update ocr_rec

configs/rec/rec_icdar15_train.yml

@@ -10,7 +10,7 @@ Global:
   cal_metric_during_train: True
   pretrained_model:
   checkpoints:
-  save_inference_dir:
+  save_inference_dir: ./
   use_visualdl: False
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
@@ -60,8 +60,8 @@ Metric:
 Train:
   dataset:
     name: SimpleDataSet
-    data_dir: ./train_data/
-    label_file_list: ["./train_data/train_list.txt"]
+    data_dir: ./train_data/ic15_data/
+    label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
     transforms:
       - DecodeImage: # load image
           img_mode: BGR
@@ -81,8 +81,8 @@ Train:
 Eval:
   dataset:
     name: SimpleDataSet
-    data_dir: ./train_data/
-    label_file_list: ["./train_data/val_list.txt"]
+    data_dir: ./train_data/ic15_data
+    label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
     transforms:
       - DecodeImage: # load image
           img_mode: BGR

test/ocr_det_params.txt

-model_name:ocr_det
-python:python3.7
-gpu_list:0|0,1
-Global.auto_cast:null
-Global.epoch_num:10
-Global.save_model_dir:./output/
-Train.loader.batch_size_per_card:
-Global.use_gpu:
-Global.pretrained_model:null
-
-trainer:norm|pact
-norm_train:tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
-quant_train:deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/det_mv3_db_v2.0_train/best_accuracy
-fpgm_train:null
-distill_train:null
-
-eval:tools/eval.py -c configs/det/det_mv3_db.yml -o 
-
-Global.save_inference_dir:./output/
-Global.pretrained_model:
-norm_export:tools/export_model.py -c configs/det/det_mv3_db.yml -o 
-quant_export:deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o 
-fpgm_export:deploy/slim/prune/export_prune_model.py
-distill_export:null
-
-inference:tools/infer/predict_det.py
---use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
---rec_batch_num:1
---use_tensorrt:True|False
---precision:fp32|fp16|int8
---det_model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/
---image_dir:./inference/ch_det_data_50/all-sum-510/
---save_log_path:./test/output/

