convnext_small_4xb256_fake5m-lr4e-4/convnext_small_4xb256_fake5m-lr4e-4.py

optim_wrapper = dict(
    optimizer=dict(
        type='AdamW',
        lr=0.0004,
        weight_decay=0.05,
        eps=1e-08,
        betas=(0.9, 0.999),
        _scope_='mmpretrain'),
    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)
        })),
    type='AmpOptimWrapper',
    dtype='bfloat16',
    clip_grad=None)
param_scheduler = [
    dict(type='CosineAnnealingLR', eta_min=1e-05, by_epoch=True, begin=0)
]
train_cfg = dict(by_epoch=True, max_epochs=20, val_interval=1)
val_cfg = dict()
test_cfg = dict()
auto_scale_lr = dict(base_batch_size=4096)
model = dict(
    type='ImageClassifier',
    backbone=dict(type='ConvNeXt', arch='small', drop_path_rate=0.4),
    head=dict(
        type='LinearClsHead',
        num_classes=2,
        in_channels=768,
        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
        init_cfg=None),
    init_cfg=dict(
        type='TruncNormal', layer=['Conv2d', 'Linear'], std=0.02, bias=0.0),
    train_cfg=None)
dataset_type = 'CustomDataset'
data_preprocessor = dict(
    num_classes=2,
    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='LoadImageFromFile'),
    dict(
        type='RandomResizedCrop',
        scale=224,
        backend='pillow',
        interpolation='bicubic'),
    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
    dict(type='PackInputs')
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='ResizeEdge',
        scale=256,
        edge='short',
        backend='pillow',
        interpolation='bicubic'),
    dict(type='CenterCrop', crop_size=224),
    dict(type='PackInputs')
]
train_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    batch_size=256,
    num_workers=10,
    dataset=dict(
        type='CustomDataset',
        data_root='',
        ann_file=
        '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stablediffusionV1-5R2-dpmsolver-25-5m.csv',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='RandomResizedCrop',
                scale=224,
                backend='pillow',
                interpolation='bicubic'),
            dict(type='RandomFlip', prob=0.5, direction='horizontal'),
            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=256,
    num_workers=10,
    dataset=dict(
        type='CustomDataset',
        data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
        ann_file=
        '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV1-5R2-dpmsolver-25-1w.tsv',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='ResizeEdge',
                scale=256,
                edge='short',
                backend='pillow',
                interpolation='bicubic'),
            dict(type='CenterCrop', crop_size=224),
            dict(type='PackInputs')
        ]),
    sampler=dict(type='DefaultSampler', shuffle=False))
val_evaluator = [
    dict(type='Accuracy', topk=1),
    dict(type='SingleLabelMetric', average=None)
]
test_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    batch_size=256,
    num_workers=10,
    dataset=dict(
        type='CustomDataset',
        data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
        ann_file=
        '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV1-5R2-dpmsolver-25-1w.tsv',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='ResizeEdge',
                scale=256,
                edge='short',
                backend='pillow',
                interpolation='bicubic'),
            dict(type='CenterCrop', crop_size=224),
            dict(type='PackInputs')
        ]),
    sampler=dict(type='DefaultSampler', shuffle=False))
test_evaluator = [
    dict(type='Accuracy', topk=1),
    dict(type='SingleLabelMetric', average=None)
]
custom_hooks = [dict(type='EMAHook', momentum=0.0001, priority='ABOVE_NORMAL')]
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=True))
env_cfg = dict(
    cudnn_benchmark=True,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'))
vis_backends = [dict(type='LocalVisBackend')]
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)
launcher = 'slurm'
work_dir = 'workdir/convnext_small_4xb256_fake5m-lr4e-4'