Add fine-tuned model files

dino-4scale_resnet50_8xb2-12e_coco.py

@@ -0,0 +1,723 @@
+auto_scale_lr = dict(base_batch_size=16)
+backend_args = None
+data_root = '/kaggle/working/mmdetection/dataset/'
+dataset_type = 'CocoDataset'
+default_hooks = dict(
+    checkpoint=dict(interval=1, type='CheckpointHook'),
+    logger=dict(interval=50, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='DetVisualizationHook'))
+default_scope = 'mmdet'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+launcher = 'none'
+load_from = '/kaggle/working/mmdetection/work_dirs/dino-4scale_resnet50_8xb2-12e_coco/epoch_6.pth'
+log_level = 'INFO'
+log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
+max_epochs = 12
+metainfo = dict(classes=[
+    '000_aveda_shampoo',
+    '001_binder_clips_median',
+    '002_binder_clips_small',
+    '003_bombik_bucket',
+    '004_bonne_maman_blueberry',
+    '005_bonne_maman_raspberry',
+    '006_bonne_maman_strawberry',
+    '007_costa_caramel',
+    '008_essential_oil_bergamot',
+    '009_garlic_toast_spread',
+    '010_handcream_avocado',
+    '011_hb_calcium',
+    '012_hb_grapeseed',
+    '013_hb_marine_collagen',
+    '014_hellmanns_mayonnaise',
+    '015_illy_blend',
+    '016_japanese_finger_cookies',
+    '017_john_west_canned_tuna',
+    '018_kerastase_shampoo',
+    '019_kiehls_facial_cream',
+    '020_kiihne_balsamic',
+    '021_kiihne_honey_mustard',
+    '022_lindor_matcha',
+    '023_lindor_salted_caramel',
+    '024_lush_mask',
+    '025_pasta_sauce_black_pepper',
+    '026_pasta_sauce_tomato',
+    '027_pepsi',
+    '028_portable_yogurt_machine',
+    '029_selfile_stick',
+    '030_sour_lemon_drops',
+    '031_sticky_notes',
+    '032_stridex_green',
+    '033_thermos_flask_cream',
+    '034_thermos_flask_muji',
+    '035_thermos_flask_sliver',
+    '036_tragata_olive_oil',
+    '037_tulip_luncheon_meat',
+    '038_unicharm_cotton_pad',
+    '039_vinda_tissue',
+    '040_wrigley_doublemint_gum',
+    '041_baseball_cap_black',
+    '042_baseball_cap_pink',
+    '043_bfe_facial_mask',
+    '044_corgi_doll',
+    '045_dinosaur_doll',
+    '046_geo_mocha',
+    '047_geo_roast_charcoal',
+    '048_instant_noodle_black',
+    '049_instant_noodle_red',
+    '050_nabati_cheese_wafer',
+    '051_truffettes',
+    '052_acnes_cream',
+    '053_aveda_conditioner',
+    '054_banana_milk_drink',
+    '055_candle_beast',
+    '056_china_persimmon',
+    '057_danisa_butter_cookies',
+    '058_effaclar_duo',
+    '059_evelom_cleanser',
+    '060_glasses_box_blone',
+    '061_handcream_iris',
+    '062_handcream_lavender',
+    '063_handcream_rosewater',
+    '064_handcream_summer_hill',
+    '065_hr_serum',
+    '066_japanese_chocolate',
+    '067_kerastase_hair_treatment',
+    '068_kiehls_serum',
+    '069_korean_beef_marinade',
+    '070_korean_doenjang',
+    '071_korean_gochujang',
+    '072_korean_ssamjang',
+    '073_loccitane_soap',
+    '074_marvis_toothpaste_purple',
+    '075_mouse_thinkpad',
+    '076_oatly_chocolate',
+    '077_oatly_original',
+    '078_ousa_grated_cheese',
+    '079_polaroid_film',
+    '080_skinceuticals_be',
+    '081_skinceuticals_cf',
+    '082_skinceuticals_phyto',
+    '083_stapler_black',
+    '084_stapler_blue',
+    '085_sunscreen_blue',
+    '086_tempo_pocket_tissue',
+    '087_thermos_flask_purple',
+    '088_uha_matcha',
+    '089_urban_decay_spray',
+    '090_vitaboost_multivitamin',
+    '091_watercolor_penbox',
+    '092_youthlt_bilberry_complex',
+    '093_daiso_mod_remover',
+    '094_kaneyo_kitchen_bleach',
+    '095_lays_chip_bag_blue',
+    '096_lays_chip_bag_green',
+    '097_lays_chip_tube_auburn',
+    '098_lays_chip_tube_green',
+    '099_mug_blue',
+])
+model = dict(
+    as_two_stage=True,
+    backbone=dict(
+        depth=50,
+        frozen_stages=1,
+        init_cfg=dict(checkpoint='torchvision://resnet50', type='Pretrained'),
+        norm_cfg=dict(requires_grad=False, type='BN'),
+        norm_eval=True,
+        num_stages=4,
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        style='pytorch',
+        type='ResNet',
+        with_cp=True),
+    bbox_head=dict(
+        loss_bbox=dict(loss_weight=5.0, type='L1Loss'),
+        loss_cls=dict(
+            alpha=0.25,
+            gamma=2.0,
+            loss_weight=1.0,
+            type='FocalLoss',
+            use_sigmoid=True),
+        loss_iou=dict(loss_weight=2.0, type='GIoULoss'),
+        num_classes=100,
+        sync_cls_avg_factor=True,
+        type='DINOHead'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_size_divisor=1,
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='DetDataPreprocessor'),
+    decoder=dict(
+        layer_cfg=dict(
+            cross_attn_cfg=dict(dropout=0.0, embed_dims=256, num_levels=4),
+            ffn_cfg=dict(
+                embed_dims=256, feedforward_channels=2048, ffn_drop=0.0),
+            self_attn_cfg=dict(dropout=0.0, embed_dims=256, num_heads=8)),
+        num_layers=6,
+        post_norm_cfg=None,
+        return_intermediate=True),
+    dn_cfg=dict(
+        box_noise_scale=1.0,
+        group_cfg=dict(dynamic=True, num_dn_queries=100, num_groups=None),
+        label_noise_scale=0.5),
+    encoder=dict(
+        layer_cfg=dict(
+            ffn_cfg=dict(
+                embed_dims=256, feedforward_channels=2048, ffn_drop=0.0),
+            self_attn_cfg=dict(dropout=0.0, embed_dims=256, num_levels=4)),
+        num_layers=6),
+    neck=dict(
+        act_cfg=None,
+        in_channels=[
+            256,
+            512,
