add vi-layoutxlm (#7209)

ppstructure/vqa/predict_vqa_token_ser.py

@@ -41,7 +41,11 @@ logger = get_logger()
 class SerPredictor(object):
     def __init__(self, args):
         self.ocr_engine = PaddleOCR(
-            use_angle_cls=False, show_log=False, use_gpu=args.use_gpu)
+            use_angle_cls=args.use_angle_cls,
+            det_model_dir=args.det_model_dir,
+            rec_model_dir=args.rec_model_dir,
+            show_log=False,
+            use_gpu=args.use_gpu)
 
         pre_process_list = [{
             'VQATokenLabelEncode': {

test_tipc/configs/vi_layoutxlm_ser/train_infer_python.txt

@@ -0,0 +1,59 @@
+===========================train_params===========================
+model_name:vi_layoutxlm_ser
+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=4|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/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
+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/kie/vi_layoutxlm/ser_vi_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 --ocr_order_method=tb-yx
+--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/prepare.sh

@@ -106,7 +106,7 @@ if [ ${MODE} = "benchmark_train" ];then
         ln -s ./icdar2015_benckmark ./icdar2015
         cd ../
     fi
-    if [ ${model_name} == "layoutxlm_ser" ]; then
+    if [ ${model_name} == "layoutxlm_ser" ] || [ ${model_name} == "vi_layoutxlm_ser" ]; then
         pip install -r ppstructure/vqa/requirements.txt
         pip install paddlenlp\>=2.3.5 --force-reinstall -i https://mirrors.aliyun.com/pypi/simple/
         wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/ppstructure/dataset/XFUND.tar --no-check-certificate
@@ -220,7 +220,7 @@ 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_ser" ]; then
+    if [ ${model_name} == "layoutxlm_ser" ] || [ ${model_name} == "vi_layoutxlm_ser" ]; then
         pip install -r ppstructure/vqa/requirements.txt
         pip install paddlenlp\>=2.3.5 --force-reinstall -i https://mirrors.aliyun.com/pypi/simple/
         wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/ppstructure/dataset/XFUND.tar --no-check-certificate