Updated exported models.

models/swin_base_b32x4-fp16_fungi+val_res_384_cb_epochs_6.py

@@ -1,283 +0,0 @@
-model = dict(
-    type='ImageClassifier',
-    backbone=dict(
-        type='SwinTransformer',
-        arch='base',
-        img_size=384,
-        stage_cfgs=dict(block_cfgs=dict(window_size=12)),
-        drop_path_rate=0.5,
-        init_cfg=dict(
-            type='Pretrained',
-            checkpoint=
-            'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-base_3rdparty_in21k-384px.pth',
-            prefix='backbone')),
-    neck=dict(type='GlobalAveragePooling'),
-    head=dict(
-        type='LinearClsHead',
-        num_classes=1604,
-        in_channels=1024,
-        init_cfg=None,
-        loss=dict(
-            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
-        cal_acc=False),
-    init_cfg=[
-        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.0),
-        dict(type='Constant', layer='LayerNorm', val=1.0, bias=0.0)
-    ],
-    train_cfg=dict())
-rand_increasing_policies = [
-    dict(type='AutoContrast'),
-    dict(type='Equalize'),
-    dict(type='Invert'),
-    dict(type='Rotate', magnitude_key='angle', magnitude_range=(0, 30)),
-    dict(type='Posterize', magnitude_key='bits', magnitude_range=(4, 0)),
-    dict(type='Solarize', magnitude_key='thr', magnitude_range=(256, 0)),
-    dict(
-        type='SolarizeAdd',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 110)),
-    dict(
-        type='ColorTransform',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
-    dict(type='Contrast', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
-    dict(
-        type='Brightness', magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
-    dict(
-        type='Sharpness', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
-    dict(
-        type='Shear',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='horizontal'),
-    dict(
-        type='Shear',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='vertical'),
-    dict(
-        type='Translate',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='horizontal'),
-    dict(
-        type='Translate',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='vertical')
-]
-dataset_type = 'Fungi'
-data_preprocessor = dict(
-    num_classes=1604,
-    mean=[123.675, 116.28, 103.53],
-    std=[58.395, 57.12, 57.375],
-    to_rgb=True)
-bgr_mean = [103.53, 116.28, 123.675]
-bgr_std = [57.375, 57.12, 58.395]
-train_pipeline = [
-    dict(type='LoadImageFromFileFungi'),
-    dict(
-        type='RandomResizedCrop',
-        scale=384,
-        backend='pillow',
-        interpolation='bicubic'),
-    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-    dict(
-        type='RandAugment',
-        policies='timm_increasing',
-        num_policies=2,
-        total_level=10,
-        magnitude_level=9,
-        magnitude_std=0.5,
-        hparams=dict(pad_val=[104, 116, 124], interpolation='bicubic')),
-    dict(
-        type='RandomErasing',
-        erase_prob=0.25,
-        mode='rand',
-        min_area_ratio=0.02,
-        max_area_ratio=0.3333333333333333,
-        fill_color=[103.53, 116.28, 123.675],
-        fill_std=[57.375, 57.12, 58.395]),
-    dict(type='PackInputs')
-]
-test_pipeline = [
-    dict(type='LoadImageFromFileFungi'),
-    dict(
-        type='ResizeEdge',
-        scale=438,
-        edge='short',
-        backend='pillow',
-        interpolation='bicubic'),
-    dict(type='CenterCrop', crop_size=384),
-    dict(type='PackInputs')
-]
-train_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=32,
-    num_workers=14,
-    dataset=dict(
-        type='ClassBalancedDataset',
-        oversample_thr=0.01,
-        dataset=dict(
-            type='Fungi',
-            data_root='/scratch/slurm_tmpdir/job_22252118/',
-            ann_file='FungiCLEF2023_train_metadata_PRODUCTION.csv',
-            data_prefix='DF20/',
-            pipeline=[
-                dict(type='LoadImageFromFileFungi'),
-                dict(
-                    type='RandomResizedCrop',
-                    scale=384,
-                    backend='pillow',
-                    interpolation='bicubic'),
-                dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-                dict(
-                    type='RandAugment',
-                    policies='timm_increasing',
-                    num_policies=2,
-                    total_level=10,
-                    magnitude_level=9,
-                    magnitude_std=0.5,
-                    hparams=dict(
-                        pad_val=[104, 116, 124], interpolation='bicubic')),
-                dict(
-                    type='RandomErasing',
-                    erase_prob=0.25,
-                    mode='rand',
-                    min_area_ratio=0.02,
-                    max_area_ratio=0.3333333333333333,
-                    fill_color=[103.53, 116.28, 123.675],
-                    fill_std=[57.375, 57.12, 58.395]),
-                dict(type='PackInputs')
-            ])),
-    sampler=dict(type='DefaultSampler', shuffle=True))
-val_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=64,
-    num_workers=12,
-    dataset=dict(
-        type='Fungi',
-        data_root='/scratch/slurm_tmpdir/job_22252118/',
-        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
-        data_prefix='DF21/',
-        pipeline=[
-            dict(type='LoadImageFromFileFungi'),
-            dict(
-                type='RandomResizedCrop',
-                scale=384,
-                backend='pillow',
-                interpolation='bicubic'),
-            dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-            dict(
-                type='RandAugment',
-                policies='timm_increasing',
-                num_policies=2,
-                total_level=10,
-                magnitude_level=9,
-                magnitude_std=0.5,
