Upload with huggingface_hub

pretrain/selfsup_detr_cluster-ids-as-pseudo-labels/detr_pseudo_label.py

@@ -0,0 +1,424 @@
+model = dict(
+    type='DETR',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        frozen_stages=4,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    bbox_head=dict(
+        type='DETRHead',
+        num_classes=256,
+        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 = 'CocoDataset'
+data_root = 'data/coco/'
+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='RandomFlip', flip_ratio=0.5),
+    dict(
+        type='AutoAugment',
+        policies=[[{
+            'type':
+            'Resize',
+            'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333),
+                          (608, 1333), (640, 1333), (672, 1333), (704, 1333),
+                          (736, 1333), (768, 1333), (800, 1333)],
+            'multiscale_mode':
+            'value',
+            'keep_ratio':
+            True
+        }],
+                  [{
+                      'type': 'Resize',
+                      'img_scale': [(400, 1333), (500, 1333), (600, 1333)],
+                      'multiscale_mode': 'value',
+                      'keep_ratio': True
+                  }, {
+                      'type': 'RandomCrop',
+                      'crop_type': 'absolute_range',
+                      'crop_size': (384, 600),
+                      'allow_negative_crop': True
+                  }, {
+                      'type':
+                      'Resize',
+                      'img_scale': [(480, 1333), (512, 1333), (544, 1333),
+                                    (576, 1333), (608, 1333), (640, 1333),
+                                    (672, 1333), (704, 1333), (736, 1333),
+                                    (768, 1333), (800, 1333)],
+                      'multiscale_mode':
+                      'value',
+                      'override':
+                      True,
+                      'keep_ratio':
+                      True
+                  }]]),
+    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=1),
+    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='CocoDataset',
+        ann_file='train2017_ratio3size0008@0.5_cluster-id-as-class.json',
+        img_prefix='data/coco/train2017/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            dict(
+                type='AutoAugment',
+                policies=[[{
+                    'type':
+                    'Resize',
+                    'img_scale': [(480, 1333), (512, 1333), (544, 1333),
+                                  (576, 1333), (608, 1333), (640, 1333),
+                                  (672, 1333), (704, 1333), (736, 1333),
+                                  (768, 1333), (800, 1333)],
+                    'multiscale_mode':
+                    'value',
+                    'keep_ratio':
+                    True
+                }],
+                          [{
+                              'type': 'Resize',
+                              'img_scale': [(400, 1333), (500, 1333),
+                                            (600, 1333)],
+                              'multiscale_mode': 'value',
+                              'keep_ratio': True
+                          }, {
+                              'type': 'RandomCrop',
+                              'crop_type': 'absolute_range',
+                              'crop_size': (384, 600),
+                              'allow_negative_crop': True
+                          }, {
+                              'type':
+                              'Resize',
+                              'img_scale': [(480, 1333), (512, 1333),
+                                            (544, 1333), (576, 1333),
+                                            (608, 1333), (640, 1333),
+                                            (672, 1333), (704, 1333),
+                                            (736, 1333), (768, 1333),
+                                            (800, 1333)],
+                              'multiscale_mode':
+                              'value',
+                              'override':
+                              True,
+                              'keep_ratio':
+                              True
+                          }]]),
+            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=1),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+        ],
+        classes=[
+            'cluster_1', 'cluster_2', 'cluster_3', 'cluster_4', 'cluster_5',
+            'cluster_6', 'cluster_7', 'cluster_8', 'cluster_9', 'cluster_10',
+            'cluster_11', 'cluster_12', 'cluster_13', 'cluster_14',
+            'cluster_15', 'cluster_16', 'cluster_17', 'cluster_18',
