mmpretrain/configs/resnest/resnest50_32xb64_in1k.py

_base_ = ['../_base_/models/resnest50.py', '../_base_/default_runtime.py']

# dataset settings
dataset_type = 'ImageNet'
img_lighting_cfg = dict(
    eigval=[55.4625, 4.7940, 1.1475],
    eigvec=[[-0.5675, 0.7192, 0.4009], [-0.5808, -0.0045, -0.8140],
            [-0.5836, -0.6948, 0.4203]],
    alphastd=0.1,
    to_rgb=True)
policies = [
    dict(type='AutoContrast', prob=0.5),
    dict(type='Equalize', prob=0.5),
    dict(type='Invert', prob=0.5),
    dict(
        type='Rotate',
        magnitude_key='angle',
        magnitude_range=(0, 30),
        pad_val=0,
        prob=0.5,
        random_negative_prob=0.5),
    dict(
        type='Posterize',
        magnitude_key='bits',
        magnitude_range=(0, 4),
        prob=0.5),
    dict(
        type='Solarize',
        magnitude_key='thr',
        magnitude_range=(0, 256),
        prob=0.5),
    dict(
        type='SolarizeAdd',
        magnitude_key='magnitude',
        magnitude_range=(0, 110),
        thr=128,
        prob=0.5),
    dict(
        type='ColorTransform',
        magnitude_key='magnitude',
        magnitude_range=(-0.9, 0.9),
        prob=0.5,
        random_negative_prob=0.),
    dict(
        type='Contrast',
        magnitude_key='magnitude',
        magnitude_range=(-0.9, 0.9),
        prob=0.5,
        random_negative_prob=0.),
    dict(
        type='Brightness',
        magnitude_key='magnitude',
        magnitude_range=(-0.9, 0.9),
        prob=0.5,
        random_negative_prob=0.),
    dict(
        type='Sharpness',
        magnitude_key='magnitude',
        magnitude_range=(-0.9, 0.9),
        prob=0.5,
        random_negative_prob=0.),
    dict(
        type='Shear',
        magnitude_key='magnitude',
        magnitude_range=(0, 0.3),
        pad_val=0,
        prob=0.5,
        direction='horizontal',
        random_negative_prob=0.5),
    dict(
        type='Shear',
        magnitude_key='magnitude',
        magnitude_range=(0, 0.3),
        pad_val=0,
        prob=0.5,
        direction='vertical',
        random_negative_prob=0.5),
    dict(
        type='Cutout',
        magnitude_key='shape',
        magnitude_range=(1, 41),
        pad_val=0,
        prob=0.5),
    dict(
        type='Translate',
        magnitude_key='magnitude',
        magnitude_range=(0, 0.3),
        pad_val=0,
        prob=0.5,
        direction='horizontal',
        random_negative_prob=0.5,
        interpolation='bicubic'),
    dict(
        type='Translate',
        magnitude_key='magnitude',
        magnitude_range=(0, 0.3),
        pad_val=0,
        prob=0.5,
        direction='vertical',
        random_negative_prob=0.5,
        interpolation='bicubic')
]
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='RandAugment',
        policies=policies,
        num_policies=2,
        magnitude_level=12),
    dict(
        type='RandomResizedCrop',
        size=224,
        efficientnet_style=True,
        interpolation='bicubic',
        backend='pillow'),
    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
    dict(type='ColorJitter', brightness=0.4, contrast=0.4, saturation=0.4),
    dict(type='Lighting', **img_lighting_cfg),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=False),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='ToTensor', keys=['gt_label']),
    dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='CenterCrop',
        crop_size=224,
        efficientnet_style=True,
        interpolation='bicubic',
        backend='pillow'),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='ImageToTensor', keys=['img']),
    dict(type='Collect', keys=['img'])
]
data = dict(
    samples_per_gpu=64,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        data_prefix='data/imagenet/train',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        data_prefix='data/imagenet/val',
        ann_file='data/imagenet/meta/val.txt',
        pipeline=test_pipeline),
    test=dict(
        # replace `data/val` with `data/test` for standard test
        type=dataset_type,
        data_prefix='data/imagenet/val',
        ann_file='data/imagenet/meta/val.txt',
        pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')

# optimizer
optimizer = dict(
    type='SGD',
    lr=0.8,
    momentum=0.9,
    weight_decay=1e-4,
    paramwise_cfg=dict(bias_decay_mult=0., norm_decay_mult=0.))
optimizer_config = dict(grad_clip=None)

# learning policy
param_scheduler = [
    dict(type='LinearLR', start_factor=1e-6, by_epoch=True, begin=0, end=5),
    dict(type='CosineAnnealingLR', T_max=265, by_epoch=True, begin=5, end=270)
]
# train, val, test setting
train_cfg = dict(by_epoch=True, max_epochs=270)
val_cfg = dict(interval=1)  # validate every epoch
test_cfg = dict()