-                hparams=dict(pad_val=[104, 116, 124],
-                             interpolation='bicubic')),
-            dict(
-                type='RandomErasing',
-                erase_prob=0.25,
-                mode='rand',
-                min_area_ratio=0.02,
-                max_area_ratio=0.3333333333333333,
-                fill_color=[103.53, 116.28, 123.675],
-                fill_std=[57.375, 57.12, 58.395]),
-            dict(type='PackInputs')
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-val_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-test_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=64,
-    num_workers=12,
-    dataset=dict(
-        type='FungiTest',
-        data_root='data/fungi2023/',
-        ann_file='FungiCLEF2023_public_test_metadata_PRODUCTION.csv',
-        data_prefix='DF21/',
-        pipeline=[
-            dict(type='LoadImageFromFileFungi'),
-            dict(
-                type='ResizeEdge',
-                scale=438,
-                edge='short',
-                backend='pillow',
-                interpolation='bicubic'),
-            dict(type='CenterCrop', crop_size=384),
-            dict(
-                type='Normalize',
-                mean=[123.675, 116.28, 103.53],
-                std=[58.395, 57.12, 57.375],
-                to_rgb=True),
-            dict(type='PackInputs'),
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-test_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-optim_wrapper = dict(
-    optimizer=dict(
-        type='AdamW',
-        lr=6.25e-05,
-        weight_decay=0.05,
-        eps=1e-08,
-        betas=(0.9, 0.999)),
-    paramwise_cfg=dict(
-        norm_decay_mult=0.0,
-        bias_decay_mult=0.0,
-        flat_decay_mult=0.0,
-        custom_keys=dict({
-            '.absolute_pos_embed': dict(decay_mult=0.0),
-            '.relative_position_bias_table': dict(decay_mult=0.0)
-        })),
-    clip_grad=dict(max_norm=5),
-    type='AmpOptimWrapper')
-param_scheduler = [
-    dict(type='LinearLR', start_factor=0.01, by_epoch=False, end=4200),
-    dict(type='CosineAnnealingLR', eta_min=0, by_epoch=False, begin=4200)
-]
-train_cfg = dict(by_epoch=True, max_epochs=6, val_interval=1)
-val_cfg = dict()
-test_cfg = dict()
-auto_scale_lr = dict(base_batch_size=64, enable=True)
-default_scope = 'mmpretrain'
-default_hooks = dict(
-    timer=dict(type='IterTimerHook'),
-    logger=dict(type='LoggerHook', interval=100),
-    param_scheduler=dict(type='ParamSchedulerHook'),
-    checkpoint=dict(type='CheckpointHook', interval=1),
-    sampler_seed=dict(type='DistSamplerSeedHook'),
-    visualization=dict(type='VisualizationHook', enable=False))
-env_cfg = dict(
-    cudnn_benchmark=False,
-    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
-    dist_cfg=dict(backend='nccl'))
-vis_backends = [
-    dict(type='LocalVisBackend'),
-    dict(type='TensorboardVisBackend')
-]
-visualizer = dict(
-    type='UniversalVisualizer',
-    vis_backends=[
-        dict(type='LocalVisBackend'),
-        dict(type='TensorboardVisBackend')
-    ])
-log_level = 'INFO'
-load_from = None
-resume = False
-randomness = dict(seed=None, deterministic=False)
-checkpoint = 'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-base_3rdparty_in21k-384px.pth'
-custom_imports = dict(
-    imports=['mmpretrain_custom'], allow_failed_imports=False)
-launcher = 'pytorch'
-work_dir = './work_dirs/swin_base_b32x4-fp16_fungi+val_res_384_cb_epochs_6'

models/swin_base_b32x4-fp16_fungi+val_res_384_cb_epochs_6_20230524-5197a7e6.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5197a7e62e88740e7d950203e52a08996bcc3f6a648367c55ee9631e12220844
-size 358213519

models/swin_large_b12x6-fp16_fungi+val_res_384_cb_epochs_6.py

@@ -1,283 +0,0 @@
-model = dict(
-    type='ImageClassifier',
-    backbone=dict(
-        type='SwinTransformer',
-        arch='large',
-        img_size=384,
-        stage_cfgs=dict(block_cfgs=dict(window_size=12)),
-        drop_path_rate=0.5,
-        init_cfg=dict(
-            type='Pretrained',
-            checkpoint=
-            'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-base_3rdparty_in21k-384px.pth',
-            prefix='backbone')),
-    neck=dict(type='GlobalAveragePooling'),
-    head=dict(
-        type='LinearClsHead',
-        num_classes=1604,
-        in_channels=1536,
-        init_cfg=None,
-        loss=dict(
-            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
-        cal_acc=False),
-    init_cfg=[
-        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.0),
-        dict(type='Constant', layer='LayerNorm', val=1.0, bias=0.0)
-    ],
-    train_cfg=dict())
-rand_increasing_policies = [
-    dict(type='AutoContrast'),
-    dict(type='Equalize'),
-    dict(type='Invert'),
-    dict(type='Rotate', magnitude_key='angle', magnitude_range=(0, 30)),
-    dict(type='Posterize', magnitude_key='bits', magnitude_range=(4, 0)),
-    dict(type='Solarize', magnitude_key='thr', magnitude_range=(256, 0)),
-    dict(
-        type='SolarizeAdd',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 110)),
-    dict(
-        type='ColorTransform',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
-    dict(type='Contrast', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
-    dict(
-        type='Brightness', magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
-    dict(
-        type='Sharpness', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
-    dict(
-        type='Shear',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='horizontal'),
-    dict(
-        type='Shear',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='vertical'),
-    dict(
-        type='Translate',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='horizontal'),
-    dict(
-        type='Translate',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='vertical')
-]
-dataset_type = 'Fungi'