+            'cluster_19', 'cluster_20', 'cluster_21', 'cluster_22',
+            'cluster_23', 'cluster_24', 'cluster_25', 'cluster_26',
+            'cluster_27', 'cluster_28', 'cluster_29', 'cluster_30',
+            'cluster_31', 'cluster_32', 'cluster_33', 'cluster_34',
+            'cluster_35', 'cluster_36', 'cluster_37', 'cluster_38',
+            'cluster_39', 'cluster_40', 'cluster_41', 'cluster_42',
+            'cluster_43', 'cluster_44', 'cluster_45', 'cluster_46',
+            'cluster_47', 'cluster_48', 'cluster_49', 'cluster_50',
+            'cluster_51', 'cluster_52', 'cluster_53', 'cluster_54',
+            'cluster_55', 'cluster_56', 'cluster_57', 'cluster_58',
+            'cluster_59', 'cluster_60', 'cluster_61', 'cluster_62',
+            'cluster_63', 'cluster_64', 'cluster_65', 'cluster_66',
+            'cluster_67', 'cluster_68', 'cluster_69', 'cluster_70',
+            'cluster_71', 'cluster_72', 'cluster_73', 'cluster_74',
+            'cluster_75', 'cluster_76', 'cluster_77', 'cluster_78',
+            'cluster_79', 'cluster_80', 'cluster_81', 'cluster_82',
+            'cluster_83', 'cluster_84', 'cluster_85', 'cluster_86',
+            'cluster_87', 'cluster_88', 'cluster_89', 'cluster_90',
+            'cluster_91', 'cluster_92', 'cluster_93', 'cluster_94',
+            'cluster_95', 'cluster_96', 'cluster_97', 'cluster_98',
+            'cluster_99', 'cluster_100', 'cluster_101', 'cluster_102',
+            'cluster_103', 'cluster_104', 'cluster_105', 'cluster_106',
+            'cluster_107', 'cluster_108', 'cluster_109', 'cluster_110',
+            'cluster_111', 'cluster_112', 'cluster_113', 'cluster_114',
+            'cluster_115', 'cluster_116', 'cluster_117', 'cluster_118',
+            'cluster_119', 'cluster_120', 'cluster_121', 'cluster_122',
+            'cluster_123', 'cluster_124', 'cluster_125', 'cluster_126',
+            'cluster_127', 'cluster_128', 'cluster_129', 'cluster_130',
+            'cluster_131', 'cluster_132', 'cluster_133', 'cluster_134',
+            'cluster_135', 'cluster_136', 'cluster_137', 'cluster_138',
+            'cluster_139', 'cluster_140', 'cluster_141', 'cluster_142',
+            'cluster_143', 'cluster_144', 'cluster_145', 'cluster_146',
+            'cluster_147', 'cluster_148', 'cluster_149', 'cluster_150',
+            'cluster_151', 'cluster_152', 'cluster_153', 'cluster_154',
+            'cluster_155', 'cluster_156', 'cluster_157', 'cluster_158',
+            'cluster_159', 'cluster_160', 'cluster_161', 'cluster_162',
+            'cluster_163', 'cluster_164', 'cluster_165', 'cluster_166',
+            'cluster_167', 'cluster_168', 'cluster_169', 'cluster_170',
+            'cluster_171', 'cluster_172', 'cluster_173', 'cluster_174',
+            'cluster_175', 'cluster_176', 'cluster_177', 'cluster_178',
+            'cluster_179', 'cluster_180', 'cluster_181', 'cluster_182',
+            'cluster_183', 'cluster_184', 'cluster_185', 'cluster_186',
+            'cluster_187', 'cluster_188', 'cluster_189', 'cluster_190',
+            'cluster_191', 'cluster_192', 'cluster_193', 'cluster_194',
+            'cluster_195', 'cluster_196', 'cluster_197', 'cluster_198',
+            'cluster_199', 'cluster_200', 'cluster_201', 'cluster_202',
+            'cluster_203', 'cluster_204', 'cluster_205', 'cluster_206',
+            'cluster_207', 'cluster_208', 'cluster_209', 'cluster_210',
+            'cluster_211', 'cluster_212', 'cluster_213', 'cluster_214',
+            'cluster_215', 'cluster_216', 'cluster_217', 'cluster_218',
+            'cluster_219', 'cluster_220', 'cluster_221', 'cluster_222',
+            'cluster_223', 'cluster_224', 'cluster_225', 'cluster_226',
+            'cluster_227', 'cluster_228', 'cluster_229', 'cluster_230',
+            'cluster_231', 'cluster_232', 'cluster_233', 'cluster_234',
+            'cluster_235', 'cluster_236', 'cluster_237', 'cluster_238',
+            'cluster_239', 'cluster_240', 'cluster_241', 'cluster_242',
+            'cluster_243', 'cluster_244', 'cluster_245', 'cluster_246',
+            'cluster_247', 'cluster_248', 'cluster_249', 'cluster_250',
+            'cluster_251', 'cluster_252', 'cluster_253', 'cluster_254',
+            'cluster_255', 'cluster_256'
+        ]),
+    val=dict(
+        type='CocoDataset',
+        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',
+        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, metric='bbox', save_best='auto', gpu_collect=True)
+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 = None
+resume_from = None
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+auto_scale_lr = dict(enable=True, base_batch_size=64)
