add layoutxlm

test_tipc/configs/det_r50_vd_sast_totaltext_v2_0/train_infer_python.txt

@@ -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/det_r50_vd_sast_totaltext_v2.0/det_r50_vd_sast_totaltext.yml -o 
+norm_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_sast_totaltext_v2_0/det_r50_vd_sast_totaltext.yml -o 
 quant_export:null
 fpgm_export:null
 distill_export:null
@@ -35,7 +35,7 @@ export1:null
 export2:null
 inference_dir:null
 train_model:./inference/det_r50_vd_sast_totaltext_v2.0_train/best_accuracy
-infer_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_sast_totaltext_v2.0/det_r50_vd_sast_totaltext.yml -o
+infer_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_sast_totaltext_v2_0/det_r50_vd_sast_totaltext.yml -o
 infer_quant:False
 inference:tools/infer/predict_det.py
 --use_gpu:True|False

test_tipc/configs/layoutxlm/train_infer_python.txt

+===========================train_params===========================
+model_name:layoutxlm
+python:python3.7
+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=17
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=8|whole_train_whole_infer=8
+Architecture.Backbone.checkpoints:null
+train_model_name:latest
+train_infer_img_dir:ppstructure/docs/vqa/input/zh_val_42.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/vqa/ser/layoutxlm_xfund_zh.yml -o Global.print_batch_step=1 Global.eval_batch_step=[1000,1000] Train.loader.shuffle=false
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Architecture.Backbone.checkpoints:
+norm_export:tools/export_model.py -c configs/vqa/ser/layoutxlm_xfund_zh.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:null
+infer_export:null
+infer_quant:False
+inference:ppstructure/vqa/predict_vqa_token_ser.py  --vqa_algorithm=LayoutXLM  --ser_dict_path=train_data/XFUND/class_list_xfun.txt --output=output
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--ser_model_dir:
+--image_dir:./ppstructure/docs/vqa/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,224,224]}]
+===========================train_benchmark_params==========================
+batch_size:4
+fp_items:fp32|fp16
+epoch:3
+--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

test_tipc/docs/benchmark_train.md

@@ -69,6 +69,7 @@ train_log/
 | det_r50_vd_east_v2.0	 |[config](../configs/det_r50_vd_east_v2.0/train_infer_python.txt) | 42.485 | 42.624 /	42.663 /	42.561 |0.00239083 | 67.61 |67.825/ 	68.299/ 	68.51| 0.00999854 | 10,000| 2,000|
 | det_r50_vd_pse_v2.0	 |[config](../configs/det_r50_vd_pse_v2.0/train_infer_python.txt) | 16.455 | 16.517 / 16.555 /	16.353 |0.012201752 | 27.02 |27.288 /	27.152 /	27.408| 0.009340339 | 10,000| 2,000|
 | rec_mv3_none_bilstm_ctc_v2.0	 |[config](../configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt) | 2288.358 | 2291.906 /	2293.725 /	2290.05 |0.001602197 | 2336.17 |2327.042 /	2328.093 /	2344.915| 0.007622025 | 600,000| 160,000|
+| layoutxlm	 |[config](../configs/layoutxlm/train_infer_python.txt) | 18.001 | 18.114 /	18.107 /	18.307 |0.010924783 | 21.982 | 21.507 /	21.116 /	21.406| 0.018180127 | 1490 | 1490|
 | PP-Structure-table	 |[config](../configs/en_table_structure/train_infer_python.txt) | 14.151 | 14.077 /	14.23 /	14.25 |0.012140351 | 16.285 | 16.595 /	16.878 /	16.531 | 0.020559308 | 20,000| 5,000|
 | det_r50_dcn_fce_ctw_v2.0	 |[config](../configs/det_r50_dcn_fce_ctw_v2.0/train_infer_python.txt) | 14.057 | 14.029 /	14.02 /	14.014 |0.001069214 | 18.298 |18.411 /	18.376 /	18.331| 0.004345228 | 10,000| 2,000|
 | ch_PP-OCRv3_det	 |[config](../configs/ch_PP-OCRv3_det/train_infer_python.txt) | 8.622 | 8.431 /	8.423 /	8.479|0.006604552 | 14.203 |14.346	14.468	14.23| 0.016450097 | 10,000| 2,000|

test_tipc/prepare.sh

@@ -106,6 +106,19 @@ if [ ${MODE} = "benchmark_train" ];then
         ln -s ./icdar2015_benckmark ./icdar2015
         cd ../
     fi
+    if [ ${model_name} == "layoutxlm" ]; then
+        pip install -r ppstructure/vqa/requirements.txt
+        pip install paddlenlp>=2.3.5
+        wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/ppstructure/dataset/XFUND.tar --no-check-certificate
+        cd ./train_data/ && tar xf XFUND.tar
+        # expand gt.txt 10 times
+        cd XFUND/zh_train
+        for i in `seq 10`;do cp train.json dup$i.txt;done
+        cat dup* > train.json && rm -rf dup*
+        cd ../../
+        
+        cd ../
+    fi
 fi
 
 if [ ${MODE} = "lite_train_lite_infer" ];then
@@ -207,6 +220,13 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
         wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/rec_r32_gaspin_bilstm_att_train.tar --no-check-certificate
         cd ./pretrain_models/ && tar xf rec_r32_gaspin_bilstm_att_train.tar && cd ../
     fi
+    if [ ${model_name} == "layoutxlm" ]; then
+        pip install -r ppstructure/vqa/requirements.txt
+        pip install paddlenlp>=2.3.5
+        wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/ppstructure/dataset/XFUND.tar --no-check-certificate
+        cd ./train_data/ && tar xf XFUND.tar
+        cd ../
+    fi
 
 elif [ ${MODE} = "whole_train_whole_infer" ];then
     wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams --no-check-certificate