-data_preprocessor = dict(
-    num_classes=1604,
-    mean=[123.675, 116.28, 103.53],
-    std=[58.395, 57.12, 57.375],
-    to_rgb=True)
-bgr_mean = [103.53, 116.28, 123.675]
-bgr_std = [57.375, 57.12, 58.395]
-train_pipeline = [
-    dict(type='LoadImageFromFileFungi'),
-    dict(
-        type='RandomResizedCrop',
-        scale=384,
-        backend='pillow',
-        interpolation='bicubic'),
-    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-    dict(
-        type='RandAugment',
-        policies='timm_increasing',
-        num_policies=2,
-        total_level=10,
-        magnitude_level=9,
-        magnitude_std=0.5,
-        hparams=dict(pad_val=[104, 116, 124], interpolation='bicubic')),
-    dict(
-        type='RandomErasing',
-        erase_prob=0.25,
-        mode='rand',
-        min_area_ratio=0.02,
-        max_area_ratio=0.3333333333333333,
-        fill_color=[103.53, 116.28, 123.675],
-        fill_std=[57.375, 57.12, 58.395]),
-    dict(type='PackInputs')
-]
-test_pipeline = [
-    dict(type='LoadImageFromFileFungi'),
-    dict(
-        type='ResizeEdge',
-        scale=438,
-        edge='short',
-        backend='pillow',
-        interpolation='bicubic'),
-    dict(type='CenterCrop', crop_size=384),
-    dict(type='PackInputs')
-]
-train_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=32,
-    num_workers=14,
-    dataset=dict(
-        type='ClassBalancedDataset',
-        oversample_thr=0.01,
-        dataset=dict(
-            type='Fungi',
-            data_root='/scratch/slurm_tmpdir/job_22252118/',
-            ann_file='FungiCLEF2023_train_metadata_PRODUCTION.csv',
-            data_prefix='DF20/',
-            pipeline=[
-                dict(type='LoadImageFromFileFungi'),
-                dict(
-                    type='RandomResizedCrop',
-                    scale=384,
-                    backend='pillow',
-                    interpolation='bicubic'),
-                dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-                dict(
-                    type='RandAugment',
-                    policies='timm_increasing',
-                    num_policies=2,
-                    total_level=10,
-                    magnitude_level=9,
-                    magnitude_std=0.5,
-                    hparams=dict(
-                        pad_val=[104, 116, 124], interpolation='bicubic')),
-                dict(
-                    type='RandomErasing',
-                    erase_prob=0.25,
-                    mode='rand',
-                    min_area_ratio=0.02,
-                    max_area_ratio=0.3333333333333333,
-                    fill_color=[103.53, 116.28, 123.675],
-                    fill_std=[57.375, 57.12, 58.395]),
-                dict(type='PackInputs')
-            ])),
-    sampler=dict(type='DefaultSampler', shuffle=True))
-val_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=64,
-    num_workers=12,
-    dataset=dict(
-        type='Fungi',
-        data_root='/scratch/slurm_tmpdir/job_22252118/',
-        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
-        data_prefix='DF21/',
-        pipeline=[
-            dict(type='LoadImageFromFileFungi'),
-            dict(
-                type='RandomResizedCrop',
-                scale=384,
-                backend='pillow',
-                interpolation='bicubic'),
-            dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-            dict(
-                type='RandAugment',
-                policies='timm_increasing',
-                num_policies=2,
-                total_level=10,
-                magnitude_level=9,
-                magnitude_std=0.5,
-                hparams=dict(pad_val=[104, 116, 124],
-                             interpolation='bicubic')),
-            dict(
-                type='RandomErasing',
-                erase_prob=0.25,
-                mode='rand',
-                min_area_ratio=0.02,
-                max_area_ratio=0.3333333333333333,
-                fill_color=[103.53, 116.28, 123.675],
-                fill_std=[57.375, 57.12, 58.395]),
-            dict(type='PackInputs')
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-val_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-test_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=32,
-    num_workers=12,
-    dataset=dict(
-        type='FungiTest',
-        data_root='data/fungi2023/',
-        ann_file='FungiCLEF2023_public_test_metadata_PRODUCTION.csv',
-        data_prefix='DF21/',
-        pipeline=[
-            dict(type='LoadImageFromFileFungi'),
-            dict(
-                type='ResizeEdge',
-                scale=438,
-                edge='short',
-                backend='pillow',
-                interpolation='bicubic'),
-            dict(type='CenterCrop', crop_size=384),
-            dict(
-                type='Normalize',
-                mean=[123.675, 116.28, 103.53],
-                std=[58.395, 57.12, 57.375],
-                to_rgb=True),
-            dict(type='PackInputs'),
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-test_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-optim_wrapper = dict(
-    optimizer=dict(
-        type='AdamW',
-        lr=6.25e-05,
-        weight_decay=0.05,
-        eps=1e-08,
-        betas=(0.9, 0.999)),
-    paramwise_cfg=dict(
-        norm_decay_mult=0.0,
-        bias_decay_mult=0.0,
-        flat_decay_mult=0.0,
-        custom_keys=dict({
-            '.absolute_pos_embed': dict(decay_mult=0.0),
-            '.relative_position_bias_table': dict(decay_mult=0.0)
-        })),
-    clip_grad=dict(max_norm=5),
-    type='AmpOptimWrapper')
-param_scheduler = [
-    dict(type='LinearLR', start_factor=0.01, by_epoch=False, end=4200),
-    dict(type='CosineAnnealingLR', eta_min=0, by_epoch=False, begin=4200)
-]
-train_cfg = dict(by_epoch=True, max_epochs=6, val_interval=1)
-val_cfg = dict()
-test_cfg = dict()
