fix ci error

test/infer.sh

 #!/bin/bash
-
+FILENAME=$1
 dataline=$(cat ${FILENAME})
 # parser params
 IFS=$'\n'
 lines=(${dataline})
 function func_parser(){
     strs=$1
-    IFS=":"
+    IFS=": "
     array=(${strs})
     tmp=${array[1]}
     echo ${tmp}
@@ -17,7 +17,7 @@ train_model_list=$(func_parser "${lines[0]}")
 slim_trainer_list=$(func_parser "${lines[3]}")
 python=$(func_parser "${lines[4]}")
 # inference params
-inference=$(func_parser "${lines[5]}")
+# inference=$(func_parser "${lines[5]}")
 devices=$(func_parser "${lines[6]}")
 use_mkldnn_list=$(func_parser "${lines[7]}")
 cpu_threads_list=$(func_parser "${lines[8]}")
@@ -40,14 +40,15 @@ function status_check(){
         echo -e "\033[33m $case failed with command - ${run_command}!  \033[0m" | tee -a ${save_log}
     fi
 }
-
+IFS='|'
 for train_model in ${train_model_list[*]}; do 
-    if [ ${train_model} = "det" ];then
+    if [ ${train_model} = "ocr_det" ];then
         model_name="det"
         yml_file="configs/det/det_mv3_db.yml"
-        wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar && tar xf ./inference/ch_det_data_50.tar 
+        # wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar 
+        tar xf ./inference/ch_det_data_50.tar 
         img_dir="./inference/ch_det_data_50/"
-    elif [ ${train_model} = "rec" ];then
+    elif [ ${train_model} = "ocr_rec" ];then
         model_name="rec"
         yml_file="configs/rec/rec_mv3_none_bilstm_ctc.yml"
         wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_rec_data_200.tar && tar xf ./inference/ch_rec_data_200.tar 
@@ -71,7 +72,7 @@ for train_model in ${train_model_list[*]}; do
             else
                 eval_model_name="ch_ppocr_mobile_v2.0_rec_quant_infer"
                 wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_quant_train.tar
-            fi 
+            fi
         elif [ ${slim_trainer} = "distill" ]; then
             if [ ${model_name} = "det" ]; then
                 eval_model_name="ch_ppocr_mobile_v2.0_det_distill_infer"
@@ -89,59 +90,61 @@ for train_model in ${train_model_list[*]}; do
                 wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_prune_train.tar
             fi
         fi
-    save_log_path="${log_path}/${eval_model_name}"
-    command="${python} tools/eval.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_model_dir=${save_log_path}"
-    ${python} tools/eval.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_model_dir=${save_log_path}
-    status_check $? "${trainer}" "${command}" "${save_log_path}/train.log"
 
-    command="${python} tools/export_model.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_inference_dir=${log_path}/${eval_model_name}_infer Global.save_model_dir=${save_log_path}"
-    ${python} tools/export_model.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_inference_dir=${log_path}/${eval_model_name}_infer Global.save_model_dir=${save_log_path}
-    status_check $? "${trainer}" "${command}" "${save_log_path}/train.log"
+        save_log_path="${log_path}/${eval_model_name}"
+        command="${python} tools/eval.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_model_dir=${save_log_path}"
+        ${python} tools/eval.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_model_dir=${save_log_path}
+        status_check $? "${trainer}" "${command}" "${save_log_path}/train.log"
 
-    if [ $? -eq 0 ]; then
-        echo -e "\033[33m training of $model_name successfully!\033[0m" | tee -a ${save_log}/train.log
-    else
-        cat ${save_log}/train.log
-        echo -e "\033[33m training of $model_name failed!\033[0m" | tee -a ${save_log}/train.log
-    fi
-    if [ "${model_name}" = "det" ]; then 
-        export rec_batch_size_list=( "1" )
-        inference="tools/infer/predict_det.py"
-        det_model_dir=${log_path}/${eval_model_name}_infer
-        rec_model_dir=""
-    elif [ "${model_name}" = "rec" ]; then
-        inference="tools/infer/predict_rec.py"
-        rec_model_dir=${log_path}/${eval_model_name}_infer
-        det_model_dir=""
-    fi
-    # inference 
-    for device in ${devices[*]}; do 
-        if [ ${device} = "cpu" ]; then
-            for use_mkldnn in ${use_mkldnn_list[*]}; do
-                for threads in ${cpu_threads_list[*]}; do
-                    for rec_batch_size in ${rec_batch_size_list[*]}; do    
-                        save_log_path="${log_path}/${model_name}_${slim_trainer}_cpu_usemkldnn_${use_mkldnn}_cputhreads_${threads}_recbatchnum_${rec_batch_size}_infer.log"
-                        command="${python} ${inference} --enable_mkldnn=${use_mkldnn} --use_gpu=False --cpu_threads=${threads} --benchmark=True --det_model_dir=${det_model_dir} --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir}  --image_dir=${img_dir}  --save_log_path=${save_log_path}"
-                        ${python} ${inference} --enable_mkldnn=${use_mkldnn} --use_gpu=False --cpu_threads=${threads} --benchmark=True --det_model_dir=${det_model_dir} --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir}  --image_dir=${img_dir}  --save_log_path=${save_log_path}
-                        status_check $? "${trainer}" "${command}" "${save_log_path}"
+        command="${python} tools/export_model.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_inference_dir=${log_path}/${eval_model_name}_infer Global.save_model_dir=${save_log_path}"
+        ${python} tools/export_model.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_inference_dir="${log_path}/${eval_model_name}_infer" Global.save_model_dir=${save_log_path}
+        status_check $? "${trainer}" "${command}" "${save_log_path}/train.log"
+
+        if [ $? -eq 0 ]; then
+            echo -e "\033[33m training of $model_name successfully!\033[0m" | tee -a ${save_log}/train.log
+        else
+            cat ${save_log}/train.log
+            echo -e "\033[33m training of $model_name failed!\033[0m" | tee -a ${save_log}/train.log
+        fi
+        if [ "${model_name}" = "det" ]; then 
+            export rec_batch_size_list=( "1" )
+            inference="tools/infer/predict_det.py"
+            det_model_dir=${log_path}/${eval_model_name}_infer
+            rec_model_dir=""
+        elif [ "${model_name}" = "rec" ]; then
+            inference="tools/infer/predict_rec.py"
+            rec_model_dir=${log_path}/${eval_model_name}_infer
+            det_model_dir=""
+        fi
+        # inference 
+        for device in ${devices[*]}; do 
+            if [ ${device} = "cpu" ]; then
+                for use_mkldnn in ${use_mkldnn_list[*]}; do
+                    for threads in ${cpu_threads_list[*]}; do
+                        for rec_batch_size in ${rec_batch_size_list[*]}; do    
+                            save_log_path="${log_path}/${model_name}_${slim_trainer}_cpu_usemkldnn_${use_mkldnn}_cputhreads_${threads}_recbatchnum_${rec_batch_size}_infer.log"
+                            command="${python} ${inference} --enable_mkldnn=${use_mkldnn} --use_gpu=False --cpu_threads=${threads} --benchmark=True --det_model_dir=${det_model_dir} --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir}  --image_dir=${img_dir}  --save_log_path=${save_log_path}"
+                            ${python} ${inference} --enable_mkldnn=${use_mkldnn} --use_gpu=False --cpu_threads=${threads} --benchmark=True --det_model_dir=${det_model_dir} --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir}  --image_dir=${img_dir}  --save_log_path=${save_log_path}
+                            status_check $? "${trainer}" "${command}" "${save_log_path}"
+                        done
                     done
                 done
-            done
-        else 
-            env="CUDA_VISIBLE_DEVICES=${infer_gpu_id}"
-            for use_trt in ${gpu_trt_list[*]}; do
-                for precision in ${gpu_precision_list[*]}; do
-                    if [ ${use_trt} = "False" ] && [ ${precision} != "fp32" ]; then
-                        continue
-                    fi
-                    for rec_batch_size in ${rec_batch_size_list[*]}; do
-                        save_log_path="${log_path}/${model_name}_${slim_trainer}_gpu_usetensorrt_${use_trt}_usefp16_${precision}_recbatchnum_${rec_batch_size}_infer.log"
-                        command="${env} ${python} ${inference} --use_gpu=True --use_tensorrt=${use_trt}  --precision=${precision} --benchmark=True --det_model_dir=${log_path}/${eval_model_name}_infer --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir} --image_dir=${img_dir} --save_log_path=${save_log_path}"
-                        ${env} ${python} ${inference} --use_gpu=True --use_tensorrt=${use_trt}  --precision=${precision} --benchmark=True --det_model_dir=${log_path}/${eval_model_name}_infer --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir} --image_dir=${img_dir} --save_log_path=${save_log_path}
-                        status_check $? "${trainer}" "${command}" "${save_log_path}"
+            else 
+                env="CUDA_VISIBLE_DEVICES=${infer_gpu_id}"
+                for use_trt in ${gpu_trt_list[*]}; do
+                    for precision in ${gpu_precision_list[*]}; do
+                        if [ ${use_trt} = "False" ] && [ ${precision} != "fp32" ]; then
+                            continue
+                        fi
+                        for rec_batch_size in ${rec_batch_size_list[*]}; do
+                            save_log_path="${log_path}/${model_name}_${slim_trainer}_gpu_usetensorrt_${use_trt}_usefp16_${precision}_recbatchnum_${rec_batch_size}_infer.log"
+                            command="${env} ${python} ${inference} --use_gpu=True --use_tensorrt=${use_trt}  --precision=${precision} --benchmark=True --det_model_dir=${log_path}/${eval_model_name}_infer --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir} --image_dir=${img_dir} --save_log_path=${save_log_path}"
+                            ${env} ${python} ${inference} --use_gpu=True --use_tensorrt=${use_trt}  --precision=${precision} --benchmark=True --det_model_dir=${log_path}/${eval_model_name}_infer --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir} --image_dir=${img_dir} --save_log_path=${save_log_path}
+                            status_check $? "${trainer}" "${command}" "${save_log_path}"
+                        done
                     done
                 done
-            done
-        fi
+            fi
+        done
     done
 done