+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.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.core.bbox.assigners.hungarian_assigner',
+        'selfsup.core.bbox.assigners.pseudo_hungarian_assigner',
+        'selfsup.core.bbox.match_costs.match_cost'
+    ],
+    allow_failed_imports=False)
+classes = [
+    'cluster_1', 'cluster_2', 'cluster_3', 'cluster_4', 'cluster_5',
+    'cluster_6', 'cluster_7', 'cluster_8', 'cluster_9', 'cluster_10',
+    'cluster_11', 'cluster_12', 'cluster_13', 'cluster_14', 'cluster_15',
+    'cluster_16', 'cluster_17', 'cluster_18', 'cluster_19', 'cluster_20',
+    'cluster_21', 'cluster_22', 'cluster_23', 'cluster_24', 'cluster_25',
+    'cluster_26', 'cluster_27', 'cluster_28', 'cluster_29', 'cluster_30',
+    'cluster_31', 'cluster_32', 'cluster_33', 'cluster_34', 'cluster_35',
+    'cluster_36', 'cluster_37', 'cluster_38', 'cluster_39', 'cluster_40',
+    'cluster_41', 'cluster_42', 'cluster_43', 'cluster_44', 'cluster_45',
+    'cluster_46', 'cluster_47', 'cluster_48', 'cluster_49', 'cluster_50',
+    'cluster_51', 'cluster_52', 'cluster_53', 'cluster_54', 'cluster_55',
+    'cluster_56', 'cluster_57', 'cluster_58', 'cluster_59', 'cluster_60',
+    'cluster_61', 'cluster_62', 'cluster_63', 'cluster_64', 'cluster_65',
+    'cluster_66', 'cluster_67', 'cluster_68', 'cluster_69', 'cluster_70',
+    'cluster_71', 'cluster_72', 'cluster_73', 'cluster_74', 'cluster_75',
+    'cluster_76', 'cluster_77', 'cluster_78', 'cluster_79', 'cluster_80',
+    'cluster_81', 'cluster_82', 'cluster_83', 'cluster_84', 'cluster_85',
+    'cluster_86', 'cluster_87', 'cluster_88', 'cluster_89', 'cluster_90',
+    'cluster_91', 'cluster_92', 'cluster_93', 'cluster_94', 'cluster_95',
+    'cluster_96', 'cluster_97', 'cluster_98', 'cluster_99', 'cluster_100',
+    'cluster_101', 'cluster_102', 'cluster_103', 'cluster_104', 'cluster_105',
+    'cluster_106', 'cluster_107', 'cluster_108', 'cluster_109', 'cluster_110',
+    'cluster_111', 'cluster_112', 'cluster_113', 'cluster_114', 'cluster_115',
+    'cluster_116', 'cluster_117', 'cluster_118', 'cluster_119', 'cluster_120',
+    'cluster_121', 'cluster_122', 'cluster_123', 'cluster_124', 'cluster_125',
+    'cluster_126', 'cluster_127', 'cluster_128', 'cluster_129', 'cluster_130',
+    'cluster_131', 'cluster_132', 'cluster_133', 'cluster_134', 'cluster_135',
+    'cluster_136', 'cluster_137', 'cluster_138', 'cluster_139', 'cluster_140',
+    'cluster_141', 'cluster_142', 'cluster_143', 'cluster_144', 'cluster_145',
+    'cluster_146', 'cluster_147', 'cluster_148', 'cluster_149', 'cluster_150',
+    'cluster_151', 'cluster_152', 'cluster_153', 'cluster_154', 'cluster_155',
+    'cluster_156', 'cluster_157', 'cluster_158', 'cluster_159', 'cluster_160',
+    'cluster_161', 'cluster_162', 'cluster_163', 'cluster_164', 'cluster_165',
+    'cluster_166', 'cluster_167', 'cluster_168', 'cluster_169', 'cluster_170',
+    'cluster_171', 'cluster_172', 'cluster_173', 'cluster_174', 'cluster_175',
+    'cluster_176', 'cluster_177', 'cluster_178', 'cluster_179', 'cluster_180',
+    'cluster_181', 'cluster_182', 'cluster_183', 'cluster_184', 'cluster_185',
+    'cluster_186', 'cluster_187', 'cluster_188', 'cluster_189', 'cluster_190',
+    'cluster_191', 'cluster_192', 'cluster_193', 'cluster_194', 'cluster_195',
+    'cluster_196', 'cluster_197', 'cluster_198', 'cluster_199', 'cluster_200',
+    'cluster_201', 'cluster_202', 'cluster_203', 'cluster_204', 'cluster_205',
+    'cluster_206', 'cluster_207', 'cluster_208', 'cluster_209', 'cluster_210',
+    'cluster_211', 'cluster_212', 'cluster_213', 'cluster_214', 'cluster_215',
+    'cluster_216', 'cluster_217', 'cluster_218', 'cluster_219', 'cluster_220',
+    'cluster_221', 'cluster_222', 'cluster_223', 'cluster_224', 'cluster_225',
+    'cluster_226', 'cluster_227', 'cluster_228', 'cluster_229', 'cluster_230',
+    'cluster_231', 'cluster_232', 'cluster_233', 'cluster_234', 'cluster_235',
+    'cluster_236', 'cluster_237', 'cluster_238', 'cluster_239', 'cluster_240',
+    'cluster_241', 'cluster_242', 'cluster_243', 'cluster_244', 'cluster_245',
+    'cluster_246', 'cluster_247', 'cluster_248', 'cluster_249', 'cluster_250',
+    'cluster_251', 'cluster_252', 'cluster_253', 'cluster_254', 'cluster_255',
+    'cluster_256'
+]
+optimizer = dict(
+    type='AdamW',
+    lr=0.0002,
+    weight_decay=0.0001,
+    paramwise_cfg=dict(
+        custom_keys=dict(backbone=dict(lr_mult=0, decay_mult=0))))
+optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
+lr_config = dict(policy='step', step=[40])
+runner = dict(type='EpochBasedRunner', max_epochs=50)
+work_dir = 'work_dirs/selfsup_detr_cluster-ids-as-pseudo-labels'
+auto_resume = False
+gpu_ids = range(0, 32)