-auto_scale_lr = dict(base_batch_size=64, enable=True)
-default_scope = 'mmpretrain'
-default_hooks = dict(
-    timer=dict(type='IterTimerHook'),
-    logger=dict(type='LoggerHook', interval=100),
-    param_scheduler=dict(type='ParamSchedulerHook'),
-    checkpoint=dict(type='CheckpointHook', interval=1),
-    sampler_seed=dict(type='DistSamplerSeedHook'),
-    visualization=dict(type='VisualizationHook', enable=False))
-env_cfg = dict(
-    cudnn_benchmark=False,
-    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
-    dist_cfg=dict(backend='nccl'))
-vis_backends = [
-    dict(type='LocalVisBackend'),
-    dict(type='TensorboardVisBackend')
-]
-visualizer = dict(
-    type='UniversalVisualizer',
-    vis_backends=[
-        dict(type='LocalVisBackend'),
-        dict(type='TensorboardVisBackend')
-    ])
-log_level = 'INFO'
-load_from = None
-resume = False
-randomness = dict(seed=None, deterministic=False)
-checkpoint = 'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-base_3rdparty_in21k-384px.pth'
-custom_imports = dict(
-    imports=['mmpretrain_custom'], allow_failed_imports=False)
-launcher = 'pytorch'
-work_dir = './work_dirs/swin_base_b32x4-fp16_fungi+val_res_384_cb_epochs_6'

models/swin_large_b12x6-fp16_fungi+val_res_384_cb_epochs_6_20230524-9582690d.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9582690db5cf1d4f8d03db3804542adb8164bbf7e9386b30cf9029661fbeb1e1
-size 794832796

models/swin_large_b12x6-fp16_fungi+val_res_384_cb_epochs_6_no-margin.py

@@ -1,283 +0,0 @@
-model = dict(
-    type='ImageClassifier',
-    backbone=dict(
-        type='SwinTransformer',
-        arch='large',
-        img_size=384,
-        stage_cfgs=dict(block_cfgs=dict(window_size=12)),
-        drop_path_rate=0.5,
-        init_cfg=dict(
-            type='Pretrained',
-            checkpoint=
-            'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-base_3rdparty_in21k-384px.pth',
-            prefix='backbone')),
-    neck=dict(type='GlobalAveragePooling'),
-    head=dict(
-        type='LinearClsHead',
-        num_classes=1604,
-        in_channels=1536,
-        init_cfg=None,
-        loss=dict(
-            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
-        cal_acc=False),
-    init_cfg=[
-        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.0),
-        dict(type='Constant', layer='LayerNorm', val=1.0, bias=0.0)
-    ],
-    train_cfg=dict())
-rand_increasing_policies = [
-    dict(type='AutoContrast'),
-    dict(type='Equalize'),
-    dict(type='Invert'),
-    dict(type='Rotate', magnitude_key='angle', magnitude_range=(0, 30)),
-    dict(type='Posterize', magnitude_key='bits', magnitude_range=(4, 0)),
-    dict(type='Solarize', magnitude_key='thr', magnitude_range=(256, 0)),
-    dict(
-        type='SolarizeAdd',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 110)),
-    dict(
-        type='ColorTransform',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
-    dict(type='Contrast', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
-    dict(
-        type='Brightness', magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
-    dict(
-        type='Sharpness', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
-    dict(
-        type='Shear',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='horizontal'),
-    dict(
-        type='Shear',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='vertical'),
-    dict(
-        type='Translate',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='horizontal'),
-    dict(
-        type='Translate',
-        magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='vertical')
-]
-dataset_type = 'Fungi'
-data_preprocessor = dict(
-    num_classes=1604,
-    mean=[123.675, 116.28, 103.53],
-    std=[58.395, 57.12, 57.375],
-    to_rgb=True)
-bgr_mean = [103.53, 116.28, 123.675]
-bgr_std = [57.375, 57.12, 58.395]
-train_pipeline = [
-    dict(type='LoadImageFromFileFungi'),
-    dict(
-        type='RandomResizedCrop',
-        scale=384,
-        backend='pillow',
-        interpolation='bicubic'),
-    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-    dict(
-        type='RandAugment',
-        policies='timm_increasing',
-        num_policies=2,
-        total_level=10,
-        magnitude_level=9,
-        magnitude_std=0.5,
-        hparams=dict(pad_val=[104, 116, 124], interpolation='bicubic')),
-    dict(
-        type='RandomErasing',
-        erase_prob=0.25,
-        mode='rand',
-        min_area_ratio=0.02,
-        max_area_ratio=0.3333333333333333,
-        fill_color=[103.53, 116.28, 123.675],
-        fill_std=[57.375, 57.12, 58.395]),
-    dict(type='PackInputs')
-]
-test_pipeline = [
-    dict(type='LoadImageFromFileFungi'),
-    dict(
-        type='ResizeEdge',
-        scale=438,
-        edge='short',
-        backend='pillow',
-        interpolation='bicubic'),
-    dict(type='CenterCrop', crop_size=384),
-    dict(type='PackInputs')
-]
-train_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=32,
-    num_workers=14,
-    dataset=dict(
-        type='ClassBalancedDataset',
-        oversample_thr=0.01,
-        dataset=dict(
-            type='Fungi',
-            data_root='/scratch/slurm_tmpdir/job_22252118/',
-            ann_file='FungiCLEF2023_train_metadata_PRODUCTION.csv',
-            data_prefix='DF20/',
-            pipeline=[
-                dict(type='LoadImageFromFileFungi'),
-                dict(
-                    type='RandomResizedCrop',
-                    scale=384,
-                    backend='pillow',
-                    interpolation='bicubic'),
-                dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-                dict(
-                    type='RandAugment',
-                    policies='timm_increasing',
-                    num_policies=2,
-                    total_level=10,
-                    magnitude_level=9,
