root
4 years ago
commit
f6daae41e5
@ -0,0 +1,102 @@
|
||||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 72
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/rec/rec_mv3_tps_bilstm_att/
|
||||
save_epoch_step: 3
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: [0, 2000]
|
||||
# if pretrained_model is saved in static mode, load_static_weights must set to True
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_words/ch/word_1.jpg
|
||||
# for data or label process
|
||||
character_dict_path:
|
||||
character_type: en
|
||||
max_text_length: 25
|
||||
infer_mode: False
|
||||
use_space_char: False
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
learning_rate: 0.0005
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.00001
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: RARE
|
||||
Transform:
|
||||
name: TPS
|
||||
num_fiducial: 20
|
||||
loc_lr: 0.1
|
||||
model_name: small
|
||||
Backbone:
|
||||
name: MobileNetV3
|
||||
scale: 0.5
|
||||
model_name: large
|
||||
Neck:
|
||||
name: SequenceEncoder
|
||||
encoder_type: rnn
|
||||
hidden_size: 96
|
||||
Head:
|
||||
name: AttentionHead
|
||||
hidden_size: 96
|
||||
|
||||
|
||||
Loss:
|
||||
name: AttentionLoss
|
||||
|
||||
PostProcess:
|
||||
name: AttnLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: LMDBDateSet
|
||||
data_dir: ../training/
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- AttnLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 100]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: True
|
||||
batch_size_per_card: 256
|
||||
drop_last: True
|
||||
num_workers: 8
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: LMDBDateSet
|
||||
data_dir: ../validation/
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- AttnLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 100]
|
||||
- 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: 1
|
||||
@ -0,0 +1,101 @@
|
||||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 400
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/rec/b3_rare_r34_none_gru/
|
||||
save_epoch_step: 3
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: [0, 2000]
|
||||
# if pretrained_model is saved in static mode, load_static_weights must set to True
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_words/ch/word_1.jpg
|
||||
# for data or label process
|
||||
character_dict_path:
|
||||
character_type: en
|
||||
max_text_length: 25
|
||||
infer_mode: False
|
||||
use_space_char: False
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
learning_rate: 0.0005
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.00000
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: RARE
|
||||
Transform:
|
||||
name: TPS
|
||||
num_fiducial: 20
|
||||
loc_lr: 0.1
|
||||
model_name: large
|
||||
Backbone:
|
||||
name: ResNet
|
||||
layers: 34
|
||||
Neck:
|
||||
name: SequenceEncoder
|
||||
encoder_type: rnn
|
||||
hidden_size: 256 #96
|
||||
Head:
|
||||
name: AttentionHead # AttentionHead
|
||||
hidden_size: 256 #
|
||||
l2_decay: 0.00001
|
||||
|
||||
Loss:
|
||||
name: AttentionLoss
|
||||
|
||||
PostProcess:
|
||||
name: AttnLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: LMDBDateSet
|
||||
data_dir: ../training/
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- AttnLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 100]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: True
|
||||
batch_size_per_card: 256
|
||||
drop_last: True
|
||||
num_workers: 8
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: LMDBDateSet
|
||||
data_dir: ../validation/
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- AttnLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 100]
|
||||
- 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: 8
|
||||
@ -0,0 +1,107 @@
|
||||
Global:
|
||||
use_gpu: True
|
||||
epoch_num: 72
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 5
|
||||
save_model_dir: ./output/rec/srn_new
|
||||
save_epoch_step: 3
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: [0, 5000]
|
||||
# if pretrained_model is saved in static mode, load_static_weights must set to True
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_words/ch/word_1.jpg
|
||||
# for data or label process
|
||||
character_dict_path:
|
||||
character_type: en
|
||||
max_text_length: 25
|
||||
num_heads: 8
|
||||
infer_mode: False
|
||||
use_space_char: False
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
clip_norm: 10.0
|
||||
lr:
|
||||
learning_rate: 0.0001
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: SRN
|
||||
in_channels: 1
|
||||
Transform:
|
||||
Backbone:
|
||||
name: ResNetFPN
|
||||
Head:
|
||||
name: SRNHead
|
||||
max_text_length: 25
|
||||
num_heads: 8
|
||||
num_encoder_TUs: 2
|
||||
num_decoder_TUs: 4
|
||||
hidden_dims: 512
|
||||
|
||||
Loss:
|
||||
name: SRNLoss
|
||||
|
||||
PostProcess:
|
||||
name: SRNLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: LMDBDataSet
|
||||
data_dir: ./train_data/srn_train_data_duiqi
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- SRNLabelEncode: # Class handling label
|
||||
- SRNRecResizeImg:
|
||||
image_shape: [1, 64, 256]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image',
|
||||
'label',
|
||||
'length',
|
||||
'encoder_word_pos',
|
||||
'gsrm_word_pos',
|
||||
'gsrm_slf_attn_bias1',
|
||||
'gsrm_slf_attn_bias2'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: False
|
||||
batch_size_per_card: 64
|
||||
drop_last: False
|
||||
num_workers: 4
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: LMDBDataSet
|
||||
data_dir: ./train_data/data_lmdb_release/evaluation
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- SRNLabelEncode: # Class handling label
|
||||
- SRNRecResizeImg:
|
||||
image_shape: [1, 64, 256]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image',
|
||||
'label',
|
||||
'length',
|
||||
'encoder_word_pos',
|
||||
'gsrm_word_pos',
|
||||
'gsrm_slf_attn_bias1',
|
||||
'gsrm_slf_attn_bias2']
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size_per_card: 32
|
||||
num_workers: 4
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue