first commit
Some checks are pending
Build/Publish Develop Docs / deploy (push) Waiting to run

This commit is contained in:
2025-07-02 08:57:16 +03:00
commit 56532cc9a9
1901 changed files with 457695 additions and 0 deletions

View File

@@ -0,0 +1,123 @@
Global:
use_gpu: True
epoch_num: &epoch_num 200
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/re_layoutlmv2_xfund_zh
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_21.jpg
save_res_path: ./output/re_layoutlmv2_xfund_zh/res/
Architecture:
model_type: kie
algorithm: &algorithm "LayoutLMv2"
Transform:
Backbone:
name: LayoutLMv2ForRe
pretrained: True
checkpoints:
Loss:
name: LossFromOutput
key: loss
reduction: mean
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
clip_norm: 10
lr:
learning_rate: 0.00005
warmup_epoch: 10
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: VQAReTokenLayoutLMPostProcess
Metric:
name: VQAReTokenMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: &class_path train_data/XFUND/class_list_xfun.txt
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids','image', 'entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 8
collate_fn: ListCollator
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image','entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 8
collate_fn: ListCollator

View File

@@ -0,0 +1,123 @@
Global:
use_gpu: True
epoch_num: &epoch_num 130
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/re_layoutxlm_xfund_zh
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_21.jpg
save_res_path: ./output/re_layoutxlm_xfund_zh/res/
Architecture:
model_type: kie
algorithm: &algorithm "LayoutXLM"
Transform:
Backbone:
name: LayoutXLMForRe
pretrained: True
checkpoints:
Loss:
name: LossFromOutput
key: loss
reduction: mean
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
clip_norm: 10
lr:
learning_rate: 0.00005
warmup_epoch: 10
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: VQAReTokenLayoutLMPostProcess
Metric:
name: VQAReTokenMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: &class_path train_data/XFUND/class_list_xfun.txt
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- TensorizeEntitiesRelations:
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox','attention_mask', 'token_type_ids', 'image', 'entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 2
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- TensorizeEntitiesRelations:
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 8

View File

@@ -0,0 +1,121 @@
Global:
use_gpu: True
epoch_num: &epoch_num 200
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/ser_layoutlm_xfund_zh
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_42.jpg
save_res_path: ./output/re_layoutlm_xfund_zh/res
Architecture:
model_type: kie
algorithm: &algorithm "LayoutLM"
Transform:
Backbone:
name: LayoutLMForSer
pretrained: True
checkpoints:
num_classes: &num_classes 7
Loss:
name: VQASerTokenLayoutLMLoss
num_classes: *num_classes
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
lr:
name: Linear
learning_rate: 0.00005
epochs: *epoch_num
warmup_epoch: 2
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: VQASerTokenLayoutLMPostProcess
class_path: &class_path train_data/XFUND/class_list_xfun.txt
Metric:
name: VQASerTokenMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 16
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 4

View File

@@ -0,0 +1,122 @@
Global:
use_gpu: True
epoch_num: &epoch_num 200
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/ser_layoutlmv2_xfund_zh/
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_42.jpg
save_res_path: ./output/ser_layoutlmv2_xfund_zh/res/
Architecture:
model_type: kie
algorithm: &algorithm "LayoutLMv2"
Transform:
Backbone:
name: LayoutLMv2ForSer
pretrained: True
checkpoints:
num_classes: &num_classes 7
Loss:
name: VQASerTokenLayoutLMLoss
num_classes: *num_classes
key: "backbone_out"
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
lr:
name: Linear
learning_rate: 0.00005
epochs: *epoch_num
warmup_epoch: 2
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: VQASerTokenLayoutLMPostProcess
class_path: &class_path train_data/XFUND/class_list_xfun.txt
Metric:
name: VQASerTokenMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 4

View File

@@ -0,0 +1,122 @@
Global:
use_gpu: True
epoch_num: &epoch_num 200
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/ser_layoutxlm_xfund_zh
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_42.jpg
save_res_path: ./output/ser_layoutxlm_xfund_zh/res
Architecture:
model_type: kie
algorithm: &algorithm "LayoutXLM"
Transform:
Backbone:
name: LayoutXLMForSer
pretrained: True
checkpoints:
num_classes: &num_classes 7
Loss:
name: VQASerTokenLayoutLMLoss
num_classes: *num_classes
key: "backbone_out"
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
lr:
name: Linear
learning_rate: 0.00005
epochs: *epoch_num
warmup_epoch: 2
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: VQASerTokenLayoutLMPostProcess
class_path: &class_path train_data/XFUND/class_list_xfun.txt
Metric:
name: VQASerTokenMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 4