test/prepare.sh

-#!/bin/bash
-FILENAME=$1
-# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
-MODE=$2
-
-dataline=$(cat ${FILENAME})
-
-# parser params
-IFS=$'\n'
-lines=(${dataline})
-function func_parser_key(){
-    strs=$1
-    IFS=":"
-    array=(${strs})
-    tmp=${array[0]}
-    echo ${tmp}
-}
-function func_parser_value(){
-    strs=$1
-    IFS=":"
-    array=(${strs})
-    tmp=${array[1]}
-    echo ${tmp}
-}
-IFS=$'\n'
-# The training params
-model_name=$(func_parser_value "${lines[0]}")
-train_model_list=$(func_parser_value "${lines[0]}")
-
-trainer_list=$(func_parser_value "${lines[10]}")
-
-# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer']
-MODE=$2
-# prepare pretrained weights and dataset
-if [ ${train_model_list[*]} = "ocr_det" ]; then
-  wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
-  wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar
-  cd pretrain_models && tar xf det_mv3_db_v2.0_train.tar && cd ../
-  fi
-if [ ${MODE} = "lite_train_infer" ];then
-    # pretrain lite train data
-    rm -rf ./train_data/icdar2015
-    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_lite.tar
-    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar # todo change to bcebos
-
-    cd ./train_data/ && tar xf icdar2015_lite.tar && tar xf ic15_data.tar
-    ln -s ./icdar2015_lite ./icdar2015
-    cd ../
-    epoch=10
-    eval_batch_step=10
-elif [ ${MODE} = "whole_train_infer" ];then
-    rm -rf ./train_data/icdar2015
-    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar
-    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
-    cd ./train_data/ && tar xf icdar2015.tar && tar xf ic15_data.tar && cd ../
-    epoch=500
-    eval_batch_step=200
-elif [ ${MODE} = "whole_infer" ];then
-    rm -rf ./train_data/icdar2015
-    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_infer.tar
-    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
-    cd ./train_data/ && tar xf icdar2015_infer.tar && tar xf ic15_data.tar
-    ln -s ./icdar2015_infer ./icdar2015
-    cd ../
-    epoch=10
-    eval_batch_step=10
-else
-    rm -rf ./train_data/icdar2015
-    wget -nc -P ./train_data https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
-    if [ ${model_name} = "ocr_det" ]; then
-        eval_model_name="ch_ppocr_mobile_v2.0_det_infer"
-        wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
-        cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-    else 
-        eval_model_name="ch_ppocr_mobile_v2.0_rec_train"
-        wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar
-        cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-    fi 
-fi
-
-
-IFS='|'
-for train_model in ${train_model_list[*]}; do 
-    if [ ${train_model} = "ocr_det" ];then
-        model_name="ocr_det"
-        yml_file="configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml"
-        wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
-        cd ./inference && tar xf ch_det_data_50.tar && cd ../
-        img_dir="./inference/ch_det_data_50/all-sum-510"
-        data_dir=./inference/ch_det_data_50/
-        data_label_file=[./inference/ch_det_data_50/test_gt_50.txt]
-    elif [ ${train_model} = "ocr_rec" ];then
-        model_name="ocr_rec"
-        yml_file="configs/rec/rec_mv3_none_bilstm_ctc.yml"
-        wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar
-        cd ./inference && tar xf rec_inference.tar  && cd ../
-        img_dir="./inference/rec_inference/"
-        data_dir=./inference/rec_inference
-        data_label_file=[./inference/rec_inference/rec_gt_test.txt]
-    fi
-
-    # eval 
-    for slim_trainer in ${trainer_list[*]}; do 
-        if [ ${slim_trainer} = "norm" ]; then
-            if [ ${model_name} = "det" ]; then
-                eval_model_name="ch_ppocr_mobile_v2.0_det_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            else 
-                eval_model_name="ch_ppocr_mobile_v2.0_rec_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            fi 
-        elif [ ${slim_trainer} = "pact" ]; then
-            if [ ${model_name} = "det" ]; then
-                eval_model_name="ch_ppocr_mobile_v2.0_det_quant_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_quant_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            else
-                eval_model_name="ch_ppocr_mobile_v2.0_rec_quant_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_quant_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            fi
-        elif [ ${slim_trainer} = "distill" ]; then
-            if [ ${model_name} = "det" ]; then
-                eval_model_name="ch_ppocr_mobile_v2.0_det_distill_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_distill_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            else
-                eval_model_name="ch_ppocr_mobile_v2.0_rec_distill_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_distill_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            fi 
-        elif [ ${slim_trainer} = "fpgm" ]; then
-            if [ ${model_name} = "det" ]; then
-                eval_model_name="ch_ppocr_mobile_v2.0_det_prune_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            else
-                eval_model_name="ch_ppocr_mobile_v2.0_rec_prune_train"
-                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_prune_train.tar
-                cd ./inference && tar xf ${eval_model_name}.tar && cd ../
-            fi
-        fi
-    done
-done