pretrain/selfsup_mask-rcnn_swin-b_lsj-3x-coco_simmim-pretrain/final_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aca88dfee95a9cb04041b5b93a19169aaa3bb14ff12c237042bc981205d85ab
+size 422177783

pretrain/selfsup_mask-rcnn_swin-b_lsj-3x-coco_simmim-pretrain/selfsup_mask-rcnn_swin-b_simmim.py

@@ -0,0 +1,447 @@
+model = dict(
+    type='SelfSupDetector',
+    backbone=dict(
+        type='SelfSupMaskRCNN',
+        backbone=dict(
+            type='SwinTransformer',
+            embed_dims=128,
+            depths=[2, 2, 18, 2],
+            num_heads=[4, 8, 16, 32],
+            window_size=7,
+            mlp_ratio=4,
+            qkv_bias=True,
+            qk_scale=None,
+            drop_rate=0.0,
+            attn_drop_rate=0.0,
+            drop_path_rate=0.2,
+            patch_norm=True,
+            out_indices=(0, 1, 2, 3),
+            with_cp=False,
+            frozen_stages=4,
+            convert_weights=True,
+            init_cfg=dict(
+                type='Pretrained',
+                checkpoint=
+                'https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22k.pth'
+            )),
+        neck=dict(
+            type='FPN',
+            in_channels=[128, 256, 512, 1024],
+            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='L1Loss', loss_weight=1.0)),
+        roi_head=dict(
+            type='SelfSupStandardRoIHead',
+            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,
+                num_classes=256,
+                roi_feat_size=7,
+                reg_class_agnostic=False,
+                loss_bbox=dict(type='L1Loss', loss_weight=1.0),
+                loss_cls=dict(
+                    type='ContrastiveLoss', loss_weight=1.0, temperature=0.5)),
+            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,
+                    match_low_quality=True,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=4096,
+                    pos_fraction=1.0,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=False),
+                allowed_border=-1,
+                pos_weight=-1,
+                debug=False),
+            rpn_proposal=dict(
+                nms_pre=2000,
+                max_per_img=1000,
+                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=True,
+                    ignore_iof_thr=-1,
+                    gt_max_assign_all=False),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=4096,
+                    pos_fraction=1,
+                    neg_pos_ub=0,
+                    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=0.05,
+                nms=dict(type='nms', iou_threshold=0.5),
+                max_per_img=100,
+                mask_thr_binary=0.5)),
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='pretrain/simmim_swin-b_mmselfsup-pretrain.pth')))
+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=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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=4,
+    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': [(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                          (1333, 768), (1333, 800)],
+            'multiscale_mode':
+            'value',
+            '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': [(1333, 640), (1333, 672), (1333, 704),
+                                     (1333, 736), (1333, 768), (1333, 800)],
+                       'multiscale_mode':
+                       'value',
+                       '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, metric='bbox')
+optimizer = dict(
+    type='AdamW',
+    lr=6e-05,
+    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=1000,
+    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=32)
+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.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.core.bbox.assigners.hungarian_assigner',
+        'selfsup.core.bbox.assigners.pseudo_hungarian_assigner',
+        'selfsup.core.bbox.match_costs.match_cost'
+    ],
+    allow_failed_imports=False)
+pretrained = 'https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22k.pth'
+find_unused_parameters = True
+work_dir = 'work_dirs/selfsup_mask-rcnn_swin-b_lsj-3x-coco_simmim-pretrain'
+auto_resume = False
+gpu_ids = range(0, 8)

