add SLANet ch config
parent
6eca179e96
commit
6a27f58992
configs/table
|
@ -0,0 +1,141 @@
|
|||
Global:
|
||||
use_gpu: True
|
||||
epoch_num: 400
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 20
|
||||
save_model_dir: ./output/SLANet_ch
|
||||
save_epoch_step: 400
|
||||
# evaluation is run every 331 iterations after the 0th iteration
|
||||
eval_batch_step: [0, 331]
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir: ./output/SLANet_ch/infer
|
||||
use_visualdl: False
|
||||
infer_img: doc/table/table.jpg
|
||||
# for data or label process
|
||||
character_dict_path: ppocr/utils/dict/table_structure_dict_ch.txt
|
||||
character_type: en
|
||||
max_text_length: &max_text_length 500
|
||||
box_format: &box_format xyxyxyxy # 'xywh', 'xyxy', 'xyxyxyxy'
|
||||
infer_mode: False
|
||||
use_sync_bn: True
|
||||
save_res_path: output/infer
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
clip_norm: 5.0
|
||||
lr:
|
||||
learning_rate: 0.001
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.00000
|
||||
|
||||
Architecture:
|
||||
model_type: table
|
||||
algorithm: SLANet
|
||||
Backbone:
|
||||
name: PPLCNet
|
||||
scale: 1.0
|
||||
pretrained: True
|
||||
use_ssld: True
|
||||
Neck:
|
||||
name: CSPPAN
|
||||
out_channels: 96
|
||||
Head:
|
||||
name: SLAHead
|
||||
hidden_size: 256
|
||||
max_text_length: *max_text_length
|
||||
loc_reg_num: &loc_reg_num 8
|
||||
|
||||
Loss:
|
||||
name: SLALoss
|
||||
structure_weight: 1.0
|
||||
loc_weight: 2.0
|
||||
loc_loss: smooth_l1
|
||||
|
||||
PostProcess:
|
||||
name: TableLabelDecode
|
||||
merge_no_span_structure: &merge_no_span_structure True
|
||||
|
||||
Metric:
|
||||
name: TableMetric
|
||||
main_indicator: acc
|
||||
compute_bbox_metric: False
|
||||
loc_reg_num: *loc_reg_num
|
||||
box_format: *box_format
|
||||
del_thead_tbody: True
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: PubTabDataSet
|
||||
data_dir: /path/to/train_data/
|
||||
label_file_list: [/path/to/train_gt.txt]
|
||||
transforms:
|
||||
- DecodeImage:
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- TableLabelEncode:
|
||||
learn_empty_box: False
|
||||
merge_no_span_structure: *merge_no_span_structure
|
||||
replace_empty_cell_token: False
|
||||
loc_reg_num: *loc_reg_num
|
||||
max_text_length: *max_text_length
|
||||
- TableBoxEncode:
|
||||
in_box_format: *box_format
|
||||
out_box_format: *box_format
|
||||
- ResizeTableImage:
|
||||
max_len: 488
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
order: 'hwc'
|
||||
- PaddingTableImage:
|
||||
size: [488, 488]
|
||||
- ToCHWImage:
|
||||
- KeepKeys:
|
||||
keep_keys: [ 'image', 'structure', 'bboxes', 'bbox_masks', 'shape' ]
|
||||
loader:
|
||||
shuffle: True
|
||||
batch_size_per_card: 48
|
||||
drop_last: True
|
||||
num_workers: 1
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: PubTabDataSet
|
||||
data_dir: /path/to/val_data/
|
||||
label_file_list: [/path/to/val_gt.txt]
|
||||
transforms:
|
||||
- DecodeImage:
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- TableLabelEncode:
|
||||
learn_empty_box: False
|
||||
merge_no_span_structure: *merge_no_span_structure
|
||||
replace_empty_cell_token: False
|
||||
loc_reg_num: *loc_reg_num
|
||||
max_text_length: *max_text_length
|
||||
- TableBoxEncode:
|
||||
in_box_format: *box_format
|
||||
out_box_format: *box_format
|
||||
- ResizeTableImage:
|
||||
max_len: 488
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
order: 'hwc'
|
||||
- PaddingTableImage:
|
||||
size: [488, 488]
|
||||
- ToCHWImage:
|
||||
- KeepKeys:
|
||||
keep_keys: [ 'image', 'structure', 'bboxes', 'bbox_masks', 'shape' ]
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size_per_card: 48
|
||||
num_workers: 1
|
Loading…
Reference in New Issue