test/test.sh

-#!/bin/bash
-FILENAME=$1
-# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
-MODE=$2
-
-dataline=$(cat ${FILENAME})
-
-# parser params
-IFS=$'\n'
-lines=(${dataline})
-function func_parser_key(){
-    strs=$1
-    IFS=":"
-    array=(${strs})
-    tmp=${array[0]}
-    echo ${tmp}
-}
-function func_parser_value(){
-    strs=$1
-    IFS=":"
-    array=(${strs})
-    tmp=${array[1]}
-    echo ${tmp}
-}
-function status_check(){
-    last_status=$1   # the exit code
-    run_command=$2
-    run_log=$3
-    if [ $last_status -eq 0 ]; then
-        echo -e "\033[33m Run successfully with command - ${run_command}!  \033[0m" | tee -a ${run_log}
-    else
-        echo -e "\033[33m Run failed with command - ${run_command}!  \033[0m" | tee -a ${run_log}
-    fi
-}
-
-IFS=$'\n'
-# The training params
-model_name=$(func_parser_value "${lines[0]}")
-python=$(func_parser_value "${lines[1]}")
-gpu_list=$(func_parser_value "${lines[2]}")
-autocast_list=$(func_parser_value "${lines[3]}")
-autocast_key=$(func_parser_key "${lines[3]}")
-epoch_key=$(func_parser_key "${lines[4]}")
-epoch_num=$(func_parser_value "${lines[4]}")
-save_model_key=$(func_parser_key "${lines[5]}")
-train_batch_key=$(func_parser_key "${lines[6]}")
-train_use_gpu_key=$(func_parser_key "${lines[7]}")
-pretrain_model_key=$(func_parser_key "${lines[8]}")
-pretrain_model_value=$(func_parser_value "${lines[8]}")
-
-trainer_list=$(func_parser_value "${lines[9]}")
-norm_trainer=$(func_parser_value "${lines[10]}")
-pact_trainer=$(func_parser_value "${lines[11]}")
-fpgm_trainer=$(func_parser_value "${lines[12]}")
-distill_trainer=$(func_parser_value "${lines[13]}")
-
-eval_py=$(func_parser_value "${lines[14]}")
-
-save_infer_key=$(func_parser_key "${lines[15]}")
-export_weight=$(func_parser_key "${lines[16]}")
-norm_export=$(func_parser_value "${lines[17]}")
-pact_export=$(func_parser_value "${lines[18]}")
-fpgm_export=$(func_parser_value "${lines[19]}")
-distill_export=$(func_parser_value "${lines[20]}")
-
-inference_py=$(func_parser_value "${lines[21]}")
-use_gpu_key=$(func_parser_key "${lines[22]}")
-use_gpu_list=$(func_parser_value "${lines[22]}")
-use_mkldnn_key=$(func_parser_key "${lines[23]}")
-use_mkldnn_list=$(func_parser_value "${lines[23]}")
-cpu_threads_key=$(func_parser_key "${lines[24]}")
-cpu_threads_list=$(func_parser_value "${lines[24]}")
-batch_size_key=$(func_parser_key "${lines[25]}")
-batch_size_list=$(func_parser_value "${lines[25]}")
-use_trt_key=$(func_parser_key "${lines[26]}")
-use_trt_list=$(func_parser_value "${lines[26]}")
-precision_key=$(func_parser_key "${lines[27]}")
-precision_list=$(func_parser_value "${lines[27]}")
-infer_model_key=$(func_parser_key "${lines[28]}")
-infer_model=$(func_parser_value "${lines[28]}")
-image_dir_key=$(func_parser_key "${lines[29]}")
-infer_img_dir=$(func_parser_value "${lines[29]}")
-save_log_key=$(func_parser_key "${lines[30]}")
-
-LOG_PATH="./test/output"
-mkdir -p ${LOG_PATH}
-status_log="${LOG_PATH}/results.log"
-
-
-function func_inference(){
-    IFS='|'
-    _python=$1
-    _script=$2
-    _model_dir=$3
-    _log_path=$4
-    _img_dir=$5
-    
-    # inference 
-    for use_gpu in ${use_gpu_list[*]}; do 
-        if [ ${use_gpu} = "False" ]; then
-            for use_mkldnn in ${use_mkldnn_list[*]}; do
-                for threads in ${cpu_threads_list[*]}; do
-                    for batch_size in ${batch_size_list[*]}; do
-                        _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log"
-                        command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${cpu_threads_key}=${threads} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir}  ${save_log_key}=${_save_log_path} --benchmark=True"
-                        eval $command
-                        status_check $? "${command}" "${status_log}"
-                    done
-                done
-            done
-        else
-            for use_trt in ${use_trt_list[*]}; do
-                for precision in ${precision_list[*]}; do
-                    if [ ${use_trt} = "False" ] && [ ${precision} != "fp32" ]; then
-                        continue
-                    fi
-                    for batch_size in ${batch_size_list[*]}; do
-                        _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
