model = dict( type='DETR', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(3, ), frozen_stages=1, norm_cfg=dict(type='SyncBN', requires_grad=True), norm_eval=True, style='pytorch', init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), bbox_head=dict( type='DETRHead', num_classes=20, in_channels=2048, transformer=dict( type='Transformer', encoder=dict( type='DetrTransformerEncoder', num_layers=6, transformerlayers=dict( type='BaseTransformerLayer', attn_cfgs=[ dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.1) ], feedforward_channels=2048, ffn_dropout=0.1, operation_order=('self_attn', 'norm', 'ffn', 'norm'))), decoder=dict( type='DetrTransformerDecoder', return_intermediate=True, num_layers=6, transformerlayers=dict( type='DetrTransformerDecoderLayer', attn_cfgs=dict( type='MultiheadAttention', embed_dims=256, num_heads=8, dropout=0.1), feedforward_channels=2048, ffn_dropout=0.1, operation_order=('self_attn', 'norm', 'cross_attn', 'norm', 'ffn', 'norm')))), positional_encoding=dict( type='SinePositionalEncoding', num_feats=128, normalize=True), loss_cls=dict( type='CrossEntropyLoss', bg_cls_weight=0.1, use_sigmoid=False, loss_weight=1.0, class_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=5.0), loss_iou=dict(type='GIoULoss', loss_weight=2.0)), train_cfg=dict( assigner=dict( type='HungarianAssigner', cls_cost=dict(type='ClassificationCost', weight=1.0), reg_cost=dict(type='BBoxL1Cost', weight=5.0, box_format='xywh'), iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))), test_cfg=dict(max_per_img=100)) dataset_type = 'VOCDataset' data_root = 'data/VOCdevkit/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576), (1333, 608), (1333, 640), (1333, 672), (1333, 704), (1333, 736), (1333, 768), (1333, 800)], multiscale_mode='value', keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), 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='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='VOCDataset', ann_file=[ 'data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt', 'data/VOCdevkit/VOC2012/ImageSets/Main/trainval.txt' ], img_prefix=['data/VOCdevkit/VOC2007/', 'data/VOCdevkit/VOC2012/'], pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576), (1333, 608), (1333, 640), (1333, 672), (1333, 704), (1333, 736), (1333, 768), (1333, 800)], multiscale_mode='value', keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), 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='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ]), val=dict( type='VOCDataset', ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt', img_prefix='data/VOCdevkit/VOC2007/', 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='VOCDataset', ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt', img_prefix='data/VOCdevkit/VOC2007/', 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=1, metric='mAP', save_best='auto') checkpoint_config = dict(interval=1) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) custom_hooks = [ dict(type='NumClassCheckHook'), dict( type='MMDetWandbHook', init_kwargs=dict(project='I2B', group='finetune'), interval=50, num_eval_images=0, log_checkpoint=False) ] dist_params = dict(backend='nccl') log_level = 'INFO' load_from = 'pretrain/selfsup_detr_clusters-as-classes_add-contrastive-temp0.5-weight1.0/final_model.pth' resume_from = None workflow = [('train', 1)] opencv_num_threads = 0 mp_start_method = 'fork' auto_scale_lr = dict(enable=False, base_batch_size=16) custom_imports = None norm_cfg = dict(type='SyncBN', requires_grad=True) optimizer = dict( type='AdamW', lr=0.0001, weight_decay=0.0001, paramwise_cfg=dict( custom_keys=dict(backbone=dict(lr_mult=0.1, decay_mult=1.0)))) optimizer_config = dict(grad_clip=None) lr_config = dict(policy='step', step=[70]) runner = dict(type='EpochBasedRunner', max_epochs=100) work_dir = 'work_dirs/finetune_detr_100e_voc0712' auto_resume = False gpu_ids = range(0, 8)