Merge pull request #6582 from andyjpaddle/table

[TIPC] add table to tipc

test_tipc/configs/det_r50_vd_sast_icdar15_v2.0/train_infer_python.txt

@@ -4,7 +4,7 @@ python:python3.7
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=5000
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
 Global.save_model_dir:./output/
 Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
 Global.pretrained_model:null
@@ -45,7 +45,7 @@ inference:tools/infer/predict_det.py
 --use_tensorrt:False
 --precision:fp32
 --det_model_dir:
---image_dir:./inference/ch_det_data_50/all-sum-510/
+--image_dir:./inference/ch_det_data_50/all-sum-510/00008790.jpg
 null:null
 --benchmark:True
 --det_algorithm:SAST

test_tipc/configs/en_table_structure/table_mv3.yml

+Global:
+  use_gpu: true
+  epoch_num: 10
+  log_smooth_window: 20
+  print_batch_step: 5
+  save_model_dir: ./output/table_mv3/
+  save_epoch_step: 3
+  # evaluation is run every 400 iterations after the 0th iteration
+  eval_batch_step: [0, 400]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/table/table.jpg
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/table_structure_dict.txt
+  character_type: en
+  max_text_length: 100
+  max_elem_length: 800
+  max_cell_num: 500
+  infer_mode: False
+  process_total_num: 0
+  process_cut_num: 0
+
+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: TableAttn
+  Backbone:
+    name: MobileNetV3
+    scale: 1.0
+    model_name: large
+  Head:
+    name: TableAttentionHead
+    hidden_size: 256
+    l2_decay: 0.00001
+    loc_type: 2
+    max_text_length: 100
+    max_elem_length: 800
+    max_cell_num: 500
+
+Loss:
+  name: TableAttentionLoss
+  structure_weight: 100.0
+  loc_weight: 10000.0
+
+PostProcess:
+  name: TableLabelDecode
+
+Metric:
+  name: TableMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: PubTabDataSet
+    data_dir: ./train_data/pubtabnet/train
+    label_file_path: ./train_data/pubtabnet/train.jsonl
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ResizeTableImage:
+          max_len: 488
+      - TableLabelEncode:
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - PaddingTableImage:
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
+  loader:
+    shuffle: True
+    batch_size_per_card: 32
+    drop_last: True
+    num_workers: 1
+
+Eval:
+  dataset:
+    name: PubTabDataSet
+    data_dir: ./train_data/pubtabnet/test/
+    label_file_path: ./train_data/pubtabnet/test.jsonl
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ResizeTableImage:
+          max_len: 488
+      - TableLabelEncode:
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - PaddingTableImage:
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 1

test_tipc/configs/en_table_structure/train_infer_python.txt

+===========================train_params===========================
+model_name:en_table_structure
+python:python3.7
+gpu_list:0|0,1
+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:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+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/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:False
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer  --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]

test_tipc/configs/en_table_structure/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:en_table_structure
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+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:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+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/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:False
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer  --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]

test_tipc/configs/en_table_structure_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:en_table_structure_KL
+python:python3.7
+Global.pretrained_model:
+Global.save_inference_dir:null
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer/
+infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+infer_quant:True
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer  --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:int8
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+null:null

test_tipc/configs/en_table_structure_PACT/train_infer_python.txt

+===========================train_params===========================
+model_name:en_table_structure_PACT
+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=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:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:pact_train
+norm_train:null 
+pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:null 
+quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:True
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer  --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]

test_tipc/configs/en_table_structure_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:en_table_structure_PACT
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+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=16|whole_train_whole_infer=128
+Global.pretrained_model:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:pact_train
+norm_train:null 
+pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:null 
+quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o 
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:True
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer  --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]

test_tipc/prepare.sh

@@ -55,6 +55,9 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
     if [ ${model_name} == "en_table_structure" ];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 ../
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
     fi
     cd ./pretrain_models/ && tar xf det_mv3_db_v2.0_train.tar && cd ../
     rm -rf ./train_data/icdar2015
@@ -147,9 +150,12 @@ elif [ ${MODE} = "whole_train_whole_infer" ];then
         wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/total_text_lite.tar  --no-check-certificate
         cd ./train_data && tar xf total_text.tar && ln -s total_text_lite total_text  && cd ../
     fi
-    if [ ${model_name} == "en_table_structure" ];then
+    if [[ ${model_name} =~ "en_table_structure" ]];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 ../
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
     fi
 elif [ ${MODE} = "lite_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
@@ -172,9 +178,12 @@ elif [ ${MODE} = "lite_train_whole_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} == "en_table_structure" ];then
+    if [[ ${model_name} =~ "en_table_structure" ]];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 ../
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
     fi
 elif [ ${MODE} = "whole_infer" ];then
     wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
@@ -335,9 +344,11 @@ elif [ ${MODE} = "whole_infer" ];then
         wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar --no-check-certificate
         cd ./inference/ && tar xf det_r50_vd_east_v2.0_train.tar & cd ../
     fi
-    if [ ${model_name} == "en_table_structure" ];then
+    if [[ ${model_name} =~ "en_table_structure" ]];then
         wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
-        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar  && cd ../
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
     fi
 fi
 
@@ -383,6 +394,14 @@ if [ ${MODE} = "klquant_whole_infer" ]; then
         cd ./train_data/ && tar xf ic15_data.tar && cd ../
         cd ./inference && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf rec_inference.tar &&  cd ../ 
     fi
+    if [ ${model_name} = "en_table_structure_KL" ];then
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+        wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/pubtabnet.tar --no-check-certificate
+        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
+        cd ./train_data/ && tar xf pubtabnet.tar && cd ../
+    fi
 fi
 
 if [ ${MODE} = "cpp_infer" ];then