View File

@@ -0,0 +1,111 @@
Global:
use_gpu: True
epoch_num: 60
log_smooth_window: 20
print_batch_step: 50
save_model_dir: ./output/kie_5/
save_epoch_step: 50
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [ 0, 80 ]
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: False
cal_metric_during_train: False
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
class_path: &class_path ./train_data/wildreceipt/class_list.txt
infer_img: ./train_data/wildreceipt/1.txt
save_res_path: ./output/sdmgr_kie/predicts_kie.txt
img_scale: [ 1024, 512 ]
Architecture:
model_type: kie
algorithm: SDMGR
Transform:
Backbone:
name: Kie_backbone
Head:
name: SDMGRHead
Loss:
name: SDMGRLoss
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Piecewise
learning_rate: 0.001
decay_epochs: [ 60, 80, 100]
values: [ 0.001, 0.0001, 0.00001]
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0.00005
PostProcess:
name: None
Metric:
name: KIEMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/wildreceipt/
label_file_list: [ './train_data/wildreceipt/wildreceipt_train.txt' ]
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- KieLabelEncode: # Class handling label
character_dict_path: ./train_data/wildreceipt/dict.txt
class_path: *class_path
- KieResize:
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'image', 'relations', 'texts', 'points', 'labels', 'tag', 'shape'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 4
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/wildreceipt
label_file_list:
- ./train_data/wildreceipt/wildreceipt_test.txt
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- KieLabelEncode: # Class handling label
character_dict_path: ./train_data/wildreceipt/dict.txt
- KieResize:
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'image', 'relations', 'texts', 'points', 'labels', 'tag', 'ori_image', 'ori_boxes', 'shape']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 4

View File

@@ -0,0 +1,130 @@
Global:
use_gpu: True
epoch_num: &epoch_num 130
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/re_vi_layoutxlm_xfund_zh
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_21.jpg
save_res_path: ./output/re/xfund_zh/with_gt
kie_rec_model_dir:
kie_det_model_dir:
Architecture:
model_type: kie
algorithm: &algorithm "LayoutXLM"
Transform:
Backbone:
name: LayoutXLMForRe
pretrained: True
mode: vi
checkpoints:
Loss:
name: LossFromOutput
key: loss
reduction: mean
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
clip_norm: 10
lr:
learning_rate: 0.00005
warmup_epoch: 10
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: VQAReTokenLayoutLMPostProcess
Metric:
name: VQAReTokenMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: &class_path train_data/XFUND/class_list_xfun.txt
use_textline_bbox_info: &use_textline_bbox_info True
order_method: &order_method "tb-yx"
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- TensorizeEntitiesRelations:
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox','attention_mask', 'token_type_ids', 'entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 2
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: *class_path
use_textline_bbox_info: *use_textline_bbox_info
order_method: *order_method
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- TensorizeEntitiesRelations:
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 8

View File

@@ -0,0 +1,175 @@
Global:
use_gpu: True
epoch_num: &epoch_num 130
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/re_vi_layoutxlm_xfund_zh_udml
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_21.jpg
save_res_path: ./output/re/xfund_zh/with_gt
Architecture:
model_type: &model_type "kie"
name: DistillationModel
algorithm: Distillation
Models:
Teacher:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: &algorithm "LayoutXLM"
Transform:
Backbone:
name: LayoutXLMForRe
pretrained: True
mode: vi
checkpoints:
Student:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: *algorithm
Transform:
Backbone:
name: LayoutXLMForRe
pretrained: True
mode: vi
checkpoints:
Loss:
name: CombinedLoss
loss_config_list:
- DistillationLossFromOutput:
weight: 1.0
model_name_list: ["Student", "Teacher"]
key: loss
reduction: mean
- DistillationVQADistanceLoss:
weight: 0.5
mode: "l2"
model_name_pairs:
- ["Student", "Teacher"]
key: hidden_states
index: 5
name: "loss_5"
- DistillationVQADistanceLoss:
weight: 0.5
mode: "l2"
model_name_pairs:
- ["Student", "Teacher"]
key: hidden_states
index: 8
name: "loss_8"
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
clip_norm: 10
lr:
learning_rate: 0.00005
warmup_epoch: 10
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: DistillationRePostProcess
model_name: ["Student", "Teacher"]
key: null
Metric:
name: DistillationMetric
base_metric_name: VQAReTokenMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: &class_path train_data/XFUND/class_list_xfun.txt
use_textline_bbox_info: &use_textline_bbox_info True
# [None, "tb-yx"]
order_method: &order_method "tb-yx"
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- TensorizeEntitiesRelations:
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox','attention_mask', 'token_type_ids', 'entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 2
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: True
algorithm: *algorithm
class_path: *class_path
use_textline_bbox_info: *use_textline_bbox_info
order_method: *order_method
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQAReTokenRelation:
- VQAReTokenChunk:
max_seq_len: *max_seq_len
- TensorizeEntitiesRelations:
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'entities', 'relations'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 8