-                    magnitude_std=0.5,
-                    hparams=dict(
-                        pad_val=[104, 116, 124], interpolation='bicubic')),
-                dict(
-                    type='RandomErasing',
-                    erase_prob=0.25,
-                    mode='rand',
-                    min_area_ratio=0.02,
-                    max_area_ratio=0.3333333333333333,
-                    fill_color=[103.53, 116.28, 123.675],
-                    fill_std=[57.375, 57.12, 58.395]),
-                dict(type='PackInputs')
-            ])),
-    sampler=dict(type='DefaultSampler', shuffle=True))
-val_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=64,
-    num_workers=12,
-    dataset=dict(
-        type='Fungi',
-        data_root='/scratch/slurm_tmpdir/job_22252118/',
-        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
-        data_prefix='DF21/',
-        pipeline=[
-            dict(type='LoadImageFromFileFungi'),
-            dict(
-                type='RandomResizedCrop',
-                scale=384,
-                backend='pillow',
-                interpolation='bicubic'),
-            dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-            dict(
-                type='RandAugment',
-                policies='timm_increasing',
-                num_policies=2,
-                total_level=10,
-                magnitude_level=9,
-                magnitude_std=0.5,
-                hparams=dict(pad_val=[104, 116, 124],
-                             interpolation='bicubic')),
-            dict(
-                type='RandomErasing',
-                erase_prob=0.25,
-                mode='rand',
-                min_area_ratio=0.02,
-                max_area_ratio=0.3333333333333333,
-                fill_color=[103.53, 116.28, 123.675],
-                fill_std=[57.375, 57.12, 58.395]),
-            dict(type='PackInputs')
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-val_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-test_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=32,
-    num_workers=12,
-    dataset=dict(
-        type='FungiTest',
-        data_root='data/fungi2023/',
-        ann_file='FungiCLEF2023_public_test_metadata_PRODUCTION.csv',
-        data_prefix='DF21/',
-        pipeline=[
-            dict(type='LoadImageFromFileFungi'),
-            dict(
-                type='ResizeEdge',
-                scale=384,
-                edge='short',
-                backend='pillow',
-                interpolation='bicubic'),
-            dict(type='CenterCrop', crop_size=384),
-            dict(
-                type='Normalize',
-                mean=[123.675, 116.28, 103.53],
-                std=[58.395, 57.12, 57.375],
-                to_rgb=True),
-            dict(type='PackInputs'),
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-test_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-optim_wrapper = dict(
-    optimizer=dict(
-        type='AdamW',
-        lr=6.25e-05,
-        weight_decay=0.05,
-        eps=1e-08,
-        betas=(0.9, 0.999)),
-    paramwise_cfg=dict(
-        norm_decay_mult=0.0,
-        bias_decay_mult=0.0,
-        flat_decay_mult=0.0,
-        custom_keys=dict({
-            '.absolute_pos_embed': dict(decay_mult=0.0),
-            '.relative_position_bias_table': dict(decay_mult=0.0)
-        })),
-    clip_grad=dict(max_norm=5),
-    type='AmpOptimWrapper')
-param_scheduler = [
-    dict(type='LinearLR', start_factor=0.01, by_epoch=False, end=4200),
-    dict(type='CosineAnnealingLR', eta_min=0, by_epoch=False, begin=4200)
-]
-train_cfg = dict(by_epoch=True, max_epochs=6, val_interval=1)
-val_cfg = dict()
-test_cfg = dict()
-auto_scale_lr = dict(base_batch_size=64, enable=True)
-default_scope = 'mmpretrain'
-default_hooks = dict(
-    timer=dict(type='IterTimerHook'),
-    logger=dict(type='LoggerHook', interval=100),
-    param_scheduler=dict(type='ParamSchedulerHook'),
-    checkpoint=dict(type='CheckpointHook', interval=1),
-    sampler_seed=dict(type='DistSamplerSeedHook'),
-    visualization=dict(type='VisualizationHook', enable=False))
-env_cfg = dict(
-    cudnn_benchmark=False,
-    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
-    dist_cfg=dict(backend='nccl'))
-vis_backends = [
-    dict(type='LocalVisBackend'),
-    dict(type='TensorboardVisBackend')
-]
-visualizer = dict(
-    type='UniversalVisualizer',
-    vis_backends=[
-        dict(type='LocalVisBackend'),
-        dict(type='TensorboardVisBackend')
-    ])
-log_level = 'INFO'
-load_from = None
-resume = False
-randomness = dict(seed=None, deterministic=False)
-checkpoint = 'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-base_3rdparty_in21k-384px.pth'
-custom_imports = dict(
-    imports=['mmpretrain_custom'], allow_failed_imports=False)
-launcher = 'pytorch'
-work_dir = './work_dirs/swin_base_b32x4-fp16_fungi+val_res_384_cb_epochs_6'

models/{swinv2_base_w24_b32x4-fp16_fungi+val_res_384_cb_epochs_6.py → swinv2_base_w24_b16x4-fp16_fungi+val_res_384_cb_epochs_6.py}

@@ -1,284 +1,366 @@
+auto_scale_lr = dict(base_batch_size=64)
+bgr_mean = [
+    103.53,
+    116.28,
+    123.675,
+]
+bgr_std = [
+    57.375,
+    57.12,
+    58.395,
+]
+checkpoint = 'https://download.openmmlab.com/mmclassification/v0/swin-v2/pretrain/swinv2-base-w12_3rdparty_in21k-192px_20220803-f7dc9763.pth'
+custom_imports = dict(
+    allow_failed_imports=False, imports=[
+        'mmpretrain_custom',
+    ])
+data_preprocessor = dict(
+    mean=[
+        123.675,
+        116.28,
+        103.53,
+    ],
+    num_classes=1604,
+    std=[
+        58.395,
+        57.12,
+        57.375,
+    ],
+    to_rgb=True)
+dataset_type = 'Fungi'
+default_hooks = dict(
+    checkpoint=dict(interval=1, type='CheckpointHook'),
+    logger=dict(interval=100, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(enable=False, type='VisualizationHook'))