pretrain/selfsup_mask_rcnn_soft-teacher-mstrain_sampler-4096-1.0_temperature-0.2_1x_coco_mocov2-pretrain/final_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7905e6dc0b5158a6f896575d62a3f3ed0c1dd9d7ff4bb8e923339c2b46b587c
+size 170913485

pretrain/selfsup_mask_rcnn_soft-teacher-mstrain_sampler-4096-1.0_temperature-0.2_1x_coco_mocov2-pretrain/mask_rcnn.py

@@ -0,0 +1,417 @@
+model = dict(
+    type='SelfSupDetector',
+    backbone=dict(
+        type='SelfSupMaskRCNN',
+        backbone=dict(
+            type='ResNet',
+            depth=50,
+            num_stages=4,
+            out_indices=(0, 1, 2, 3),
+            frozen_stages=4,
+            norm_cfg=dict(type='BN', requires_grad=False),
+            norm_eval=True,
+            style='pytorch',
+            init_cfg=dict(
+                type='Pretrained',
+                checkpoint='pretrain/mocov2_resnet50_256bs-coslr-800e_in1k.pth'
+            )),
+        neck=dict(
+            type='FPN',
+            in_channels=[256, 512, 1024, 2048],
+            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='L1Loss', loss_weight=1.0)),
+        roi_head=dict(
+            type='SelfSupStandardRoIHead',
+            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,
+                num_classes=256,
+                roi_feat_size=7,
+                loss_cls=dict(
+                    type='ContrastiveLoss', loss_weight=1.0, temperature=0.2)),
+            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,
+                    match_low_quality=True,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=4096,
+                    pos_fraction=1.0,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=False),
+                allowed_border=-1,
+                pos_weight=-1,
+                debug=False),
+            rpn_proposal=dict(
+                nms_pre=2000,
+                max_per_img=1000,
+                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=True,
+                    ignore_iof_thr=-1,
+                    gt_max_assign_all=False),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=4096,
+                    pos_fraction=1,
+                    neg_pos_ub=0,
+                    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=0.05,
+                nms=dict(type='nms', iou_threshold=0.5),
+                max_per_img=100,
+                mask_thr_binary=0.5))))
+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=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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': [(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                          (1333, 768), (1333, 800)],
+            'multiscale_mode':
+            'value',
+            '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': [(1333, 640), (1333, 672), (1333, 704),
+                                     (1333, 736), (1333, 768), (1333, 800)],
+                       'multiscale_mode':
+                       'value',
+                       '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(metric='bbox', interval=65535)
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+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='mmdet_pretrain', 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=False, base_batch_size=16)
+custom_imports = dict(
+    imports=[
+        'mmselfsup.core', 'mmselfsup.datasets.pipelines',
+        '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.roi_heads.bbox_heads.convfc_bbox_head',
+        'selfsup.models.roi_heads.standard_roi_head',
+        'selfsup.models.detectors.selfsup_detector',
+        'selfsup.models.detectors.selfsup_fcos',
+        'selfsup.models.detectors.selfsup_detr',
+        'selfsup.models.detectors.selfsup_retinanet',
+        'selfsup.models.detectors.selfsup_mask_rcnn',
+        'selfsup.core.bbox.match_costs.match_cost'
+    ],
+    allow_failed_imports=False)
+work_dir = 'work_dirs/selfsup_mask_rcnn_soft-teacher-mstrain_sampler-4096-1.0_temperature-0.2_1x_coco_mocov2-pretrain'
+auto_resume = False
+gpu_ids = range(0, 8)