View File

@@ -0,0 +1,138 @@
Global:
use_gpu: True
epoch_num: &epoch_num 200
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/ser_vi_layoutxlm_xfund_zh
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_42.jpg
d2s_train_image_shape: [3, 224, 224]
# if you want to predict using the groundtruth ocr info,
# you can use the following config
# infer_img: train_data/XFUND/zh_val/val.json
# infer_mode: False
save_res_path: ./output/ser/xfund_zh/res
kie_rec_model_dir:
kie_det_model_dir:
amp_custom_white_list: ['scale', 'concat', 'elementwise_add']
Architecture:
model_type: kie
algorithm: &algorithm "LayoutXLM"
Transform:
Backbone:
name: LayoutXLMForSer
pretrained: True
checkpoints:
# one of base or vi
mode: vi
num_classes: &num_classes 7
Loss:
name: VQASerTokenLayoutLMLoss
num_classes: *num_classes
key: "backbone_out"
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
lr:
name: Linear
learning_rate: 0.00005
epochs: *epoch_num
warmup_epoch: 2
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: VQASerTokenLayoutLMPostProcess
class_path: &class_path train_data/XFUND/class_list_xfun.txt
Metric:
name: VQASerTokenMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
use_textline_bbox_info: &use_textline_bbox_info True
# one of [None, "tb-yx"]
order_method: &order_method "tb-yx"
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
use_textline_bbox_info: *use_textline_bbox_info
order_method: *order_method
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 4

View File

@@ -0,0 +1,182 @@
Global:
use_gpu: True
epoch_num: &epoch_num 200
log_smooth_window: 10
print_batch_step: 10
save_model_dir: ./output/ser_vi_layoutxlm_xfund_zh_udml
save_epoch_step: 2000
# evaluation is run every 10 iterations after the 0th iteration
eval_batch_step: [ 0, 19 ]
cal_metric_during_train: False
save_inference_dir:
use_visualdl: False
seed: 2022
infer_img: ppstructure/docs/kie/input/zh_val_42.jpg
save_res_path: ./output/ser_layoutxlm_xfund_zh/res
Architecture:
model_type: &model_type "kie"
name: DistillationModel
algorithm: Distillation
Models:
Teacher:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: &algorithm "LayoutXLM"
Transform:
Backbone:
name: LayoutXLMForSer
pretrained: True
# one of base or vi
mode: vi
checkpoints:
num_classes: &num_classes 7
Student:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: *algorithm
Transform:
Backbone:
name: LayoutXLMForSer
pretrained: True
# one of base or vi
mode: vi
checkpoints:
num_classes: *num_classes
Loss:
name: CombinedLoss
loss_config_list:
- DistillationVQASerTokenLayoutLMLoss:
weight: 1.0
model_name_list: ["Student", "Teacher"]
key: backbone_out
num_classes: *num_classes
- DistillationSERDMLLoss:
weight: 1.0
act: "softmax"
use_log: true
model_name_pairs:
- ["Student", "Teacher"]
key: backbone_out
- DistillationVQADistanceLoss:
weight: 0.5
mode: "l2"
model_name_pairs:
- ["Student", "Teacher"]
key: hidden_states_5
name: "loss_5"
- DistillationVQADistanceLoss:
weight: 0.5
mode: "l2"
model_name_pairs:
- ["Student", "Teacher"]
key: hidden_states_8
name: "loss_8"
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
lr:
name: Linear
learning_rate: 0.00005
epochs: *epoch_num
warmup_epoch: 10
regularizer:
name: L2
factor: 0.00000
PostProcess:
name: DistillationSerPostProcess
model_name: ["Student", "Teacher"]
key: backbone_out
class_path: &class_path train_data/XFUND/class_list_xfun.txt
Metric:
name: DistillationMetric
base_metric_name: VQASerTokenMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_train/image
label_file_list:
- train_data/XFUND/zh_train/train.json
ratio_list: [ 1.0 ]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
# one of [None, "tb-yx"]
order_method: &order_method "tb-yx"
- VQATokenPad:
max_seq_len: &max_seq_len 512
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 4
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/XFUND/zh_val/image
label_file_list:
- train_data/XFUND/zh_val/val.json
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- VQATokenLabelEncode: # Class handling label
contains_re: False
algorithm: *algorithm
class_path: *class_path
order_method: *order_method
- VQATokenPad:
max_seq_len: *max_seq_len
return_attention_mask: True
- VQASerTokenChunk:
max_seq_len: *max_seq_len
- Resize:
size: [224,224]
- NormalizeImage:
scale: 1
mean: [ 123.675, 116.28, 103.53 ]
std: [ 58.395, 57.12, 57.375 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 8
num_workers: 4