59 lines
1.6 KiB
Python
59 lines
1.6 KiB
Python
_base_ = [
|
|
'../_base_/models/efficientnet_v2/efficientnetv2_b0.py',
|
|
'../_base_/datasets/imagenet_bs32.py',
|
|
'../_base_/schedules/imagenet_bs256.py',
|
|
'../_base_/default_runtime.py',
|
|
]
|
|
|
|
# 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=192,
|
|
backend='pillow',
|
|
interpolation='bicubic'),
|
|
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
|
|
dict(
|
|
type='RandAugment',
|
|
policies='timm_increasing',
|
|
num_policies=2,
|
|
total_level=10,
|
|
magnitude_level=9,
|
|
magnitude_std=0.5,
|
|
hparams=dict(
|
|
pad_val=[round(x) for x in bgr_mean], interpolation='bicubic')),
|
|
dict(
|
|
type='RandomErasing',
|
|
erase_prob=0.25,
|
|
mode='rand',
|
|
min_area_ratio=0.02,
|
|
max_area_ratio=1 / 3,
|
|
fill_color=bgr_mean,
|
|
fill_std=bgr_std),
|
|
dict(type='PackInputs'),
|
|
]
|
|
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='EfficientNetCenterCrop', crop_size=224, crop_padding=0),
|
|
dict(type='PackInputs'),
|
|
]
|
|
|
|
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
|
|
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
|
|
test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
|