PaddleOCR/configs/rec/rec_mv3_none_none_ctc_lmdb.yml

106 lines
2.3 KiB
YAML

Global:
use_gpu: false
epoch_num: 500
log_smooth_window: 20
print_batch_step: 1
save_model_dir: ./output/rec/test/
save_epoch_step: 500
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: 1016
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: True
pretrained_model:
checkpoints: #output/rec/rec_crnn/best_accuracy
save_inference_dir:
use_visualdl: True
infer_img: doc/imgs_words/ch/word_1.jpg
# for data or label process
max_text_length: 80
character_dict_path: /home/zhoujun20/rec/lmdb/dict.txt
character_type: 'en'
use_space_char: True
infer_mode: False
use_tps: False
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
learning_rate:
name: Cosine
lr: 0.0005
warmup_epoch: 1
regularizer:
name: 'L2'
factor: 0.00001
Architecture:
type: rec
algorithm: CRNN
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: small
small_stride: [ 1, 2, 2, 2 ]
Neck:
name: SequenceEncoder
encoder_type: reshape
Head:
name: CTC
fc_decay: 0.00001
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
TRAIN:
dataset:
name: LMDBDateSet
file_list:
- /Users/zhoujun20/Downloads/evaluation_new # dataset1
ratio_list: [ 0.4,0.6 ]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecAug:
- RecResizeImg:
image_shape: [ 3,32,320 ]
- keepKeys:
keep_keys: [ 'image','label','length' ] # dataloader将按照此顺序返回list
loader:
batch_size: 256
shuffle: True
drop_last: True
num_workers: 8
EVAL:
dataset:
name: LMDBDateSet
file_list:
- /home/zhoujun20/rec/lmdb/val
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [ 3,32,320 ]
- keepKeys:
keep_keys: [ 'image','label','length' ] # dataloader将按照此顺序返回list
loader:
shuffle: False
drop_last: False
batch_size: 256
num_workers: 8