diff --git a/TensorFlow/built-in/cv/image_classification/ResNet50_ID0058_for_TensorFlow/test/train_performance_bs256_1p_profiling1.sh b/TensorFlow/built-in/cv/image_classification/ResNet50_ID0058_for_TensorFlow/test/train_performance_bs256_1p_profiling1.sh
new file mode 100644
index 0000000000000000000000000000000000000000..fb11c0aab150423d4c3cf95802e71bdf83addda8
--- /dev/null
+++ b/TensorFlow/built-in/cv/image_classification/ResNet50_ID0058_for_TensorFlow/test/train_performance_bs256_1p_profiling1.sh
@@ -0,0 +1,204 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+
+#集合通信参数,不需要修改
+export RANK_SIZE=1
+export JOB_ID=99990001
+export RANK_ID=1
+export HCCL_CONNECT_TIMEOUT=600
+RANK_ID_START=0
+
+# 数据集路径,保持为空,不需要修改
+data_path=""
+ffts='None'
+#设置默认日志级别,不需要修改
+export ASCEND_GLOBAL_LOG_LEVEL_ETP=3
+export PROFILING_MODE=true
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="ResNet50_ID0058_for_TensorFlow"
+#训练epoch
+train_epochs=1
+#训练batch_size
+batch_size=256
+#训练step
+train_steps=2000
+#学习率
+learning_rate=
+
+#维测参数，precision_mode需要模型审视修改
+precision_mode="must_keep_origin_dtype"
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+autotune=False
+
+# 帮助信息，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_full_1p.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --precision_mode         precision mode(allow_fp32_to_fp16/force_fp16/must_keep_origin_dtype/allow_mix_precision)
+    --over_dump		         if or not over detection, default is False
+    --data_dump_flag	     data dump flag, default is False
+    --data_dump_step		 data dump step, default is 10
+    --profiling		         if or not profiling for performance debug, default is False
+    --autotune               whether to enable autotune, default is False
+    --data_path		         source data of training
+    -h/--help		         show help message
+    "
+    exit 1
+fi
+
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --hf32 ]];then
+        hf32=`echo ${para#*=}`
+    elif [[ $para == --fp32 ]];then
+        fp32=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --ffts* ]];then
+        ffts=`echo ${para#*=}`
+    elif [[ $para == --autotune* ]];then
+        autotune=`echo ${para#*=}`
+        mv $install_path/fwkacllib/data/rl/Ascend910/custom $install_path/fwkacllib/data/rl/Ascend910/custom_bak
+        mv $install_path/fwkacllib/data/tiling/Ascend910/custom $install_path/fwkacllib/data/tiling/Ascend910/custom_bak
+        autotune_dump_path=${cur_path}/output/autotune_dump
+        mkdir -p ${autotune_dump_path}/GA
+        mkdir -p ${autotune_dump_path}/rl
+        cp -rf $install_path/fwkacllib/data/tiling/Ascend910/custom ${autotune_dump_path}/GA/
+        cp -rf $install_path/fwkacllib/data/rl/Ascend910/custom ${autotune_dump_path}/RL/
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    fi
+done
+
+if [[ ${fp32} == "--hf32" ]];then
+  export ENABLE_HF32_EXECUTION=1
+fi
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+#修改参数
+sed -i "50s|PATH_TO_BE_CONFIGURED|${data_path}|g"  $cur_path/../src/configs/res50_256bs_1p.py
+sed -i "107s|PATH_TO_BE_CONFIGURED|${cur_path}/output/0/d\_solution/ckpt0|g"  $cur_path/../src/configs/res50_256bs_1p.py
+
+cp data_loader.py $cur_path/../src/data_loader/resnet50/
+
+if [[ ${ffts} == "--ffts" ]];then
+   export ASCEND_ENHANCE_ENABLE=1
+fi
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+cd $cur_path/../
+#进入训练脚本目录，需要模型审视修改
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $ASCEND_DEVICE_ID"
+    export RANK_ID=$RANK_ID
+    export DEVICE_INDEX=$RANK_ID
+    
+    #创建DeviceID输出目录，不需要修改
+    if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+
+    #执行训练脚本，以下传参不需要修改，其他需要模型审视修改
+    #--data_dir, --model_dir, --precision_mode, --over_dump, --over_dump_path，--data_dump_flag，--data_dump_step，--data_dump_path，--profiling，--profiling_dump_path，--autotune
+    nohup python3.7 ${cur_path}/../src/mains/res50.py --config_file=res50_256bs_1p \
+    --max_train_steps=${train_steps} \