-                        command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_trt_key}=${use_trt} ${precision_key}=${precision} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir}  ${save_log_key}=${_save_log_path}  --benchmark=True"
-                        eval $command
-                        status_check $? "${command}" "${status_log}"
-                    done
-                done
-            done
-        fi
-    done
-}
-
-if [ ${MODE} != "infer" ]; then
-
-IFS="|"
-for gpu in ${gpu_list[*]}; do
-    use_gpu=True
-    if [ ${gpu} = "-1" ];then
-        use_gpu=False
-        env=""
-    elif [ ${#gpu} -le 1 ];then
-        env="export CUDA_VISIBLE_DEVICES=${gpu}"
-        eval ${env}
-    elif [ ${#gpu} -le 15 ];then
-        IFS=","
-        array=(${gpu})
-        env="export CUDA_VISIBLE_DEVICES=${array[0]}"
-        IFS="|"
-    else
-        IFS=";"
-        array=(${gpu})
-        ips=${array[0]}
-        gpu=${array[1]}
-        IFS="|"
-        env=" "
-    fi
-    for autocast in ${autocast_list[*]}; do 
-        for trainer in ${trainer_list[*]}; do 
-            if [ ${trainer} = "pact" ]; then
-                run_train=${pact_trainer}
-                run_export=${pact_export}
-            elif [ ${trainer} = "fpgm" ]; then
-                run_train=${fpgm_trainer}
-                run_export=${fpgm_export}
-            elif [ ${trainer} = "distill" ]; then
-                run_train=${distill_trainer}
-                run_export=${distill_export}
-            else
-                run_train=${norm_trainer}
-                run_export=${norm_export}
-            fi
-
-            if [ ${run_train} = "null" ]; then
-                continue
-            fi
-            if [ ${run_export} = "null" ]; then
-                continue
-            fi
-
-            # not set autocast when autocast is null
-            if [ ${autocast} = "null" ]; then
-                set_autocast=" "
-            else
-                set_autocast="${autocast_key}=${autocast}"
-            fi
-            # not set epoch when whole_train_infer
-            if [ ${MODE} != "whole_train_infer" ]; then
-                set_epoch="${epoch_key}=${epoch_num}"
-            else
-                set_epoch=" "
-            fi
-            # set pretrain
-            if [ ${pretrain_model_value} != "null" ]; then
-                set_pretrain="${pretrain_model_key}=${pretrain_model_value}"
-            else
-                set_pretrain=" "
-            fi
-
-            save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
-            if [ ${#gpu} -le 2 ];then  # train with cpu or single gpu
-                cmd="${python} ${run_train} ${train_use_gpu_key}=${use_gpu}  ${save_model_key}=${save_log} ${set_epoch} ${set_pretrain} ${set_autocast}"
-            elif [ ${#gpu} -le 15 ];then  # train with multi-gpu
-                cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${save_model_key}=${save_log}  ${set_epoch} ${set_pretrain} ${set_autocast}"
-            else     # train with multi-machine
-                cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${save_model_key}=${save_log} ${set_pretrain} ${set_epoch} ${set_autocast}"
-            fi
-            # run train
-            eval $cmd
-            status_check $? "${cmd}" "${status_log}"
-
-            # run eval
-            eval_cmd="${python} ${eval_py} ${save_model_key}=${save_log} ${pretrain_model_key}=${save_log}/latest" 
-            eval $eval_cmd
-            status_check $? "${eval_cmd}" "${status_log}"
-
-            # run export model
-            save_infer_path="${save_log}"
-            export_cmd="${python} ${run_export} ${save_model_key}=${save_log} ${export_weight}=${save_log}/latest ${save_infer_key}=${save_infer_path}"
-            eval $export_cmd
-            status_check $? "${export_cmd}" "${status_log}"
-
-            #run inference
-            eval $env
-            save_infer_path="${save_log}"
-            func_inference "${python}" "${inference_py}" "${save_infer_path}" "${LOG_PATH}" "${infer_img_dir}"
-            eval "unset CUDA_VISIBLE_DEVICES"
-        done
-    done
-done
-
-else
-    GPUID=$3
-    if [ ${#GPUID} -le 0 ];then
-        env=" "
-    else
-        env="export CUDA_VISIBLE_DEVICES=${GPUID}"
-    fi
-    echo $env
-    #run inference
-    func_inference "${python}" "${inference_py}" "${infer_model}" "${LOG_PATH}" "${infer_img_dir}"
-fi

