File size: 9,957 Bytes
6410dbb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 |
optim_wrapper = dict(
optimizer=dict(
type='AdamW',
lr=0.0004,
weight_decay=0.05,
eps=1e-08,
betas=(0.9, 0.999),
_scope_='mmpretrain'),
paramwise_cfg=dict(
norm_decay_mult=0.0,
bias_decay_mult=0.0,
flat_decay_mult=0.0,
custom_keys=dict({
'.absolute_pos_embed': dict(decay_mult=0.0),
'.relative_position_bias_table': dict(decay_mult=0.0)
})),
type='AmpOptimWrapper',
dtype='bfloat16',
clip_grad=None)
param_scheduler = [
dict(type='CosineAnnealingLR', eta_min=1e-05, by_epoch=False, begin=0)
]
train_cfg = dict(by_epoch=True, max_epochs=10, val_interval=1)
val_cfg = dict()
test_cfg = dict()
auto_scale_lr = dict(base_batch_size=4096)
model = dict(
type='ImageClassifier',
backbone=dict(
frozen_stages=2,
type='ConvNeXt',
arch='small',
drop_path_rate=0.4,
init_cfg=dict(
type='Pretrained',
checkpoint=
'https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth',
prefix='backbone')),
head=dict(
type='LinearClsHead',
num_classes=2,
in_channels=768,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
init_cfg=None),
init_cfg=dict(
type='TruncNormal', layer=['Conv2d', 'Linear'], std=0.02, bias=0.0),
train_cfg=None)
dataset_type = 'CustomDataset'
data_preprocessor = dict(
num_classes=2,
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True)
bgr_mean = [103.53, 116.28, 123.675]
bgr_std = [57.375, 57.12, 58.395]
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='ResizeEdge',
scale=256,
edge='short',
backend='pillow',
interpolation='bicubic'),
dict(type='CenterCrop', crop_size=224),
dict(type='PackInputs')
]
train_dataloader = dict(
pin_memory=True,
persistent_workers=True,
collate_fn=dict(type='default_collate'),
batch_size=256,
num_workers=10,
dataset=dict(
type='ConcatDataset',
datasets=[
dict(
type='CustomDataset',
data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
ann_file=
'/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/IF80w.csv',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
]),
dict(
type='CustomDataset',
data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
ann_file=
'/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/if-dpmsolver++-50-20w.tsv',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
]),
dict(
type='CustomDataset',
data_root='',
ann_file=
'/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/cc1m.csv',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
])
]),
sampler=dict(type='DefaultSampler', shuffle=True))
val_dataloader = dict(
pin_memory=True,
persistent_workers=True,
collate_fn=dict(type='default_collate'),
batch_size=256,
num_workers=10,
dataset=dict(
type='ConcatDataset',
datasets=[
dict(
type='CustomDataset',
data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
ann_file=
'/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/if-dpmsolver++-25-1w.tsv',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
]),
dict(
type='CustomDataset',
data_root='',
ann_file=
'/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/cc1w.csv',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
])
]),
sampler=dict(type='DefaultSampler', shuffle=False))
val_evaluator = [
dict(type='Accuracy', topk=1),
dict(type='SingleLabelMetric', average=None)
]
test_dataloader = dict(
pin_memory=True,
persistent_workers=True,
collate_fn=dict(type='default_collate'),
batch_size=256,
num_workers=10,
dataset=dict(
type='ConcatDataset',
datasets=[
dict(
type='CustomDataset',
data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
ann_file=
'/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/if-dpmsolver++-25-1w.tsv',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
]),
dict(
type='CustomDataset',
data_root='',
ann_file=
'/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/cc1w.csv',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
scale=224,
backend='pillow',
interpolation='bicubic'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='JPEG', compress_val=65, prob=0.5),
dict(type='GaussianBlur', radius=1.5, prob=0.5),
dict(type='PackInputs')
])
]),
sampler=dict(type='DefaultSampler', shuffle=False))
test_evaluator = [
dict(type='Accuracy', topk=1),
dict(type='SingleLabelMetric', average=None)
]
custom_hooks = [dict(type='EMAHook', momentum=0.0001, priority='ABOVE_NORMAL')]
default_scope = 'mmpretrain'
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=100),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', interval=1),
sampler_seed=dict(type='DistSamplerSeedHook'),
visualization=dict(type='VisualizationHook', enable=True))
env_cfg = dict(
cudnn_benchmark=True,
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
dist_cfg=dict(backend='nccl'))
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
type='UniversalVisualizer',
vis_backends=[
dict(type='LocalVisBackend'),
dict(type='TensorboardVisBackend')
])
log_level = 'INFO'
load_from = None
resume = False
randomness = dict(seed=None, deterministic=False)
launcher = 'slurm'
work_dir = 'workdir/convnext_small_4xb256_IF_1m_lr4e-4_aug_5e-1'
|