+    --iterations_per_loop=100 \
+    --debug=True \
+    --eval=False \
+    --precision_mode ${precision_mode} \
+    --model_dir=${cur_path}/output/${ASCEND_DEVICE_ID}/d_solution/ckpt${ASCEND_DEVICE_ID} > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+done 
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+#参数改回
+sed -i "50s|${data_path}|PATH_TO_BE_CONFIGURED|g"  $cur_path/../src/configs/res50_256bs_1p.py
+sed -i "107s|${cur_path}/output/0/d\_solution/ckpt0|PATH_TO_BE_CONFIGURED|g"  $cur_path/../src/configs/res50_256bs_1p.py
+
+#结果打印，不需要修改
+echo "------------------ Final result ------------------"
+#输出性能FPS，需要模型审视修改
+FPS=`cat ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | grep "FPS: " | awk -F "FPS: " '{print $2}' | awk -F "  loss:" '{print $1}' | tail -n +2 | awk '{sum+=$1} END {print sum/NR}'`
+#打印，不需要修改
+echo "Final Performance images/sec : $FPS"
+
+#输出训练精度,需要模型审视修改
+#train_accuracy=`grep -A 1 top1 $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $3}'`
+#打印，不需要修改
+#echo "Final Train Accuracy : ${train_accuracy}"
+echo "E2E Training Duration sec : $e2e_time"
+
+#稳定性精度看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+if [[ ${fp32} == "--fp32" ]];then
+  CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'fp32'_'profiling1'_'perf'
+elif [[ ${hf32} == "--hf32" ]];then
+  CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'hf32'_'profiling1'_'perf'
+elif [[ ${ffts} == "--ffts" ]];then
+  CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'profiling1'_'perf'_'ffts'
+else
+  CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'profiling1'_'perf'
+fi
+
+
+
+##获取性能数据
+#吞吐量，不需要修改
+ActualFPS=${FPS}
+#单迭代训练时长，不需要修改
+TrainingTime=`awk 'BEGIN{printf "%.2f\n",'${batch_size}'*'${RANK_SIZE}'*1000/'${FPS}'}'`
+
+#从train_$ASCEND_DEVICE_ID.log提取Loss到train_${CaseName}_loss.txt中，需要根据模型审视
+grep "FPS: " $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log | awk -F "loss: " '{print $2}' | awk -F "total" '{print $1}' >> $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+
+#最后一个迭代loss值，不需要修改
+ActualLoss=`awk 'END {print}' $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
\ No newline at end of file
diff --git a/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_ID3057_FwFM_performance_1p_RT2_profiling1.sh b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_ID3057_FwFM_performance_1p_RT2_profiling1.sh
new file mode 100644
index 0000000000000000000000000000000000000000..26478c6d4772435db0b9389b26531b9c0662ed86
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_ID3057_FwFM_performance_1p_RT2_profiling1.sh
@@ -0,0 +1,171 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+
+#集合通信参数,不需要修改
+
+export RANK_SIZE=1
+export JOB_ID=10087
+RANK_ID_START=0
+RankSize=1
+# 数据集路径,保持为空,不需要修改
+data_path=""
+#export ASCEND_SLOG_PRINT_TO_STDOUT=1
+export PROFILING_MODE=true
+#使能RT2.0
+export ENABLE_RUNTIME_V2=1
+
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="FwFM_ID3057_for_TensorFlow"
+#训练epoch
+train_epochs=5
+#训练batch_size
+batch_size=128
+#训练step
+train_steps=
+#学习率
+learning_rate=
+
+#维测参数，precision_mode需要模型审视修改
+precision_mode="allow_fp32_to_fp16"
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+
+# 帮助信息，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_performance_1P.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --precision_mode         precision mode(allow_fp32_to_fp16/force_fp16/must_keep_origin_dtype/allow_mix_precision)
+    --over_dump		           if or not over detection, default is False
+    --data_dump_flag		     data dump flag, default is False
+    --data_dump_step		     data dump step, default is 10
+    --profiling		           if or not profiling for performance debug, default is False
+	--data_path		           source data of training
+    -h/--help		             show help message
+    "
+    exit 1
+fi
+
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+#进入训练脚本目录，需要模型审视修改
+cd $cur_path/../examples
+
+sed -i "s|epochs=10|epochs=5|g" run_fwfm.py
+
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $ASCEND_DEVICE_ID"
+    export RANK_ID=$RANK_ID
+
+    #创建DeviceID输出目录，不需要修改
+    if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+    
+    #执行训练脚本，以下传参不需要修改，其他需要模型审视修改
+    #--data_dir, --model_dir, --precision_mode, --over_dump, --over_dump_path，--data_dump_flag，--data_dump_step，--data_dump_path，--profiling，--profiling_dump_path
+    nohup python3 run_fwfm.py \
+        --data_dir=${data_path} \
+        --precision_mode=${precision_mode} \
+        --profiling=${profiling} \
+        --profiling_dump_path=${profiling_dump_path} > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+done 
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+sed -i "s|epochs=5|epochs=10|g" run_fwfm.py
+
+#结果打印，不需要修改
+echo "------------------ Final result ------------------"
+# #输出性能FPS，需要模型审视修改
+
+Time=`cat $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|tr -d '\b\r'|grep -Eo "[0-9]*us/sample"|awk -F "us/sample" 'END {print $1}'`
+FPS=`awk 'BEGIN{printf "%.2f\n", 1 /'${Time}'*1000000}'`
+#打印，不需要修改
+echo "Final Performance item/sec : $FPS"
+
+#输出CompileTime
+CompileTime=`grep '/sample' $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log| head -n 2| awk '{print $4}' | awk -F 's' '{sum+=$1} END {print sum}'`
+
+# #输出训练精度,需要模型审视修改
+train_accuracy=`grep "test AUC" ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk '{print $3}'`
+# #打印，不需要修改
+echo "Final Train Accuracy : ${train_accuracy}"
+echo "E2E Training Duration sec : $e2e_time"
+
+#性能看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'RT2'_'profiling1'_'perf'
+
+##获取性能数据，不需要修改
+#吞吐量
+
+ActualFPS=${FPS}
+#单迭代训练时长
+TrainingTime=`awk 'BEGIN{printf "%.2f\n",'${BatchSize}'/'${FPS}'}'`
+
+#从train_$ASCEND_DEVICE_ID.log提取Loss到train_${CaseName}_loss.txt中，需要根据模型审视
+cat $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|tr -d '\b\r'|grep -Eo " loss: [0-9]*\.[0-9]*"|awk -F " " '{print $2}' > $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+
+#最后一个迭代loss值，不需要修改
+ActualLoss=`awk 'END {print}' $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainAccuracy = ${train_accuracy}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CompileTime = ${CompileTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
diff --git a/TensorFlow/built-in/recommendation/WideDeep_ID2712_for_TensorFlow/test/train_performance_1p_profiling1.sh b/TensorFlow/built-in/recommendation/WideDeep_ID2712_for_TensorFlow/test/train_performance_1p_profiling1.sh
new file mode 100644
index 0000000000000000000000000000000000000000..d863b6a5147a38ec87b370fb9293a9df3934c980
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/WideDeep_ID2712_for_TensorFlow/test/train_performance_1p_profiling1.sh
@@ -0,0 +1,162 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+#export ASCEND_SLOG_PRINT_TO_STDOUT=1
+#export GE_USE_STATIC_MEMORY=1
+export PROFILING_MODE=true
+#集合通信参数,不需要修改
+
+export RANK_SIZE=1
+export JOB_ID=10087
+
+
+RANK_ID_START=0
+
+#基础参数，需要模型审视修改
+#Batch Size
+batch_size=131072
+#网络名称，同目录名称
+Network="WideDeep_ID2712_for_TensorFlow"
+#Device数量，单卡默认为1
+RankSize=1
+
+#参数配置
+data_path="/npu/traindata/ID2940_CarPeting_TF_WideDeep_TF"
+train_size=13107200
+display_step=10
+
+#维持参数，以下不需要修改
+over_dump=False
+precision_mode="allow_mix_precision"
+# 帮助信息，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_performance_1p.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --over_dump		         if or not over detection, default is False
+    --data_path		         source data of training
+    --train_epochs       train epochs
+    -h/--help		         show help message
+    "
+    exit 1
+fi
+
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+##############执行训练##########
+if [ -d $cur_path/output ];then
+   rm -rf $cur_path/output/*
+   mkdir -p $cur_path/output/$ASCEND_DEVICE_ID/ckpt
+else
+   mkdir -p $cur_path/output/$ASCEND_DEVICE_ID/ckpt
+fi
+
+#if [ -d $cur_path/../config/1p_$ASCEND_DEVICE.json ];then
+#    export RANK_TABLE_FILE=$cur_path/../config/1p_$ASCEND_DEVICE.json
+#    export RANK_ID=$ASCEND_DEVICE_ID
+#else
+#    export RANK_TABLE_FILE=$cur_path/../config/1p.json
+#    export RANK_ID=0
+#fi
+wait
+
+#配置文件备份和修改
+cd $cur_path/../
+if [  -f configs/config.py.bak ];then
+   cp configs/config.py.bak configs/config.py
+   rm -f configs/config.py.run
+else
+   cp configs/config.py configs/config.py.bak
+   rm -f configs/config.py.run
+fi
+sed -i "s%/npu/traindata/ID2940_CarPeting_TF_WideDeep_TF%${data_path}%p" configs/config.py
+sed -i "s%./model%$cur_path/output/$ASCEND_DEVICE_ID/ckpt%p" configs/config.py
+sed -i "s%59761827%${train_size}%p" configs/config.py
+sed -i "s%display_step = 100%display_step = $display_step%p" configs/config.py
+#echo `cat configs/config.py |uniq > configs/config.py; cp -f configs/config.py configs/config.py.run`
+cp configs/config.py configs/config.py.run
+#训练执行
+start=$(date +%s)
+nohup python3 train.py --data_path=$data_path \
+	               --ckpt_path=$cur_path/output/$ASCEND_DEVICE_ID/ckpt \
+		       --train_size=$train_size \
+		       --precision_mode=$precision_mode \
+		       --display_step=$display_step > $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log 2>&1 &
+wait
+end=$(date +%s)
+e2e_time=$(( $end - $start ))
+
+#配置文件恢复
+mv -f configs/config.py.bak configs/config.py
+
+#结果打印，不需要修改
+echo "------------------ Final result ------------------"
+#输出性能FPS，需要模型审视修改
+
+#FPS=`grep 'fps :'  $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log| awk -F' ' '{print $25}' | tail -n 1`
+time=`grep -rn 'epoch 2 total time ='  $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log| awk -F '=' '{print $2}'|sed s/[[:space:]]//g`
+FPS=`awk 'BEGIN{printf "%.2f\n",'100'*'${batch_size}'/'${time}'}'`
+#打印，不需要修改
+echo "Final Performance images/sec : $FPS"
+
+#输出训练精度,需要模型审视修改
+train_accuracy=`grep 'eval auc' $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log| awk -F' ' '{print $8}' |tail -n 1`
+#打印，不需要修改
+echo "Final Train Accuracy : ${train_accuracy}"
+echo "E2E Training Duration sec : $e2e_time"
+
+#稳定性精度看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+if [[ $precision_mode == "must_keep_origin_dtype" ]];then
+    CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'fp32'_'profiling1'_'perf'
+else
+    CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'profiling1'_'perf'
+fi
+echo "CaseName : $CaseName"
+
+##获取性能数据
+#吞吐量，不需要修改
+ActualFPS=${FPS}
+#单迭代训练时长，不需要修改
+TrainingTime=$time
+echo "TrainingTime(ms/step) : $TrainingTime"
+
+#从train_$ASCEND_DEVICE_ID.log提取Loss到train_${CaseName}_loss.txt中，需要根据模型审视
+loss=`grep 'loss =' $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | tr -d '\b\r' | awk -F' ' '{print $9}'|sed 's/,$//'`
+echo "${loss}"> $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+
+#最后一个迭代loss值，不需要修改
+ActualLoss=`cat $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt | tail -n 1`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainAccuracy = ${train_accuracy}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
\ No newline at end of file
diff --git a/TensorFlow2/built-in/cv/image_classification/ResNet50_ID0360_for_TensorFlow2.X/test/train_performance_1p_profiling1.sh b/TensorFlow2/built-in/cv/image_classification/ResNet50_ID0360_for_TensorFlow2.X/test/train_performance_1p_profiling1.sh
new file mode 100644
index 0000000000000000000000000000000000000000..eafd3e067e782c7660b02fa8704001d157f14234
--- /dev/null
+++ b/TensorFlow2/built-in/cv/image_classification/ResNet50_ID0360_for_TensorFlow2.X/test/train_performance_1p_profiling1.sh
@@ -0,0 +1,201 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+export PROFILING_MODE=true
+#集合通信参数,不需要修改
+
+export RANK_SIZE=1
+export JOB_ID=10087
+RANK_ID_START=0
+
+
+# 数据集路径,保持为空,不需要修改
+data_path=""
+
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="ResNet50_ID0360_for_TensorFlow2.X"
+#训练epoch
+train_epochs=2
+#训练batch_size
+batch_size=256
+#训练step
+train_steps=`expr 1281167 / ${batch_size}`
+#学习率
+learning_rate=0.495
+
+#TF2.X独有，需要模型审视修改
