fastmim_vit_base_cfg.py

# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
crop_size = (512, 512)
model = dict(
    type='EncoderDecoder',
    pretrained='/cache/vit_base_fastmim_hog_800e_finetune_100e.pth',
    backbone=dict(
        type='ViTBEiT',
        img_size=512,
        patch_size=16,
        embed_dim=768,
        depth=12,
        num_heads=12,
        mlp_ratio=4,
        qkv_bias=True,
        use_abs_pos_emb=True,
        use_rel_pos_bias=True,
        init_values=1.,
        drop_path_rate=0.1,
        out_indices=[1, 3, 9, 11]),
    decode_head=dict(
        type='UPerHead',
        in_channels=[768, 768, 768, 768],
        in_index=[0, 1, 2, 3],
        pool_scales=(1, 2, 3, 6),
        channels=768,
        dropout_ratio=0.1,
        num_classes=150,
        norm_cfg=norm_cfg,
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    auxiliary_head=dict(
        type='FCNHead',
        in_channels=768,
        in_index=3,
        channels=256,
        num_convs=1,
        concat_input=False,
        dropout_ratio=0.1,
        num_classes=150,
        norm_cfg=norm_cfg,
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
    # model training and testing settings
    train_cfg=dict(),
    test_cfg=dict(mode='slide', crop_size=crop_size, stride=(341, 341)))  # yapf: disable
# dataset settings
dataset_type = 'ADE20KDataset'
data_root = '/cache/data/ade/ADEChallengeData2016'
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', reduce_zero_label=True),
    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PhotoMetricDistortion'),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(2048, 512),
        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        data_root=data_root,
        img_dir='images/training',
        ann_dir='annotations/training',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        data_root=data_root,
        img_dir='images/validation',
        ann_dir='annotations/validation',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        data_root=data_root,
        img_dir='images/validation',
        ann_dir='annotations/validation',
        pipeline=test_pipeline))
# optimizer
optimizer = dict(type='AdamW', lr=3e-4, betas=(0.9, 0.999), weight_decay=0.05,
                 constructor='LayerDecayOptimizerConstructor', paramwise_cfg=dict(num_layers=12, layer_decay_rate=0.75))
optimizer_config = dict()
# learning policy
lr_config = dict(policy='poly', warmup='linear', warmup_iters=1500, warmup_ratio=1e-6, power=1.0,
                 min_lr=0.0, by_epoch=False)
# runtime settings
runner = dict(type='IterBasedRunner', max_iters=160000)
checkpoint_config = dict(by_epoch=False, interval=16000)
evaluation = dict(interval=16000, metric='mIoU', pre_eval=True)
# yapf:disable
log_config = dict(
    interval=1000,
    hooks=[
        dict(type='TextLoggerHook', by_epoch=False),
        # dict(type='TensorboardLoggerHook')
        # dict(type='PaviLoggerHook') # for internal services
    ])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
cudnn_benchmark = True