+            1024,
+            2048,
+        ],
+        kernel_size=1,
+        norm_cfg=dict(num_groups=32, type='GN'),
+        num_outs=4,
+        out_channels=256,
+        type='ChannelMapper'),
+    num_feature_levels=4,
+    num_queries=900,
+    positional_encoding=dict(
+        normalize=True, num_feats=128, offset=0.0, temperature=20),
+    test_cfg=dict(max_per_img=300),
+    train_cfg=dict(
+        assigner=dict(
+            match_costs=[
+                dict(type='FocalLossCost', weight=2.0),
+                dict(box_format='xywh', type='BBoxL1Cost', weight=5.0),
+                dict(iou_mode='giou', type='IoUCost', weight=2.0),
+            ],
+            type='HungarianAssigner')),
+    type='DINO',
+    with_box_refine=True)
+num_levels = 4
+optim_wrapper = dict(
+    clip_grad=dict(max_norm=0.1, norm_type=2),
+    optimizer=dict(lr=0.0001, type='AdamW', weight_decay=0.0001),
+    paramwise_cfg=dict(custom_keys=dict(backbone=dict(lr_mult=0.1))),
+    type='OptimWrapper')
+param_scheduler = [
+    dict(
+        begin=0,
+        by_epoch=True,
+        end=12,
+        gamma=0.1,
+        milestones=[
+            11,
+        ],
+        type='MultiStepLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        ann_file=None,
+        backend_args=None,
+        data_prefix=dict(img=''),
+        data_root='/kaggle/input/insdet-test/InsDet-Test',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                1333,
+                800,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoDataset'),
+    drop_last=False,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    ann_file='/kaggle/working/mmdetection/dataset/annotations/val.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+test_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        1333,
+        800,
+    ), type='Resize'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        meta_keys=(
+            'img_id',
+            'img_path',
+            'ori_shape',
+            'img_shape',
+            'scale_factor',
+        ),
+        type='PackDetInputs'),
+]
+train_cfg = dict(max_epochs=6, type='EpochBasedTrainLoop', val_interval=1)
+train_dataloader = dict(
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    batch_size=1,
+    dataset=dict(
+        ann_file='annotations/train.json',
+        backend_args=None,
+        data_prefix=dict(img='train/'),
+        data_root='/kaggle/working/mmdetection/dataset/',
+        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+        metainfo=dict(classes=[
+            '000_aveda_shampoo',
+            '001_binder_clips_median',
+            '002_binder_clips_small',
+            '003_bombik_bucket',
+            '004_bonne_maman_blueberry',
+            '005_bonne_maman_raspberry',
+            '006_bonne_maman_strawberry',
+            '007_costa_caramel',
+            '008_essential_oil_bergamot',
+            '009_garlic_toast_spread',
+            '010_handcream_avocado',
+            '011_hb_calcium',
+            '012_hb_grapeseed',
+            '013_hb_marine_collagen',
+            '014_hellmanns_mayonnaise',
+            '015_illy_blend',
+            '016_japanese_finger_cookies',
+            '017_john_west_canned_tuna',
+            '018_kerastase_shampoo',
+            '019_kiehls_facial_cream',
+            '020_kiihne_balsamic',
+            '021_kiihne_honey_mustard',
+            '022_lindor_matcha',
+            '023_lindor_salted_caramel',
+            '024_lush_mask',
+            '025_pasta_sauce_black_pepper',
+            '026_pasta_sauce_tomato',
+            '027_pepsi',
+            '028_portable_yogurt_machine',
+            '029_selfile_stick',
+            '030_sour_lemon_drops',
+            '031_sticky_notes',
+            '032_stridex_green',
+            '033_thermos_flask_cream',
+            '034_thermos_flask_muji',
+            '035_thermos_flask_sliver',
+            '036_tragata_olive_oil',
+            '037_tulip_luncheon_meat',
+            '038_unicharm_cotton_pad',
+            '039_vinda_tissue',
+            '040_wrigley_doublemint_gum',
+            '041_baseball_cap_black',
+            '042_baseball_cap_pink',
+            '043_bfe_facial_mask',
+            '044_corgi_doll',
+            '045_dinosaur_doll',
+            '046_geo_mocha',
+            '047_geo_roast_charcoal',
+            '048_instant_noodle_black',
+            '049_instant_noodle_red',
+            '050_nabati_cheese_wafer',
+            '051_truffettes',
+            '052_acnes_cream',
+            '053_aveda_conditioner',
+            '054_banana_milk_drink',
+            '055_candle_beast',
+            '056_china_persimmon',
+            '057_danisa_butter_cookies',
+            '058_effaclar_duo',
+            '059_evelom_cleanser',
+            '060_glasses_box_blone',
+            '061_handcream_iris',
+            '062_handcream_lavender',
+            '063_handcream_rosewater',
+            '064_handcream_summer_hill',
+            '065_hr_serum',
+            '066_japanese_chocolate',
+            '067_kerastase_hair_treatment',
+            '068_kiehls_serum',
+            '069_korean_beef_marinade',
+            '070_korean_doenjang',
+            '071_korean_gochujang',
+            '072_korean_ssamjang',
+            '073_loccitane_soap',
+            '074_marvis_toothpaste_purple',
+            '075_mouse_thinkpad',
+            '076_oatly_chocolate',
+            '077_oatly_original',
+            '078_ousa_grated_cheese',
