mmsegmentation/configs/segmenter/segmenter_vit-l_mask_8xb1-160k_ade20k-512x512.py

_base_ = [
    '../_base_/models/segmenter_vit-b16_mask.py',
    '../_base_/datasets/ade20k_640x640.py', '../_base_/default_runtime.py',
    '../_base_/schedules/schedule_160k.py'
]
crop_size = (640, 640)
data_preprocessor = dict(size=crop_size)
checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segmenter/vit_large_p16_384_20220308-d4efb41d.pth'  # noqa

model = dict(
    data_preprocessor=data_preprocessor,
    pretrained=checkpoint,
    backbone=dict(
        type='VisionTransformer',
        img_size=(640, 640),
        embed_dims=1024,
        num_layers=24,
        num_heads=16),
    decode_head=dict(
        type='SegmenterMaskTransformerHead',
        in_channels=1024,
        channels=1024,
        num_heads=16,
        embed_dims=1024),
    test_cfg=dict(mode='slide', crop_size=(640, 640), stride=(608, 608)))

optimizer = dict(lr=0.001, weight_decay=0.0)
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
train_dataloader = dict(
    # num_gpus: 8 -> batch_size: 8
    batch_size=1)
val_dataloader = dict(batch_size=1)