+default_scope = 'mmpretrain'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+launcher = 'pytorch'
+load_from = None
+log_level = 'INFO'
 model = dict(
-    type='ImageClassifier',
     backbone=dict(
-        type='SwinTransformerV2',
         arch='base',
-        img_size=384,
         drop_path_rate=0.2,
-        window_size=[24, 24, 24, 12],
-        pretrained_window_sizes=[12, 12, 12, 6],
+        img_size=384,
         init_cfg=dict(
-            type='Pretrained',
             checkpoint=
             'https://download.openmmlab.com/mmclassification/v0/swin-v2/pretrain/swinv2-base-w12_3rdparty_in21k-192px_20220803-f7dc9763.pth',
-            prefix='backbone')),
-    neck=dict(type='GlobalAveragePooling'),
+            prefix='backbone',
+            type='Pretrained'),
+        pretrained_window_sizes=[
+            12,
+            12,
+            12,
+            6,
+        ],
+        type='SwinTransformerV2',
+        window_size=[
+            24,
+            24,
+            24,
+            12,
+        ]),
     head=dict(
-        type='LinearClsHead',
-        num_classes=1604,
+        cal_acc=False,
         in_channels=1024,
         init_cfg=None,
         loss=dict(
-            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
-        cal_acc=False),
+            label_smooth_val=0.1, mode='original', type='LabelSmoothLoss'),
+        num_classes=1604,
+        type='LinearClsHead'),
     init_cfg=[
-        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.0),
-        dict(type='Constant', layer='LayerNorm', val=1.0, bias=0.0)
+        dict(bias=0.0, layer='Linear', std=0.02, type='TruncNormal'),
+        dict(bias=0.0, layer='LayerNorm', type='Constant', val=1.0),
     ],
-    train_cfg=dict())
+    neck=dict(type='GlobalAveragePooling'),
+    train_cfg=dict(),
+    type='ImageClassifier')
+optim_wrapper = dict(
+    clip_grad=dict(max_norm=5),
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ),
+        eps=1e-08,
+        lr=3.125e-05,
+        type='AdamW',
+        weight_decay=0.05),
+    paramwise_cfg=dict(
+        bias_decay_mult=0.0,
+        custom_keys=dict({
+            '.absolute_pos_embed': dict(decay_mult=0.0),
+            '.relative_position_bias_table': dict(decay_mult=0.0)
+        }),
+        flat_decay_mult=0.0,
+        norm_decay_mult=0.0),
+    type='AmpOptimWrapper')
+param_scheduler = [
+    dict(by_epoch=False, end=4200, start_factor=0.01, type='LinearLR'),
+    dict(begin=4200, by_epoch=False, eta_min=0, type='CosineAnnealingLR'),
+]
 rand_increasing_policies = [
     dict(type='AutoContrast'),
     dict(type='Equalize'),
     dict(type='Invert'),
-    dict(type='Rotate', magnitude_key='angle', magnitude_range=(0, 30)),
-    dict(type='Posterize', magnitude_key='bits', magnitude_range=(4, 0)),
-    dict(type='Solarize', magnitude_key='thr', magnitude_range=(256, 0)),
+    dict(magnitude_key='angle', magnitude_range=(
+        0,
+        30,
+    ), type='Rotate'),
+    dict(magnitude_key='bits', magnitude_range=(
+        4,
+        0,
+    ), type='Posterize'),
+    dict(magnitude_key='thr', magnitude_range=(
+        256,
+        0,
+    ), type='Solarize'),
     dict(
-        type='SolarizeAdd',
         magnitude_key='magnitude',
-        magnitude_range=(0, 110)),
+        magnitude_range=(
+            0,
+            110,
+        ),
+        type='SolarizeAdd'),
     dict(
-        type='ColorTransform',
         magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
-    dict(type='Contrast', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
-    dict(
-        type='Brightness', magnitude_key='magnitude',
-        magnitude_range=(0, 0.9)),
+        magnitude_range=(
+            0,
+            0.9,
+        ),
+        type='ColorTransform'),
     dict(
-        type='Sharpness', magnitude_key='magnitude', magnitude_range=(0, 0.9)),
+        magnitude_key='magnitude', magnitude_range=(
+            0,
+            0.9,
+        ), type='Contrast'),
     dict(
-        type='Shear',
         magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='horizontal'),
+        magnitude_range=(
+            0,
+            0.9,
+        ),
+        type='Brightness'),
     dict(
-        type='Shear',
         magnitude_key='magnitude',
-        magnitude_range=(0, 0.3),
-        direction='vertical'),
+        magnitude_range=(
+            0,
+            0.9,
+        ),
+        type='Sharpness'),
     dict(
-        type='Translate',
+        direction='horizontal',
         magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='horizontal'),
+        magnitude_range=(
+            0,
+            0.3,
+        ),
+        type='Shear'),
     dict(
-        type='Translate',
+        direction='vertical',
         magnitude_key='magnitude',
-        magnitude_range=(0, 0.45),
-        direction='vertical')
-]
-dataset_type = 'Fungi'
-data_preprocessor = dict(
-    num_classes=1604,
-    mean=[123.675, 116.28, 103.53],
-    std=[58.395, 57.12, 57.375],
-    to_rgb=True)
-bgr_mean = [103.53, 116.28, 123.675]
-bgr_std = [57.375, 57.12, 58.395]
-train_pipeline = [
-    dict(type='LoadImageFromFileFungi'),
-    dict(
-        type='RandomResizedCrop',
-        scale=384,
-        backend='pillow',
-        interpolation='bicubic'),
-    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+        magnitude_range=(
+            0,
+            0.3,
+        ),
+        type='Shear'),
     dict(
-        type='RandAugment',
-        policies='timm_increasing',
-        num_policies=2,
-        total_level=10,
-        magnitude_level=9,
-        magnitude_std=0.5,
-        hparams=dict(pad_val=[104, 116, 124], interpolation='bicubic')),
+        direction='horizontal',
+        magnitude_key='magnitude',
+        magnitude_range=(
+            0,
+            0.45,
+        ),
+        type='Translate'),
     dict(
-        type='RandomErasing',
-        erase_prob=0.25,
