File size: 7,229 Bytes
6fa5e3d |
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 |
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoderDiffusion',
pretrained=
'work_dirs2/deeplabv3plus_r50-d8_aspp_head_unet_fc_single_step_ade_pretrained_freeze_embed_80k_ade20k151/best_mIoU_iter_64000.pth',
backbone=dict(
type='ResNetV1cCustomInitWeights',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 2, 4),
strides=(1, 2, 1, 1),
norm_cfg=dict(type='SyncBN', requires_grad=True),
norm_eval=False,
style='pytorch',
contract_dilation=True),
decode_head=dict(
type='DepthwiseSeparableASPPHeadUnetFCHeadMultiStep',
pretrained=
'work_dirs2/deeplabv3plus_r50-d8_aspp_head_unet_fc_single_step_ade_pretrained_freeze_embed_80k_ade20k151/best_mIoU_iter_64000.pth',
dim=128,
out_dim=256,
unet_channels=528,
dim_mults=[1, 1, 1],
cat_embedding_dim=16,
ignore_index=0,
diffusion_timesteps=100,
collect_timesteps=[0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 99],
in_channels=2048,
in_index=3,
channels=512,
dilations=(1, 12, 24, 36),
c1_in_channels=256,
c1_channels=48,
dropout_ratio=0.1,
num_classes=151,
norm_cfg=dict(type='SyncBN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=None,
train_cfg=dict(),
test_cfg=dict(mode='whole'),
freeze_parameters=['backbone', 'decode_head'])
dataset_type = 'ADE20K151Dataset'
data_root = 'data/ade/ADEChallengeData2016'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=False),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(512, 512), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size=(512, 512), pad_val=0, seg_pad_val=0),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=16, pad_val=0, seg_pad_val=0),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type='ADE20K151Dataset',
data_root='data/ade/ADEChallengeData2016',
img_dir='images/training',
ann_dir='annotations/training',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=False),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(512, 512), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size=(512, 512), pad_val=0, seg_pad_val=0),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]),
val=dict(
type='ADE20K151Dataset',
data_root='data/ade/ADEChallengeData2016',
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(
type='Pad', size_divisor=16, pad_val=0, seg_pad_val=0),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='ADE20K151Dataset',
data_root='data/ade/ADEChallengeData2016',
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(
type='Pad', size_divisor=16, pad_val=0, seg_pad_val=0),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
log_config = dict(
interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
cudnn_benchmark = True
optimizer = dict(
type='AdamW', lr=0.00015, betas=[0.9, 0.96], weight_decay=0.045)
optimizer_config = dict()
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=1e-06,
step=20000,
gamma=0.5,
min_lr=1e-06,
by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=160000)
checkpoint_config = dict(by_epoch=False, interval=16000, max_keep_ckpts=1)
evaluation = dict(
interval=16000, metric='mIoU', pre_eval=True, save_best='mIoU')
checkpoint = 'work_dirs2/deeplabv3plus_r50-d8_aspp_head_unet_fc_single_step_ade_pretrained_freeze_embed_80k_ade20k151/best_mIoU_iter_64000.pth'
custom_hooks = [
dict(
type='ConstantMomentumEMAHook',
momentum=0.01,
interval=25,
eval_interval=16000,
auto_resume=True,
priority=49)
]
work_dir = './work_dirs2/deeplabv3plus_r50-d8_aspp_head_unet_fc_multi_step_ade_pretrained_freeze_embed_160k_ade20k151_finetune'
gpu_ids = range(0, 8)
auto_resume = True
|