pretrain/selfsup_mask_rcnn_soft-teacher-mstrain_sampler-4096-1.0_temperature-0.2_1x_coco_pixpro-pretrain/final_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4328af18c59d656037f81d1fd10de0878bc61849f1432e6adfe51edb37bf1bb
+size 170913485

pretrain/selfsup_mask_rcnn_soft-teacher-mstrain_sampler-4096-1.0_temperature-0.2_1x_coco_pixpro-pretrain/mask_rcnn.py

@@ -0,0 +1,417 @@
+model = dict(
+    type='SelfSupDetector',
+    backbone=dict(
+        type='SelfSupMaskRCNN',
+        backbone=dict(
+            type='ResNet',
+            depth=50,
+            num_stages=4,
+            out_indices=(0, 1, 2, 3),
+            frozen_stages=4,
+            norm_cfg=dict(type='BN', requires_grad=False),
+            norm_eval=True,
+            style='pytorch',
+            init_cfg=dict(
+                type='Pretrained',
+                checkpoint='pretrain/pixpro_resnet50_8xb128-coslr-400e_in1k.pth'
+            )),
+        neck=dict(
+            type='FPN',
+            in_channels=[256, 512, 1024, 2048],
+            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='L1Loss', loss_weight=1.0)),
+        roi_head=dict(
+            type='SelfSupStandardRoIHead',
+            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,
+                num_classes=256,
+                roi_feat_size=7,
+                loss_cls=dict(
+                    type='ContrastiveLoss', loss_weight=1.0, temperature=0.2)),
+            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,
+                    match_low_quality=True,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=4096,
+                    pos_fraction=1.0,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=False),
+                allowed_border=-1,
+                pos_weight=-1,
+                debug=False),
+            rpn_proposal=dict(
+                nms_pre=2000,
+                max_per_img=1000,
+                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=True,
+                    ignore_iof_thr=-1,
+                    gt_max_assign_all=False),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=4096,
+                    pos_fraction=1,
+                    neg_pos_ub=0,
+                    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=0.05,
+                nms=dict(type='nms', iou_threshold=0.5),
+                max_per_img=100,
+                mask_thr_binary=0.5))))
+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=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                   (1333, 768), (1333, 800)],
+        multiscale_mode='value',
+        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': [(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                          (1333, 768), (1333, 800)],
+            'multiscale_mode':
+            'value',
+            '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': [(1333, 640), (1333, 672), (1333, 704),
+                                     (1333, 736), (1333, 768), (1333, 800)],
+                       'multiscale_mode':
+                       'value',
+                       '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(metric='bbox', interval=65535)
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+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='mmdet_pretrain', 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=False, base_batch_size=16)
+custom_imports = dict(
+    imports=[
+        'mmselfsup.core', 'mmselfsup.datasets.pipelines',
+        '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.roi_heads.bbox_heads.convfc_bbox_head',
+        'selfsup.models.roi_heads.standard_roi_head',
+        'selfsup.models.detectors.selfsup_detector',
+        'selfsup.models.detectors.selfsup_fcos',
+        'selfsup.models.detectors.selfsup_detr',
+        'selfsup.models.detectors.selfsup_retinanet',
+        'selfsup.models.detectors.selfsup_mask_rcnn',
+        'selfsup.core.bbox.match_costs.match_cost'
+    ],
+    allow_failed_imports=False)
+work_dir = 'work_dirs/selfsup_mask_rcnn_soft-teacher-mstrain_sampler-4096-1.0_temperature-0.2_1x_coco_pixpro-pretrain'
+auto_resume = False
+gpu_ids = range(0, 8)