update slanet and vi_layoutxlm_ser tipc config (#9838)

* update table_mv3 tipc config

* update slanet tipc config

* update num_workers of vi_layoutxlm_ser

* add ch_PP-OCRv4_mobile_rec

* add PP-OCRv4

* update slanet tipc config

* change python3.7 to python

* update vi_layoutxlm_ser config

* update slanet tipc config

* update v4 rec config

test_tipc/configs/ch_PP-OCRv4_mobile_det/train_infer_python.txt

+===========================train_params===========================
+model_name:ch_PP-OCRv4_mobile_det
+python:python
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
+Global.pretrained_model:pretrain_models/PPLCNetV3_x0_75_ocr_det.pdparams
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml -o Global.print_batch_step=1 Train.loader.shuffle=false Global.eval_batch_step=[4000,400]
+pact_train:null
+fpgm_train:null
+distill_train:null
+to_static_train:Global.to_static=true
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml -o 
+quant_export:null
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv3_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+===========================train_benchmark_params==========================
+batch_size:8
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
+===========================to_static_train_benchmark_params===========================
+to_static_train:Global.to_static=true
\ No newline at end of file

test_tipc/configs/ch_PP-OCRv4_mobile_rec/train_infer_python.txt

+===========================train_params===========================
+model_name:ch_PP-OCRv4_mobile_rec
+python:python
+gpu_list:0
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml -o Global.cal_metric_during_train=False Global.print_batch_step=1 Train.loader.shuffle=false Train.dataset.data_dir=./train_data/ic15_data Train.dataset.label_file_list=[./train_data/ic15_data/rec_gt_train.txt] Eval.dataset.data_dir=./train_data/ic15_data Eval.dataset.label_file_list=[./train_data/ic15_data/rec_gt_test.txt] Train.loader.num_workers=16 Eval.loader.num_workers=16
+pact_train:null
+fpgm_train:null
+distill_train:null
+to_static_train:Global.to_static=true
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/ch_PP-OCRv4_rec_infer
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,48,320]}]
+===========================train_benchmark_params==========================
+batch_size:128
+fp_items:fp32|fp16
+epoch:1
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
+===========================to_static_train_benchmark_params===========================
+to_static_train:Global.to_static=true

test_tipc/configs/ch_PP-OCRv4_server_det/train_infer_python.txt

+===========================train_params===========================
+model_name:ch_PP-OCRv4_server_det
+python:python
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
+Global.pretrained_model:pretrain_models/PPHGNet_small_ocr_det.pdparams
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_teacher.yml -o Global.print_batch_step=1 Train.loader.shuffle=false Global.eval_batch_step=[4000,400]
+pact_train:null
+fpgm_train:null
+distill_train:null
+to_static_train:Global.to_static=true
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_teacher.yml -o 
+quant_export:null
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv3_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+===========================train_benchmark_params==========================
+batch_size:4
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
+===========================to_static_train_benchmark_params===========================
+to_static_train:Global.to_static=true
\ No newline at end of file

test_tipc/configs/ch_PP-OCRv4_server_rec/train_infer_python.txt

+===========================train_params===========================
+model_name:ch_PP-OCRv4_server_rec
+python:python
+gpu_list:0
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml -o Global.cal_metric_during_train=False Global.print_batch_step=1 Train.loader.shuffle=false Train.dataset.data_dir=./train_data/ic15_data Train.dataset.label_file_list=[./train_data/ic15_data/rec_gt_train.txt] Eval.dataset.data_dir=./train_data/ic15_data Eval.dataset.label_file_list=[./train_data/ic15_data/rec_gt_test.txt] Train.loader.num_workers=16 Eval.loader.num_workers=16
+pact_train:null
+fpgm_train:null
+distill_train:null
+to_static_train:Global.to_static=true
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/ch_PP-OCRv4_rec_infer
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,48,320]}]
+===========================train_benchmark_params==========================
+batch_size:128
+fp_items:fp32|fp16
+epoch:1
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
+===========================to_static_train_benchmark_params===========================
+to_static_train:Global.to_static=true

test_tipc/configs/slanet/SLANet.yml

-Global:
-  use_gpu: true
-  epoch_num: 100
-  log_smooth_window: 20
-  print_batch_step: 20
-  save_model_dir: ./output/SLANet
-  save_epoch_step: 400
-  # evaluation is run every 1000 iterations after the 0th iteration
-  eval_batch_step: [0, 1000]
-  cal_metric_during_train: True
-  pretrained_model:
-  checkpoints:
-  save_inference_dir: ./output/SLANet/infer
-  use_visualdl: False
-  infer_img: ppstructure/docs/table/table.jpg
-  # for data or label process
-  character_dict_path: ppocr/utils/dict/table_structure_dict.txt
-  character_type: en
-  max_text_length: &max_text_length 500
-  box_format: &box_format 'xyxy' # 'xywh', 'xyxy', 'xyxyxyxy'
-  infer_mode: False
-  use_sync_bn: True
-  save_res_path: 'output/infer'
-  d2s_train_image_shape: [3, -1, -1]
-  amp_custom_white_list: ['concat', 'elementwise_sub', 'set_value']
-
-Optimizer:
-  name: Adam
-  beta1: 0.9
-  beta2: 0.999
-  clip_norm: 5.0
-  lr:
-    name: Piecewise
-    learning_rate: 0.001
-    decay_epochs : [40, 50]
-    values : [0.001, 0.0001, 0.00005]
-  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 4
-
-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
-
-Train:
-  dataset:
-    name: PubTabDataSet
-    data_dir: ./train_data/pubtabnet/train/
-    label_file_list: [./train_data/pubtabnet/train.jsonl]
-    transforms:
-      - DecodeImage: # load image
-          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: ./train_data/pubtabnet/test/
-    label_file_list: [./train_data/pubtabnet/test.jsonl]
-    transforms:
-      - DecodeImage: # load image
-          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

