mmpretrain/configs/_base_/datasets/imagenet_bs512_mae.py

34 lines
908 B
Python

# dataset settings
dataset_type = 'ImageNet'
data_root = 'data/imagenet/'
data_preprocessor = dict(
type='SelfSupDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=224,
scale=(0.2, 1.0),
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5),
dict(type='PackSelfSupInputs', meta_keys=['img_path'])
]
train_dataloader = dict(
batch_size=512,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
collate_fn=dict(type='default_collate'),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='meta/train.txt',
data_prefix=dict(img_path='train/'),
pipeline=train_pipeline))