71 lines
1.9 KiB
Python
71 lines
1.9 KiB
Python
# dataset settings
|
|
dataset_type = 'ImageNet'
|
|
data_preprocessor = dict(
|
|
num_classes=1000,
|
|
# RGB format normalization parameters
|
|
mean=[123.675, 116.28, 103.53],
|
|
std=[58.395, 57.12, 57.375],
|
|
# convert image from BGR to RGB
|
|
to_rgb=True,
|
|
)
|
|
|
|
bgr_mean = data_preprocessor['mean'][::-1]
|
|
bgr_std = data_preprocessor['std'][::-1]
|
|
|
|
train_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='RandomResizedCrop', scale=224, backend='pillow'),
|
|
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
|
|
dict(
|
|
type='AutoAugment',
|
|
policies='imagenet',
|
|
hparams=dict(pad_val=[round(x) for x in bgr_mean])),
|
|
dict(
|
|
type='RandomErasing',
|
|
erase_prob=0.2,
|
|
mode='rand',
|
|
min_area_ratio=0.02,
|
|
max_area_ratio=1 / 3,
|
|
fill_color=bgr_mean,
|
|
fill_std=bgr_std),
|
|
dict(type='PackClsInputs'),
|
|
]
|
|
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
|
|
dict(type='CenterCrop', crop_size=224),
|
|
dict(type='PackClsInputs'),
|
|
]
|
|
|
|
train_dataloader = dict(
|
|
batch_size=128,
|
|
num_workers=5,
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root='data/imagenet',
|
|
ann_file='meta/train.txt',
|
|
data_prefix='train',
|
|
pipeline=train_pipeline),
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
persistent_workers=True,
|
|
)
|
|
|
|
val_dataloader = dict(
|
|
batch_size=128,
|
|
num_workers=5,
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root='data/imagenet',
|
|
ann_file='meta/val.txt',
|
|
data_prefix='val',
|
|
pipeline=test_pipeline),
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
persistent_workers=True,
|
|
)
|
|
val_evaluator = dict(type='Accuracy', topk=(1, 5))
|
|
|
|
# If you want standard test, please manually configure the test dataset
|
|
test_dataloader = val_dataloader
|
|
test_evaluator = val_evaluator
|