tests/ocr_det_params.txt

@@ -49,3 +49,4 @@ inference:tools/infer/predict_det.py
 --save_log_path:null
 --benchmark:True
 null:null
+

test/ocr_rec_params.txt → tests/ocr_rec_params.txt

+===========================train_params===========================
 model_name:ocr_rec
-python:python
-gpu_list:0|0,1
+python:python3.7
+gpu_list:0|2,3
+Global.use_gpu:True|True
 Global.auto_cast:null
-Global.epoch_num:10
+Global.epoch_num:lite_train_infer=2|whole_train_infer=300
 Global.save_model_dir:./output/
-Train.loader.batch_size_per_card:
-Global.use_gpu:
+Train.loader.batch_size_per_card:lite_train_infer=128|whole_train_infer=128
 Global.pretrained_model:null
-
-trainer:norm|pact
-norm_train:tools/train.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
-quant_train:deploy/slim/quantization/quant.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
+train_model_name:latest
+train_infer_img_dir:./train_data/ic15_data/train
+null:null
+##
+trainer:norm_train|pact_train
+norm_train:tools/train.py -c configs/rec/rec_icdar15_train.yml -o
+pact_train:deploy/slim/quantization/quant.py -c configs/rec/rec_icdar15_train.yml -o
 fpgm_train:null
 distill_train:null
-
-eval:tools/eval.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
-
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c configs/rec/rec_icdar15_train.yml -o
+null:null
+##
+===========================infer_params===========================
 Global.save_inference_dir:./output/
 Global.pretrained_model:
-norm_export:tools/export_model.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
-quant_export:deploy/slim/quantization/export_model.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
+norm_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
+quant_export:deploy/slim/quantization/export_model.py -c configs/rec/rec_icdar15_train.yml -o
 fpgm_export:null
 distill_export:null
-
+export1:null
+export2:null
+##
+infer_model:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+infer_export:null
+infer_quant:False
 inference:tools/infer/predict_rec.py
 --use_gpu:True|False
 --enable_mkldnn:True|False
@@ -30,6 +44,8 @@ inference:tools/infer/predict_rec.py
 --rec_batch_num:1
 --use_tensorrt:True|False
 --precision:fp32|fp16|int8
---rec_model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--rec_model_dir:
 --image_dir:./inference/rec_inference
---save_log_path:./test/output/
+--save_log_path:./test/output/
\ No newline at end of file
+--benchmark:True
+null:null

tests/prepare.sh

@@ -35,32 +35,42 @@ if [ ${MODE} = "lite_train_infer" ];then
     # pretrain lite train data
     wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
     rm -rf ./train_data/icdar2015
+    rm -rf ./train_data/ic15_data
     wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_lite.tar
-    cd ./train_data/ && tar xf icdar2015_lite.tar
+    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar # todo change to bcebos
+
+    cd ./train_data/ && tar xf icdar2015_lite.tar && tar xf ic15_data.tar
     ln -s ./icdar2015_lite ./icdar2015
     cd ../
 elif [ ${MODE} = "whole_train_infer" ];then
     wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
     rm -rf ./train_data/icdar2015
+    rm -rf ./train_data/ic15_data
     wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar
-    cd ./train_data/ && tar xf icdar2015.tar && cd ../
+    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
+    cd ./train_data/ && tar xf icdar2015.tar && tar xf ic15_data.tar && cd ../
 elif [ ${MODE} = "whole_infer" ];then
     wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
     rm -rf ./train_data/icdar2015
+    rm -rf ./train_data/ic15_data
     wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_infer.tar
-    cd ./train_data/ && tar xf icdar2015_infer.tar
+    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
+    cd ./train_data/ && tar xf icdar2015_infer.tar && tar xf ic15_data.tar
     ln -s ./icdar2015_infer ./icdar2015
     cd ../
 else
-    rm -rf ./train_data/icdar2015
-    if [[ ${model_name} = "ocr_det" ]]; then
-        wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
+    if [ ${model_name} = "ocr_det" ]; then
         eval_model_name="ch_ppocr_mobile_v2.0_det_infer"
+        rm -rf ./train_data/icdar2015
+        wget -nc -P ./train_data https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
         cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_det_data_50.tar && cd ../
     else 
+        rm -rf ./train_data/ic15_data
         eval_model_name="ch_ppocr_mobile_v2.0_rec_train"
+        wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar
-        cd ./inference && tar xf ${eval_model_name}.tar && cd ../
+        cd ./inference && tar xf ${eval_model_name}.tar && tar xf ic15_data.tar && cd ../
     fi 
 fi
+