Merge pull request #7447 from WenmuZhou/tipc

[TIPC] fix layoutxlm_ser ch_ppocr_mobile_v2_0_det_FPGM ch_ppocr_mobile_v2_0_rec_FPGM error

test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml

+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, 187 ]
+  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

test_tipc/configs/layoutxlm_ser/train_infer_python.txt

@@ -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/layoutlm_series/ser_layoutlm_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 test_tipc/configs/layoutxlm_ser/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
@@ -27,7 +27,7 @@ null:null
 ===========================infer_params===========================
 Global.save_inference_dir:./output/
 Architecture.Backbone.checkpoints:
-norm_export:tools/export_model.py -c configs/kie/layoutlm_series/ser_layoutlm_xfund_zh.yml -o 
+norm_export:tools/export_model.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o 
 quant_export:
 fpgm_export: 
 distill_export:null

test_tipc/configs/table_master/train_infer_python.txt

@@ -37,8 +37,8 @@ export2:null
 infer_model:null
 infer_export:null
 infer_quant:False
-inference:ppstructure/table/predict_structure.py  --table_char_dict_path=./ppocr/utils/dict/table_master_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --output ./output/table --table_algorithm=TableMaster --table_max_len=480 
---use_gpu:True|False
+inference:ppstructure/table/predict_structure.py  --table_char_dict_path=./ppocr/utils/dict/table_master_structure_dict.txt --output ./output/table --table_algorithm=TableMaster --table_max_len=480 
+--use_gpu:True
 --enable_mkldnn:False
 --cpu_threads:6
 --rec_batch_num:1

test_tipc/prepare.sh

@@ -21,7 +21,11 @@ model_name=$(func_parser_value "${lines[1]}")
 trainer_list=$(func_parser_value "${lines[14]}")
 
 if [ ${MODE} = "benchmark_train" ];then
-    pip install -r requirements.txt
+    python_name_list=$(func_parser_value "${lines[2]}")
+    array=(${python_name_list}) 
+    python_name=${array[0]}
+    ${python_name} -m pip install -r requirements.txt
+    ${python_name} -m pip install git+https://github.com/LDOUBLEV/AutoLog
     if [[ ${model_name} =~ "ch_ppocr_mobile_v2_0_det" || ${model_name} =~ "det_mv3_db_v2_0" ]];then
         wget -nc -P  ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/MobileNetV3_large_x0_5_pretrained.pdparams  --no-check-certificate
         rm -rf ./train_data/icdar2015
@@ -107,8 +111,8 @@ if [ ${MODE} = "benchmark_train" ];then
         cd ../
     fi
     if [ ${model_name} == "layoutxlm_ser" ] || [ ${model_name} == "vi_layoutxlm_ser" ]; then
-        pip install -r ppstructure/kie/requirements.txt
-        pip install opencv-python -U
+        ${python_name} -m pip install -r ppstructure/kie/requirements.txt
+        ${python_name} -m pip install opencv-python -U
         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
@@ -122,6 +126,11 @@ if [ ${MODE} = "benchmark_train" ];then
 fi
 
 if [ ${MODE} = "lite_train_lite_infer" ];then
+    python_name_list=$(func_parser_value "${lines[2]}")
+    array=(${python_name_list}) 
+    python_name=${array[0]}
+    ${python_name} -m pip install -r requirements.txt
+    ${python_name} -m pip install git+https://github.com/LDOUBLEV/AutoLog
     # pretrain lite train data
     wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams  --no-check-certificate
     wget -nc -P ./pretrain_models/  https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar  --no-check-certificate
@@ -212,6 +221,10 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
     if [ ${model_name} == "ch_ppocr_mobile_v2_0_rec_FPGM" ]; then
         wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar --no-check-certificate
         cd ./pretrain_models/ && tar xf ch_ppocr_mobile_v2.0_rec_train.tar && cd ../
+        ${python_name} -m pip install paddleslim
+    fi
+    if [ ${model_name} == "ch_ppocr_mobile_v2_0_det_FPGM" ]; then
+        ${python_name} -m pip install paddleslim
     fi
     if [ ${model_name} == "det_mv3_east_v2_0" ]; then
         wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar --no-check-certificate
@@ -230,8 +243,8 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
         cd ./pretrain_models/ && tar xf rec_r32_gaspin_bilstm_att_train.tar && cd ../
     fi
     if [ ${model_name} == "layoutxlm_ser" ] || [ ${model_name} == "vi_layoutxlm_ser" ]; then
-        pip install -r ppstructure/kie/requirements.txt
-        pip install opencv-python -U
+        ${python_name} -m pip install -r ppstructure/kie/requirements.txt
+        ${python_name} -m pip install opencv-python -U
         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 ../
@@ -639,6 +652,7 @@ if [ ${MODE} = "serving_infer" ];then
     ${python_name} -m pip install paddle-serving-server-gpu
     ${python_name} -m pip install paddle_serving_client
     ${python_name} -m pip install paddle-serving-app
+    ${python_name} -m pip install git+https://github.com/LDOUBLEV/AutoLog
     # wget model
     if [ ${model_name} == "ch_ppocr_mobile_v2_0_det_KL" ] || [ ${model_name} == "ch_ppocr_mobile_v2.0_rec_KL" ] ; then
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_det_klquant_infer.tar --no-check-certificate