+            '079_polaroid_film',
+            '080_skinceuticals_be',
+            '081_skinceuticals_cf',
+            '082_skinceuticals_phyto',
+            '083_stapler_black',
+            '084_stapler_blue',
+            '085_sunscreen_blue',
+            '086_tempo_pocket_tissue',
+            '087_thermos_flask_purple',
+            '088_uha_matcha',
+            '089_urban_decay_spray',
+            '090_vitaboost_multivitamin',
+            '091_watercolor_penbox',
+            '092_youthlt_bilberry_complex',
+            '093_daiso_mod_remover',
+            '094_kaneyo_kitchen_bleach',
+            '095_lays_chip_bag_blue',
+            '096_lays_chip_bag_green',
+            '097_lays_chip_tube_auburn',
+            '098_lays_chip_tube_green',
+            '099_mug_blue',
+        ]),
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(
+                transforms=[
+                    [
+                        dict(
+                            keep_ratio=True,
+                            scales=[
+                                (
+                                    480,
+                                    1333,
+                                ),
+                                (
+                                    512,
+                                    1333,
+                                ),
+                                (
+                                    544,
+                                    1333,
+                                ),
+                                (
+                                    576,
+                                    1333,
+                                ),
+                                (
+                                    608,
+                                    1333,
+                                ),
+                                (
+                                    640,
+                                    1333,
+                                ),
+                                (
+                                    672,
+                                    1333,
+                                ),
+                                (
+                                    704,
+                                    1333,
+                                ),
+                                (
+                                    736,
+                                    1333,
+                                ),
+                                (
+                                    768,
+                                    1333,
+                                ),
+                                (
+                                    800,
+                                    1333,
+                                ),
+                            ],
+                            type='RandomChoiceResize'),
+                    ],
+                    [
+                        dict(
+                            keep_ratio=True,
+                            scales=[
+                                (
+                                    400,
+                                    4200,
+                                ),
+                                (
+                                    500,
+                                    4200,
+                                ),
+                                (
+                                    600,
+                                    4200,
+                                ),
+                            ],
+                            type='RandomChoiceResize'),
+                        dict(
+                            allow_negative_crop=True,
+                            crop_size=(
+                                384,
+                                600,
+                            ),
+                            crop_type='absolute_range',
+                            type='RandomCrop'),
+                        dict(
+                            keep_ratio=True,
+                            scales=[
+                                (
+                                    480,
+                                    1333,
+                                ),
+                                (
+                                    512,
+                                    1333,
+                                ),
+                                (
+                                    544,
+                                    1333,
+                                ),
+                                (
+                                    576,
+                                    1333,
+                                ),
+                                (
+                                    608,
+                                    1333,
+                                ),
+                                (
+                                    640,
+                                    1333,
+                                ),
+                                (
+                                    672,
+                                    1333,
+                                ),
+                                (
+                                    704,
+                                    1333,
+                                ),
+                                (
+                                    736,
+                                    1333,
+                                ),
+                                (
+                                    768,
+                                    1333,