test/params.txt

 train_model_list: ocr_det
 gpu_list: -1|0|0,1
 auto_cast_list: False
-trainer_list: norm|quant|prune
+trainer_list: norm|quant
 python: python3.7
 
 inference: python

test/test.sh

@@ -78,7 +78,7 @@ function status_check(){
     fi
 }
 
-
+IFS="|"
 for train_model in ${train_model_list[*]}; do 
     if [ ${train_model} = "ocr_det" ];then
         model_name="det"
@@ -107,7 +107,7 @@ for train_model in ${train_model_list[*]}; do
             env="CUDA_VISIBLE_DEVICES=${array[0]}"
             IFS="|"
         fi
-
+        IFS="|"
         for auto_cast in ${auto_cast_list[*]}; do 
             for slim_trainer in ${slim_trainer_list[*]}; do 
                 if [ ${slim_trainer} = "norm" ]; then
@@ -126,13 +126,13 @@ for train_model in ${train_model_list[*]}; do
                     trainer="tools/train.py"
                     export_model="tools/export_model.py"
                 fi
-                save_log=${log_path}/${model_name}_${slim_trainer}_autocast_${auto_cast}_gpuid_${gpu}
+                save_log="${log_path}/${model_name}_${slim_trainer}_autocast_${auto_cast}_gpuid_${gpu}"
                 command="${env} ${python}  ${launch}  ${trainer}  -c ${yml_file} -o Global.epoch_num=${epoch} Global.eval_batch_step=${eval_batch_step} Global.auto_cast=${auto_cast}  Global.save_model_dir=${save_log} Global.use_gpu=${use_gpu}"
                 ${env} ${python}  ${launch}  ${trainer}  -c ${yml_file} -o Global.epoch_num=${epoch} Global.eval_batch_step=${eval_batch_step} Global.auto_cast=${auto_cast}  Global.save_model_dir=${save_log} Global.use_gpu=${use_gpu}
                 status_check $? "${trainer}" "${command}" "${save_log}/train.log"
 
-                command="${env} ${python} ${export_model} -c ${yml_file} -o Global.pretrained_model=${save_log}/best_accuracy Global.save_inference_dir=${save_log}/export_inference/ Global.save_model_dir=${save_log}"
-                ${env} ${python} ${export_model} -c ${yml_file} -o Global.pretrained_model=${save_log}/best_accuracy Global.save_inference_dir=${save_log}/export_inference/ Global.save_model_dir=${save_log} 
+                command="${env} ${python} ${export_model} -c ${yml_file} -o Global.pretrained_model=${save_log}/latest Global.save_inference_dir=${save_log}/export_inference/ Global.save_model_dir=${save_log}"
+                ${env} ${python} ${export_model} -c ${yml_file} -o Global.pretrained_model=${save_log}/latest Global.save_inference_dir=${save_log}/export_inference/ Global.save_model_dir=${save_log} 
                 status_check $? "${trainer}" "${command}" "${save_log}/train.log"
                
                 if [ "${model_name}" = "det" ]; then