mirror of
https://github.com/open-mmlab/mmpretrain.git
synced 2025-06-03 06:40:40 +08:00
bc3c4a35ee
* [Feature]: Add caption * [Feature]: Update scienceqa * [CI] Add test mim CI. (#879) * refactor imagenet dataset * refactor imagenet dataset * refactor imagenet dataset * update imagenet21k * update configs * update mnist * update dataset_prepare.md * fix sun397 url and update user_guides/dataset_prepare.md * update dataset_prepare.md * fix sun397 dataset * fix sun397 * update chinese dataset_prepare.md * update dataset_prepare.md * [Refactor] update voc dataset * [Refactor] update voc dataset * refactor imagenet * refactor imagenet * use mmengine.fileio --------- Co-authored-by: liuyuan <3463423099@qq.com> Co-authored-by: Ma Zerun <mzr1996@163.com> Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
59 lines
1.5 KiB
Python
59 lines
1.5 KiB
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)
|
|
|
|
# The difference between mocov2 and mocov1 is the transforms in the pipeline
|
|
view_pipeline = [
|
|
dict(
|
|
type='RandomResizedCrop',
|
|
scale=224,
|
|
crop_ratio_range=(0.2, 1.),
|
|
backend='pillow'),
|
|
dict(
|
|
type='RandomApply',
|
|
transforms=[
|
|
dict(
|
|
type='ColorJitter',
|
|
brightness=0.4,
|
|
contrast=0.4,
|
|
saturation=0.4,
|
|
hue=0.1)
|
|
],
|
|
prob=0.8),
|
|
dict(
|
|
type='RandomGrayscale',
|
|
prob=0.2,
|
|
keep_channels=True,
|
|
channel_weights=(0.114, 0.587, 0.2989)),
|
|
dict(
|
|
type='GaussianBlur',
|
|
magnitude_range=(0.1, 2.0),
|
|
magnitude_std='inf',
|
|
prob=0.5),
|
|
dict(type='RandomFlip', prob=0.5),
|
|
]
|
|
|
|
train_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='MultiView', num_views=2, transforms=[view_pipeline]),
|
|
dict(type='PackInputs')
|
|
]
|
|
|
|
train_dataloader = dict(
|
|
batch_size=32,
|
|
num_workers=8,
|
|
drop_last=True,
|
|
persistent_workers=True,
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
collate_fn=dict(type='default_collate'),
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
split='train',
|
|
pipeline=train_pipeline))
|