+                                ),
+                                (
+                                    800,
+                                    1333,
+                                ),
+                            ],
+                            type='RandomChoiceResize'),
+                    ],
+                ],
+                type='RandomChoice'),
+            dict(type='PackDetInputs'),
+        ],
+        type='CocoDataset'),
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='DefaultSampler'))
+train_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(
+        transforms=[
+            [
+                dict(
+                    keep_ratio=True,
+                    scales=[
+                        (
+                            480,
+                            1333,
+                        ),
+                        (
+                            512,
+                            1333,
+                        ),
+                        (
+                            544,
+                            1333,
+                        ),
+                        (
+                            576,
+                            1333,
+                        ),
+                        (
+                            608,
+                            1333,
+                        ),
+                        (
+                            640,
+                            1333,
+                        ),
+                        (
+                            672,
+                            1333,
+                        ),
+                        (
+                            704,
+                            1333,
+                        ),
+                        (
+                            736,
+                            1333,
+                        ),
+                        (
+                            768,
+                            1333,
+                        ),
+                        (
+                            800,
+                            1333,
+                        ),
+                    ],
+                    type='RandomChoiceResize'),
+            ],
+            [
+                dict(
+                    keep_ratio=True,
+                    scales=[
+                        (
+                            400,
+                            4200,
+                        ),
+                        (
+                            500,
+                            4200,
+                        ),
+                        (
+                            600,
+                            4200,
+                        ),
+                    ],
+                    type='RandomChoiceResize'),
+                dict(
+                    allow_negative_crop=True,
+                    crop_size=(
+                        384,
+                        600,
+                    ),
+                    crop_type='absolute_range',
+                    type='RandomCrop'),
+                dict(
+                    keep_ratio=True,
+                    scales=[
+                        (
+                            480,
+                            1333,
+                        ),
+                        (
+                            512,
+                            1333,
+                        ),
+                        (
+                            544,
+                            1333,
+                        ),
+                        (
+                            576,
+                            1333,
+                        ),
+                        (
+                            608,
+                            1333,
+                        ),
+                        (
+                            640,
+                            1333,
+                        ),
+                        (
+                            672,
+                            1333,
+                        ),
+                        (
+                            704,
+                            1333,
+                        ),
+                        (
+                            736,
+                            1333,
+                        ),
+                        (
+                            768,
+                            1333,
+                        ),
+                        (
+                            800,
+                            1333,
+                        ),
+                    ],
+                    type='RandomChoiceResize'),
+            ],
+        ],
+        type='RandomChoice'),
+    dict(type='PackDetInputs'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        ann_file='annotations/instances_val2017.json',
+        backend_args=None,
+        data_prefix=dict(img='val2017/'),
+        data_root='data/coco/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                1333,
+                800,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoDataset'),
+    drop_last=False,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    ann_file='/kaggle/working/mmdetection/dataset/annotations/val.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='DetLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = './work_dirs/dino-4scale_resnet50_8xb2-12e_coco'

epoch_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6941313283f8661beca8e66eb0c6da1b6cebf57566490b210788f793f9eb626
+size 537956199

last_checkpoint

@@ -0,0 +1 @@
+/kaggle/working/mmdetection/work_dirs/dino-4scale_resnet50_8xb2-12e_coco/epoch_6.pth