File size: 7,250 Bytes
985cc7f |
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 |
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
backbone=dict(
type='VisionTransformer',
model_name='vit_base_patch16_224',
img_size=768,
patch_size=16,
in_chans=3,
embed_dim=768,
depth=12,
num_heads=12,
num_classes=104,
drop_rate=0.0,
norm_cfg=dict(type='SyncBN', requires_grad=True),
pos_embed_interp=True,
align_corners=False),
decode_head=dict(
type='VisionTransformerUpHead',
in_channels=768,
channels=512,
in_index=11,
img_size=768,
embed_dim=768,
num_classes=104,
norm_cfg=dict(type='SyncBN', requires_grad=True),
num_conv=2,
upsampling_method='bilinear',
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=[
dict(
type='VisionTransformerUpHead',
in_channels=768,
channels=512,
in_index=5,
img_size=768,
embed_dim=768,
num_classes=104,
norm_cfg=dict(type='SyncBN', requires_grad=True),
num_conv=2,
upsampling_method='bilinear',
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='VisionTransformerUpHead',
in_channels=768,
channels=512,
in_index=7,
img_size=768,
embed_dim=768,
num_classes=104,
norm_cfg=dict(type='SyncBN', requires_grad=True),
num_conv=2,
upsampling_method='bilinear',
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
dict(
type='VisionTransformerUpHead',
in_channels=768,
channels=512,
in_index=9,
img_size=768,
embed_dim=768,
num_classes=104,
norm_cfg=dict(type='SyncBN', requires_grad=True),
num_conv=2,
upsampling_method='bilinear',
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4))
])
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(768, 768), stride=(512, 512))
dataset_type = 'CustomDataset'
data_root = './data/FoodSeg103/Images/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (768, 768)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(768, 768), 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=(768, 768), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2049, 1025),
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='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=2,
train=dict(
type='CustomDataset',
data_root='./data/FoodSeg103/Images/',
img_dir='img_dir/train',
ann_dir='ann_dir/train',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(768, 768), 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=(768, 768), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]),
val=dict(
type='CustomDataset',
data_root='./data/FoodSeg103/Images/',
img_dir='img_dir/test',
ann_dir='ann_dir/test',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2049, 1025),
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='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CustomDataset',
data_root='./data/FoodSeg103/Images/',
img_dir='img_dir/test',
ann_dir='ann_dir/test',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2049, 1025),
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='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='SGD',
lr=0.01,
momentum=0.9,
weight_decay=0.0,
paramwise_cfg=dict(custom_keys=dict(head=dict(lr_mult=10.0))))
optimizer_config = dict()
lr_config = dict(policy='poly', power=0.9, min_lr=0.0001, by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=80000)
checkpoint_config = dict(by_epoch=False, interval=4000)
evaluation = dict(interval=4000, metric='mIoU')
find_unused_parameters = True
work_dir = 'checkpoints/SETR_Naive_RMP'
gpu_ids = range(0, 1)
|