You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
102 lines
2.3 KiB
YAML
102 lines
2.3 KiB
YAML
8 months ago
|
Global:
|
||
|
|
use_gpu: True
|
||
|
|
epoch_num: 21
|
||
|
|
log_smooth_window: 20
|
||
|
|
print_batch_step: 10
|
||
|
|
save_model_dir: ./output/rec/nrtr/
|
||
|
|
save_epoch_step: 1
|
||
|
|
# evaluation is run every 2000 iterations
|
||
|
|
eval_batch_step: [0, 2000]
|
||
|
|
cal_metric_during_train: True
|
||
|
|
pretrained_model:
|
||
|
|
checkpoints:
|
||
|
|
save_inference_dir:
|
||
|
|
use_visualdl: False
|
||
|
|
infer_img: doc/imgs_words_en/word_10.png
|
||
|
|
# for data or label process
|
||
|
|
character_dict_path: ppocr/utils/EN_symbol_dict.txt
|
||
|
|
max_text_length: 25
|
||
|
|
infer_mode: False
|
||
|
|
use_space_char: False
|
||
|
|
save_res_path: ./output/rec/predicts_nrtr.txt
|
||
|
|
|
||
|
|
Optimizer:
|
||
|
|
name: Adam
|
||
|
|
beta1: 0.9
|
||
|
|
beta2: 0.99
|
||
|
|
clip_norm: 5.0
|
||
|
|
lr:
|
||
|
|
name: Cosine
|
||
|
|
learning_rate: 0.0005
|
||
|
|
warmup_epoch: 2
|
||
|
|
regularizer:
|
||
|
|
name: 'L2'
|
||
|
|
factor: 0.
|
||
|
|
|
||
|
|
Architecture:
|
||
|
|
model_type: rec
|
||
|
|
algorithm: NRTR
|
||
|
|
in_channels: 1
|
||
|
|
Transform:
|
||
|
|
Backbone:
|
||
|
|
name: MTB
|
||
|
|
cnn_num: 2
|
||
|
|
Head:
|
||
|
|
name: Transformer
|
||
|
|
d_model: 512
|
||
|
|
num_encoder_layers: 6
|
||
|
|
beam_size: -1 # When Beam size is greater than 0, it means to use beam search when evaluation.
|
||
|
|
|
||
|
|
|
||
|
|
Loss:
|
||
|
|
name: CELoss
|
||
|
|
smoothing: True
|
||
|
|
|
||
|
|
PostProcess:
|
||
|
|
name: NRTRLabelDecode
|
||
|
|
|
||
|
|
Metric:
|
||
|
|
name: RecMetric
|
||
|
|
main_indicator: acc
|
||
|
|
|
||
|
|
Train:
|
||
|
|
dataset:
|
||
|
|
name: LMDBDataSet
|
||
|
|
data_dir: ./train_data/data_lmdb_release/training/
|
||
|
|
transforms:
|
||
|
|
- DecodeImage: # load image
|
||
|
|
img_mode: BGR
|
||
|
|
channel_first: False
|
||
|
|
- NRTRLabelEncode: # Class handling label
|
||
|
|
- GrayRecResizeImg:
|
||
|
|
image_shape: [100, 32] # W H
|
||
|
|
resize_type: PIL # PIL or OpenCV
|
||
|
|
- KeepKeys:
|
||
|
|
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||
|
|
loader:
|
||
|
|
shuffle: True
|
||
|
|
batch_size_per_card: 512
|
||
|
|
drop_last: True
|
||
|
|
num_workers: 8
|
||
|
|
|
||
|
|
Eval:
|
||
|
|
dataset:
|
||
|
|
name: LMDBDataSet
|
||
|
|
data_dir: ./train_data/data_lmdb_release/evaluation/
|
||
|
|
transforms:
|
||
|
|
- DecodeImage: # load image
|
||
|
|
img_mode: BGR
|
||
|
|
channel_first: False
|
||
|
|
- NRTRLabelEncode: # Class handling label
|
||
|
|
- GrayRecResizeImg:
|
||
|
|
image_shape: [100, 32] # W H
|
||
|
|
resize_type: PIL # PIL or OpenCV
|
||
|
|
- KeepKeys:
|
||
|
|
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||
|
|
loader:
|
||
|
|
shuffle: False
|
||
|
|
drop_last: False
|
||
|
|
batch_size_per_card: 256
|
||
|
|
num_workers: 4
|
||
|
|
use_shared_memory: False
|