Spaces:
Running
Running
File size: 3,021 Bytes
29f689c |
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 |
Global:
device: gpu
epoch_num: 10
log_smooth_window: 20
print_batch_step: 10
output_dir: ./output/rec/u14m_filter/svtrv2_visionlan_LF1/
eval_epoch_step: [0, 1]
eval_batch_step: [0, 500]
cal_metric_during_train: True
pretrained_model:
checkpoints:
use_tensorboard: false
infer_img:
# for data or label process
character_dict_path: &character_dict_path ./tools/utils/EN_symbol_dict.txt # 96en
# ./tools/utils/ppocr_keys_v1.txt # ch
max_text_length: &max_text_length 25
use_space_char: &use_space_char False
save_res_path: ./output/rec/u14m_filter/predicts_svtrv2_visionlan_LF1.txt
grad_clip_val: 20
use_amp: True
Optimizer:
name: AdamW
lr: 0.00065 # for 4gpus bs256/gpu
weight_decay: 0.05
filter_bias_and_bn: True
LRScheduler:
name: OneCycleLR
warmup_epoch: 1.5 # pct_start 0.075*20 = 1.5ep
cycle_momentum: False
Architecture:
model_type: rec
algorithm: VisionLAN
Transform:
Encoder:
name: SVTRv2LNConvTwo33
use_pos_embed: False
dims: [128, 256, 384]
depths: [6, 6, 6]
num_heads: [4, 8, 12]
mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','FGlobal','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
local_k: [[5, 5], [5, 5], [-1, -1]]
sub_k: [[1, 1], [2, 1], [-1, -1]]
last_stage: false
feat2d: True
Decoder:
name: VisionLANDecoder
training_step: &training_step 'LF_1'
n_position: 128
Loss:
name: VisionLANLoss
training_step: *training_step
PostProcess:
name: VisionLANLabelDecode
character_dict_path: *character_dict_path
use_space_char: *use_space_char
Metric:
name: RecMetric
main_indicator: acc
is_filter: True
Train:
dataset:
name: LMDBDataSet
data_dir: ../Union14M-L-LMDB-Filtered
transforms:
- DecodeImagePIL: # load image
img_mode: RGB
- PARSeqAugPIL:
- VisionLANLabelEncode:
character_dict_path: *character_dict_path
use_space_char: *use_space_char
max_text_length: *max_text_length
- RecTVResize:
image_shape: [32, 128]
padding: False
- KeepKeys:
keep_keys: ['image', 'label', 'label_res', 'label_sub', 'label_id', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 256
drop_last: True
num_workers: 4
Eval:
dataset:
name: LMDBDataSet
data_dir: ../evaluation
transforms:
- DecodeImagePIL: # load image
img_mode: RGB
- VisionLANLabelEncode:
character_dict_path: *character_dict_path
use_space_char: *use_space_char
max_text_length: *max_text_length
- RecTVResize:
image_shape: [32, 128]
padding: False
- KeepKeys:
keep_keys: ['image', 'label', 'label_res', 'label_sub', 'label_id', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 2
|