-
Notifications
You must be signed in to change notification settings - Fork 317
/
upernet_swin_small_patch4_windown7_512x512_160k_ade20k.yaml
64 lines (60 loc) · 1.64 KB
/
upernet_swin_small_patch4_windown7_512x512_160k_ade20k.yaml
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
DATA:
BATCH_SIZE: 2 # per GPU [total bs is set to 8 or 16]
BATCH_SIZE_VAL: 1 # per GPU
DATASET: 'ADE20K' # dataset name
DATA_PATH: '/home/ssd3/wutianyi/datasets/ADEChallengeData2016'
CROP_SIZE: (512,512) # input_size (training)
NUM_CLASSES: 150
MODEL:
NAME: 'UperNet_Swin'
ENCODER:
TYPE: 'SwinTransformer'
OUT_INDICES: [0, 1, 2, 3] # stage_i
PRETRAINED: './pretrain_models/backbones/vit_large_patch16_224.pdparams'
DECODER_TYPE: 'UperHead'
UPERHEAD:
IN_CHANNELS: [96, 192, 384, 768]
IN_INDEX: [0, 1, 2, 3]
POOL_SCALES: [1, 2, 3, 6]
CHANNELS: 512
DROP_RATIO: 0.1
ALIGN_CORNERS: False
TRANS:
PATCH_SIZE: 4
WINDOW_SIZE: 7
IN_CHANNELS: 3
HIDDEN_SIZE: 96 # 768(Base), 1024(Large), 1280(Huge)
EMBED_DIM: 96
STAGE_DEPTHS: [2, 2, 18, 2]
NUM_HEADS: [3, 6, 12, 24]
MLP_RATIO: 4
QKV_BIAS: True
QK_SCALE: None
APE: False # absolute positional embeddings
PATCH_NORM: True
AUX:
AUXIHEAD: True
AUXFCN:
IN_CHANNELS: 384
UP_RATIO: 16
TRAIN:
BASE_LR: 0.00006
END_LR: 1e-4
DECODER_LR_COEF: 10.0
ITERS: 160000
POWER: 0.9
DECAY_STEPS: 160000
LR_SCHEDULER:
NAME: 'PolynomialDecay'
OPTIMIZER:
WEIGHT_DECAY: 0.0
GRAD_CLIP: 1.0
NAME: 'SGD'
MOMENTUM: 0.9
VAL:
MULTI_SCALES_VAL: False
SCALE_RATIOS: [0.5, 0.75, 1.0]
IMAGE_BASE_SIZE: 512
CROP_SIZE: [512,512]
STRIDE_SIZE: [341,341]
SAVE_DIR: "./output/UperNet_swin_small_patch4_windown7_512x512_160k_ade20k"