test_tipc/configs/slanet/train_infer_python.txt

 ===========================train_params===========================
 model_name:slanet
-python:python3.7
+python:python
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:fp32
@@ -13,7 +13,7 @@ train_infer_img_dir:./ppstructure/docs/table/table.jpg
 null:null
 ##
 trainer:norm_train
-norm_train:tools/train.py -c test_tipc/configs/slanet/SLANet.yml -o Global.print_batch_step=1 Train.loader.shuffle=false
+norm_train:tools/train.py -c configs/table/SLANet.yml -o Global.cal_metric_during_train=False Global.print_batch_step=1 Train.loader.shuffle=false Train.dataset.data_dir=./train_data/pubtabnet/train Train.dataset.label_file_list=[./train_data/pubtabnet/train.jsonl] Eval.dataset.data_dir=./train_data/pubtabnet/test Eval.dataset.label_file_list=[./train_data/pubtabnet/test.jsonl]
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -27,7 +27,7 @@ null:null
 ===========================infer_params===========================
 Global.save_inference_dir:./output/
 Global.checkpoints:
-norm_export:tools/export_model.py -c test_tipc/configs/slanet/SLANet.yml -o
+norm_export:tools/export_model.py -c configs/table/SLANet.yml -o
 quant_export:
 fpgm_export: 
 distill_export:null
@@ -52,7 +52,7 @@ null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,488,488]}]
 ===========================train_benchmark_params==========================
-batch_size:32
+batch_size:64
 fp_items:fp32|fp16
 epoch:2
 --profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile

test_tipc/configs/vi_layoutxlm_ser/train_infer_python.txt

 ===========================train_params===========================
 model_name:vi_layoutxlm_ser
-python:python3.7
+python:python
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:fp32
@@ -13,7 +13,7 @@ train_infer_img_dir:ppstructure/docs/kie/input/zh_val_42.jpg
 null:null
 ##
 trainer:norm_train
-norm_train:tools/train.py -c ./configs/kie/vi_layoutxlm/ser_vi_layoutxlm_xfund_zh.yml -o Global.print_batch_step=1 Global.eval_batch_step=[1000,1000] Train.loader.shuffle=false
+norm_train:tools/train.py -c ./configs/kie/vi_layoutxlm/ser_vi_layoutxlm_xfund_zh.yml -o Global.print_batch_step=1 Global.eval_batch_step=[1000,1000] Train.loader.shuffle=false Train.loader.num_workers=32 Eval.loader.num_workers=32
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -52,7 +52,7 @@ null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,224,224]}]
 ===========================train_benchmark_params==========================
-batch_size:4
+batch_size:8
 fp_items:fp32|fp16
 epoch:3
 --profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile

test_tipc/prepare.sh

@@ -40,6 +40,22 @@ if [ ${MODE} = "benchmark_train" ];then
             cd ../../../
         fi
     fi
+    if [[ ${model_name} =~ "ch_PP-OCRv4_mobile_det" ]];then
+        wget -nc -P  ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/PPLCNetV3_x0_75_ocr_det.pdparams  --no-check-certificate
+        rm -rf ./train_data/icdar2015
+        wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
+        cd ./train_data/ && tar xf icdar2015_benckmark.tar
+        ln -s ./icdar2015_benckmark ./icdar2015
+        cd ../
+    fi
+    if [[ ${model_name} =~ "ch_PP-OCRv4_server_det" ]];then
+        wget -nc -P  ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/PPHGNet_small_ocr_det.pdparams  --no-check-certificate
+        rm -rf ./train_data/icdar2015
+        wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
+        cd ./train_data/ && tar xf icdar2015_benckmark.tar
+        ln -s ./icdar2015_benckmark ./icdar2015
+        cd ../
+    fi
     if [[ ${model_name} =~ "ch_ppocr_server_v2_0_det" || ${model_name} =~ "ch_PP-OCRv3_det" ]];then
         rm -rf ./train_data/icdar2015
         wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
@@ -88,7 +104,7 @@ if [ ${MODE} = "benchmark_train" ];then
         ln -s ./ic15_data_benckmark ./ic15_data
         cd ../
     fi
-    if [[ ${model_name} =~ "ch_PP-OCRv2_rec" || ${model_name} =~ "ch_PP-OCRv3_rec" ]];then
+    if [[ ${model_name} =~ "ch_PP-OCRv2_rec" || ${model_name} =~ "ch_PP-OCRv3_rec" || ${model_name} =~ "ch_PP-OCRv4_mobile_rec" || ${model_name} =~ "ch_PP-OCRv4_server_rec" ]];then
         rm -rf ./train_data/ic15_data
         wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/ic15_data_benckmark.tar --no-check-certificate
         cd ./train_data/ && tar xf ic15_data_benckmark.tar
@@ -181,6 +197,12 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
         wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar --no-check-certificate
         cd ./pretrain_models/ && tar xf ch_PP-OCRv3_det_distill_train.tar && cd ../
     fi
+    if [[ ${model_name} =~ "ch_PP-OCRv4_mobile_det" ]];then
+        wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/PPLCNetV3_x0_75_ocr_det.pdparams --no-check-certificate
+    fi
+    if [[ ${model_name} =~ "ch_PP-OCRv4_server_det" ]];then
+        wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/PPHGNet_small_ocr_det.pdparams --no-check-certificate
+    fi
     if [ ${model_name} == "en_table_structure" ] || [ ${model_name} == "en_table_structure_PACT" ];then
         wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar --no-check-certificate
         cd ./pretrain_models/ && tar xf en_ppocr_mobile_v2.0_table_structure_train.tar  && cd ../