-        mode='rand',
-        min_area_ratio=0.02,
-        max_area_ratio=0.3333333333333333,
-        fill_color=[103.53, 116.28, 123.675],
-        fill_std=[57.375, 57.12, 58.395]),
-    dict(type='PackInputs')
+        direction='vertical',
+        magnitude_key='magnitude',
+        magnitude_range=(
+            0,
+            0.45,
+        ),
+        type='Translate'),
 ]
+randomness = dict(deterministic=False, seed=None)
+resume = False
+test_cfg = dict()
+test_dataloader = dict(
+    batch_size=64,
+    collate_fn=dict(type='default_collate'),
+    dataset=dict(
+        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
+        data_prefix='DF21/',
+        data_root='data/fungi2024/',
+        pipeline=[
+            dict(type='LoadImageFromFileFungi'),
+            dict(
+                backend='pillow',
+                edge='short',
+                interpolation='bicubic',
+                scale=438,
+                type='ResizeEdge'),
+            dict(crop_size=384, type='CenterCrop'),
+            dict(type='PackInputs'),
+        ],
+        type='FungiTest'),
+    num_workers=8,
+    persistent_workers=True,
+    pin_memory=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    items=[
+        'precision',
+        'recall',
+        'f1-score',
+    ], type='SingleLabelMetric')
 test_pipeline = [
     dict(type='LoadImageFromFileFungi'),
     dict(
-        type='ResizeEdge',
-        scale=438,
-        edge='short',
         backend='pillow',
-        interpolation='bicubic'),
-    dict(type='CenterCrop', crop_size=384),
-    dict(type='PackInputs')
+        edge='short',
+        interpolation='bicubic',
+        scale=438,
+        type='ResizeEdge'),
+    dict(crop_size=384, type='CenterCrop'),
+    dict(type='PackInputs'),
 ]
+train_cfg = dict(by_epoch=True, max_epochs=6, val_interval=1)
 train_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
+    batch_size=16,
     collate_fn=dict(type='default_collate'),
-    batch_size=32,
-    num_workers=14,
     dataset=dict(
-        type='ClassBalancedDataset',
-        oversample_thr=0.01,
         dataset=dict(
-            type='Fungi',
-            data_root='/scratch/slurm_tmpdir/job_22252299/',
             ann_file='FungiCLEF2023_train_metadata_PRODUCTION.csv',
             data_prefix='DF20/',
+            data_root='data/fungi2024/',
             pipeline=[
                 dict(type='LoadImageFromFileFungi'),
                 dict(
-                    type='RandomResizedCrop',
-                    scale=384,
                     backend='pillow',
-                    interpolation='bicubic'),
-                dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+                    interpolation='bicubic',
+                    scale=384,
+                    type='RandomResizedCrop'),
+                dict(direction='horizontal', prob=0.5, type='RandomFlip'),
                 dict(
-                    type='RandAugment',
-                    policies='timm_increasing',
-                    num_policies=2,
-                    total_level=10,
+                    hparams=dict(
+                        interpolation='bicubic', pad_val=[
+                            104,
+                            116,
+                            124,
+                        ]),
                     magnitude_level=9,
                     magnitude_std=0.5,
-                    hparams=dict(
-                        pad_val=[104, 116, 124], interpolation='bicubic')),
+                    num_policies=2,
+                    policies='timm_increasing',
+                    total_level=10,
+                    type='RandAugment'),
                 dict(
-                    type='RandomErasing',
                     erase_prob=0.25,
-                    mode='rand',
-                    min_area_ratio=0.02,
+                    fill_color=[
+                        103.53,
+                        116.28,
+                        123.675,
+                    ],
+                    fill_std=[
+                        57.375,
+                        57.12,
+                        58.395,
+                    ],
                     max_area_ratio=0.3333333333333333,
-                    fill_color=[103.53, 116.28, 123.675],
-                    fill_std=[57.375, 57.12, 58.395]),
-                dict(type='PackInputs')
-            ])),
-    sampler=dict(type='DefaultSampler', shuffle=True))
-val_dataloader = dict(
-    pin_memory=True,
+                    min_area_ratio=0.02,
+                    mode='rand',
+                    type='RandomErasing'),
+                dict(type='PackInputs'),
+            ],
+            type='Fungi'),
+        oversample_thr=0.01,
+        type='ClassBalancedDataset'),
+    num_workers=14,
     persistent_workers=True,
+    pin_memory=True,
+    sampler=dict(shuffle=True, type='DefaultSampler'))
+train_pipeline = [
+    dict(type='LoadImageFromFileFungi'),
+    dict(
+        backend='pillow',
+        interpolation='bicubic',
+        scale=384,
+        type='RandomResizedCrop'),
+    dict(direction='horizontal', prob=0.5, type='RandomFlip'),
+    dict(
+        hparams=dict(interpolation='bicubic', pad_val=[
+            104,
+            116,
+            124,
+        ]),
+        magnitude_level=9,
+        magnitude_std=0.5,
+        num_policies=2,
+        policies='timm_increasing',
+        total_level=10,
+        type='RandAugment'),
+    dict(
+        erase_prob=0.25,
+        fill_color=[
+            103.53,
+            116.28,
+            123.675,
+        ],
+        fill_std=[
+            57.375,
+            57.12,
+            58.395,
+        ],
+        max_area_ratio=0.3333333333333333,
+        min_area_ratio=0.02,
+        mode='rand',
+        type='RandomErasing'),
+    dict(type='PackInputs'),
+]
+val_cfg = dict()
+val_dataloader = dict(
+    batch_size=16,
