi_head=dict( type='SelfSupCBv2Head', interleaved=True, mask_info_flow=True, num_stages=3, stage_loss_weights=[1, 0.5, 0.25], bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict( type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=[ dict( type='SelfSupShared4Conv1FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=256, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.1, 0.1, 0.2, 0.2]), reg_class_agnostic=True, loss_cls=dict( type='ContrastiveLoss', loss_weight=1.0, temperature=0.5), loss_bbox=dict( type='SmoothL1Loss', beta=1.0, loss_weight=1.0)), dict( type='SelfSupShared4Conv1FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=256, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.05, 0.05, 0.1, 0.1]), reg_class_agnostic=True, loss_cls=dict( type='ContrastiveLoss', loss_weight=1.0, temperature=0.5), loss_bbox=dict( type='SmoothL1Loss', beta=1.0, loss_weight=1.0)), dict( type='SelfSupShared4Conv1FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=256, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.033, 0.033, 0.067, 0.067]), reg_class_agnostic=True, loss_cls=dict( type='ContrastiveLoss', loss_weight=1.0, temperature=0.5), loss_bbox=dict( type='SmoothL1Loss', beta=1.0, loss_weight=1.0)) ], mask_roi_extractor=None, mask_head=None), train_cfg=dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, 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=2000, 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, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, pos_weight=-1, debug=False), dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.6, neg_iou_thr=0.6, min_pos_iou=0.6, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, pos_weight=-1, debug=False), dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.7, min_pos_iou=0.7, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, pos_weight=-1, debug=False) ]), test_cfg=dict( rpn=dict( nms_pre=1000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( score_thr=0.001, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100, mask_thr_binary=0.5)))) find_unused_parameters = True fp16 = dict(loss_scale='dynamic') work_dir = 'work_dirs/selfsup_cbv2_swin-L_1x_coco' auto_resume = False gpu_ids = range(0, 64)