vit-large-p14_headless.py

_base_ = ['../_base_/default_runtime.py']

# model settings
model = dict(
    type='ImageClassifier',
    backbone=dict(
        type='VisionTransformer',
        arch='l',
        img_size=224,
        patch_size=16,
        drop_rate=0.1,
        pre_norm=True,
    ),
)

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
    dict(type='CenterCrop', crop_size=224),
    dict(type='PackInputs'),
]

test_dataloader = dict(
    batch_size=64,
    num_workers=5,
    dataset=dict(
        type='ImageNet',
        data_root='data/imagenet',
        ann_file='meta/val.txt',
        data_prefix='val',
        pipeline=test_pipeline),
    sampler=dict(type='DefaultSampler', shuffle=False),
)
test_evaluator = None