     collate_fn=dict(type='default_collate'),
-    batch_size=64,
-    num_workers=12,
     dataset=dict(
-        type='Fungi',
-        data_root='/scratch/slurm_tmpdir/job_22252299/',
         ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
         data_prefix='DF21/',
+        data_root='data/fungi2024/',
         pipeline=[
             dict(type='LoadImageFromFileFungi'),
             dict(
-                type='RandomResizedCrop',
-                scale=384,
                 backend='pillow',
-                interpolation='bicubic'),
-            dict(type='RandomFlip', prob=0.5, direction='horizontal'),
-            dict(
-                type='RandAugment',
-                policies='timm_increasing',
-                num_policies=2,
-                total_level=10,
-                magnitude_level=9,
-                magnitude_std=0.5,
-                hparams=dict(pad_val=[104, 116, 124],
-                             interpolation='bicubic')),
-            dict(
-                type='RandomErasing',
-                erase_prob=0.25,
-                mode='rand',
-                min_area_ratio=0.02,
-                max_area_ratio=0.3333333333333333,
-                fill_color=[103.53, 116.28, 123.675],
-                fill_std=[57.375, 57.12, 58.395]),
-            dict(type='PackInputs')
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-val_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-test_dataloader = dict(
-    pin_memory=True,
-    persistent_workers=True,
-    collate_fn=dict(type='default_collate'),
-    batch_size=64,
-    num_workers=12,
-    dataset=dict(
-        type='FungiTest',
-        data_root='data/fungi2023/',
-        ann_file='FungiCLEF2023_public_test_metadata_PRODUCTION.csv',
-        data_prefix='DF21/',
-        pipeline=[
-            dict(type='LoadImageFromFileFungi'),
-            dict(
-                type='ResizeEdge',
-                scale=438,
                 edge='short',
-                backend='pillow',
-                interpolation='bicubic'),
-            dict(type='CenterCrop', crop_size=384),
-            dict(
-                type='Normalize',
-                mean=[123.675, 116.28, 103.53],
-                std=[58.395, 57.12, 57.375],
-                to_rgb=True),
+                interpolation='bicubic',
+                scale=438,
+                type='ResizeEdge'),
+            dict(crop_size=384, type='CenterCrop'),
             dict(type='PackInputs'),
-        ]),
-    sampler=dict(type='DefaultSampler', shuffle=False))
-test_evaluator = dict(
-    type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
-optim_wrapper = dict(
-    optimizer=dict(
-        type='AdamW',
-        lr=6.25e-05,
-        weight_decay=0.05,
-        eps=1e-08,
-        betas=(0.9, 0.999)),
-    paramwise_cfg=dict(
-        norm_decay_mult=0.0,
-        bias_decay_mult=0.0,
-        flat_decay_mult=0.0,
-        custom_keys=dict({
-            '.absolute_pos_embed': dict(decay_mult=0.0),
-            '.relative_position_bias_table': dict(decay_mult=0.0)
-        })),
-    clip_grad=dict(max_norm=5),
-    type='AmpOptimWrapper')
-param_scheduler = [
-    dict(type='LinearLR', start_factor=0.01, by_epoch=False, end=4200),
-    dict(type='CosineAnnealingLR', eta_min=0, by_epoch=False, begin=4200)
-]
-train_cfg = dict(by_epoch=True, max_epochs=6, val_interval=1)
-val_cfg = dict()
-test_cfg = dict()
-auto_scale_lr = dict(base_batch_size=64, enable=True)
-default_scope = 'mmpretrain'
-default_hooks = dict(
-    timer=dict(type='IterTimerHook'),
-    logger=dict(type='LoggerHook', interval=100),
-    param_scheduler=dict(type='ParamSchedulerHook'),
-    checkpoint=dict(type='CheckpointHook', interval=1),
-    sampler_seed=dict(type='DistSamplerSeedHook'),
-    visualization=dict(type='VisualizationHook', enable=False))
-env_cfg = dict(
-    cudnn_benchmark=False,
-    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
-    dist_cfg=dict(backend='nccl'))
+        ],
+        type='Fungi'),
+    num_workers=12,
+    persistent_workers=True,
+    pin_memory=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    items=[
+        'precision',
+        'recall',
+        'f1-score',
+    ], type='SingleLabelMetric')
 vis_backends = [
     dict(type='LocalVisBackend'),
-    dict(type='TensorboardVisBackend')
+    dict(type='TensorboardVisBackend'),
 ]
 visualizer = dict(
     type='UniversalVisualizer',
     vis_backends=[
         dict(type='LocalVisBackend'),
-        dict(type='TensorboardVisBackend')
+        dict(type='TensorboardVisBackend'),
     ])
-log_level = 'INFO'
-load_from = None
-resume = False
-randomness = dict(seed=None, deterministic=False)
-checkpoint = 'https://download.openmmlab.com/mmclassification/v0/swin-v2/pretrain/swinv2-base-w12_3rdparty_in21k-192px_20220803-f7dc9763.pth'
-custom_imports = dict(
-    imports=['mmpretrain_custom'], allow_failed_imports=False)
-launcher = 'pytorch'
-work_dir = './work_dirs/swinv2_base_w24_b32x4-fp16_fungi+val_res_384_cb_epochs_6'
+work_dir = './work_dirs/swinv2_base_w24_b16x4-fp16_fungi+val_res_384_cb_epochs_6'

models/{swin_base_b16x4-fp16_fungi_res_384_cb_epochs_6_20230524-8b2afc73.pth → swinv2_base_w24_b16x4-fp16_fungi+val_res_384_cb_epochs_6_epoch_6_20240514-de00365e.pth}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2afc73898a5b36a0c4dc1224b6309ccc187ab481e12e1c6ce65992eafb5851
-size 358262964
+oid sha256:de00365e7b99a5467cb093480337fa269a7ce814fa271f68ceb5ade913762436
+size 413508870

models/swinv2_base_w24_b32x4-fp16_fungi+val_res_384_cb_epochs_6_20230524-a251a50a.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a251a50a21746e66ee6e0f790cd35104296bc6838d3b1bc490d0c930a117f774
-size 413462721

models/swinv2_base_w24_b32x4-fp16_fungi+val_res_384_cb_epochs_9_20230525-88a0bc68.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:88a0bc681d60df1eca31fc53db6595c58acfba80d3f8a0518598a01927272550
-size 413461441