144 lines
3.1 KiB
YAML
144 lines
3.1 KiB
YAML
Global:
|
|
debug: false
|
|
use_gpu: true
|
|
epoch_num: 200
|
|
log_smooth_window: 20
|
|
print_batch_step: 10
|
|
save_model_dir: ./output/rec_svtrv2_ch
|
|
save_epoch_step: 10
|
|
eval_batch_step: [0, 1000]
|
|
cal_metric_during_train: False
|
|
pretrained_model:
|
|
checkpoints:
|
|
save_inference_dir:
|
|
use_visualdl: false
|
|
infer_img: doc/imgs_words/ch/word_1.jpg
|
|
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
|
|
max_text_length: &max_text_length 25
|
|
infer_mode: false
|
|
use_space_char: true
|
|
distributed: true
|
|
save_res_path: ./output/rec/predicts_svrtv2.txt
|
|
d2s_train_image_shape: [3, 48, 320]
|
|
|
|
Optimizer:
|
|
name: AdamW
|
|
beta1: 0.9
|
|
beta2: 0.999
|
|
epsilon: 1.e-8
|
|
weight_decay: 0.05
|
|
no_weight_decay_name: norm
|
|
one_dim_param_no_weight_decay: True
|
|
lr:
|
|
name: Cosine
|
|
learning_rate: 0.001 # 8gpus 192bs
|
|
warmup_epoch: 5
|
|
|
|
|
|
Architecture:
|
|
model_type: rec
|
|
algorithm: SVTR_HGNet
|
|
Transform:
|
|
Backbone:
|
|
name: SVTRv2
|
|
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','Global','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
|
|
local_k: [[5, 5], [5, 5], [-1, -1]]
|
|
sub_k: [[2, 1], [2, 1], [-1, -1]]
|
|
last_stage: False
|
|
use_pool: True
|
|
Head:
|
|
name: MultiHead
|
|
head_list:
|
|
- CTCHead:
|
|
Neck:
|
|
name: svtr
|
|
dims: 256
|
|
depth: 2
|
|
hidden_dims: 256
|
|
kernel_size: [1, 3]
|
|
use_guide: True
|
|
Head:
|
|
fc_decay: 0.00001
|
|
- NRTRHead:
|
|
nrtr_dim: 384
|
|
max_text_length: *max_text_length
|
|
num_decoder_layers: 2
|
|
|
|
Loss:
|
|
name: MultiLoss
|
|
loss_config_list:
|
|
- CTCLoss:
|
|
- NRTRLoss:
|
|
|
|
PostProcess:
|
|
name: CTCLabelDecode
|
|
|
|
Metric:
|
|
name: RecMetric
|
|
main_indicator: acc
|
|
|
|
Train:
|
|
dataset:
|
|
name: MultiScaleDataSet
|
|
ds_width: false
|
|
data_dir: ./train_data/
|
|
ext_op_transform_idx: 1
|
|
label_file_list:
|
|
- ./train_data/train_list.txt
|
|
transforms:
|
|
- DecodeImage:
|
|
img_mode: BGR
|
|
channel_first: false
|
|
- RecAug:
|
|
- MultiLabelEncode:
|
|
gtc_encode: NRTRLabelEncode
|
|
- KeepKeys:
|
|
keep_keys:
|
|
- image
|
|
- label_ctc
|
|
- label_gtc
|
|
- length
|
|
- valid_ratio
|
|
sampler:
|
|
name: MultiScaleSampler
|
|
scales: [[320, 32], [320, 48], [320, 64]]
|
|
first_bs: &bs 192
|
|
fix_bs: false
|
|
divided_factor: [8, 16] # w, h
|
|
is_training: True
|
|
loader:
|
|
shuffle: true
|
|
batch_size_per_card: *bs
|
|
drop_last: true
|
|
num_workers: 8
|
|
Eval:
|
|
dataset:
|
|
name: SimpleDataSet
|
|
data_dir: ./train_data
|
|
label_file_list:
|
|
- ./train_data/val_list.txt
|
|
transforms:
|
|
- DecodeImage:
|
|
img_mode: BGR
|
|
channel_first: false
|
|
- MultiLabelEncode:
|
|
gtc_encode: NRTRLabelEncode
|
|
- RecResizeImg:
|
|
image_shape: [3, 48, 320]
|
|
- KeepKeys:
|
|
keep_keys:
|
|
- image
|
|
- label_ctc
|
|
- label_gtc
|
|
- length
|
|
- valid_ratio
|
|
loader:
|
|
shuffle: false
|
|
drop_last: false
|
|
batch_size_per_card: 128
|
|
num_workers: 4
|