+export NPU_LOOP_SIZE=${train_steps}
+
+#维测参数，precision_mode需要模型审视修改
+precision_mode="allow_mix_precision"
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+
+# 帮助信息，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_performance_1P.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --precision_mode         precision mode(allow_fp32_to_fp16/force_fp16/must_keep_origin_dtype/allow_mix_precision)
+    --over_dump		           if or not over detection, default is False
+    --data_dump_flag		     data dump flag, default is False
+    --data_dump_step		     data dump step, default is 10
+    --profiling		           if or not profiling for performance debug, default is False
+    --data_path		           source data of training
+    -h/--help		             show help message
+    "
+    exit 1
+fi
+
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    elif [[ $para == --conda_name* ]];then
+        conda_name=`echo ${para#*=}`
+        source set_conda.sh
+        source activate $conda_name
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+#进入训练脚本目录，需要模型审视修改
+cd $cur_path/../tensorflow
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $ASCEND_DEVICE_ID"
+    export RANK_ID=$RANK_ID
+
+
+
+    #创建DeviceID输出目录，不需要修改
+    if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+    #绑核，不需要绑核的模型删除，需要绑核的模型根据实际修改
+    cpucount=`lscpu | grep "CPU(s):" | head -n 1 | awk '{print $2}'`
+    cpustep=`expr $cpucount / 8`
+    echo "taskset c steps:" $cpustep
+    let a=RANK_ID*$cpustep
+    let b=RANK_ID+1
+    let c=b*$cpustep-1
+    
+    #执行训练脚本，以下传参不需要修改，其他需要模型审视修改
+    #--data_dir, --model_dir, --precision_mode, --over_dump, --over_dump_path，--data_dump_flag，--data_dump_step，--data_dump_path，--profiling，--profiling_dump_path
+    nohup taskset -c $a-$c python3 resnet_ctl_imagenet_main.py \
+        --data_dir=${data_path} \
+        --num_accumulation_steps=1 \
+        --train_steps=${train_steps} \
+        --train_epochs=${train_epochs} \
+        --model_dir=${cur_path}/output/$ASCEND_DEVICE_ID/ckpt \
+        --distribution_strategy=off \
+        --use_tf_while_loop=true \
+        --use_tf_function=true \
+        --enable_checkpoint_and_export \
+        --steps_per_loop=${train_steps} \
+        --base_learning_rate=${learning_rate} \
+        --momentum=0.901 \
+        --epochs_between_evals=1 \
+        --eval_offset_epochs=2 \
+        --optimizer=SGD \
+        --label_smoothing=0.1 \
+        --single_l2_loss_op \
+        --warmup_epochs=5 \
+        --weight_decay=0.000025 \
+        --lr_schedule=polynomial \
+        --drop_eval_remainder=True \
+        --precision_mode=${precision_mode} \
+        --over_dump=${over_dump} \
+        --over_dump_path=${over_dump_path} \
+        --data_dump_flag=${data_dump_flag} \
+        --data_dump_step=${data_dump_step} \
+        --data_dump_path=${data_dump_path} \
+        --batch_size=${batch_size} \
+        --profiling=${profiling} \
+        --profiling_dump_path=${profiling_dump_path}  > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+done 
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+#结果打印，不需要修改
+echo "------------------ Final result ------------------"
+#输出性能FPS，需要模型审视修改
+FPS=`grep TimeHistory  $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $6}'`
+#打印，不需要修改
+echo "Final Performance images/sec : $FPS"
+
+#输出训练精度,需要模型审视修改
+train_accuracy=`grep eval_accuracy $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|grep -v mlp_log|awk 'END {print $5}'| sed 's/,//g' |cut -c 1-5`
+#打印，不需要修改
+echo "Final Train Accuracy : ${train_accuracy}"
+echo "E2E Training Duration sec : $e2e_time"
+
+#性能看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'profiling1'_'perf'
+
+##获取性能数据，不需要修改
+#吞吐量
+ActualFPS=${FPS}
+#单迭代训练时长
+TrainingTime=`awk 'BEGIN{printf "%.2f\n",'${BatchSize}'*1000/'${FPS}'}'`
+
+#从train_$ASCEND_DEVICE_ID.log提取Loss到train_${CaseName}_loss.txt中，需要根据模型审视
+grep train_loss $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|grep -v BatchTimestamp|awk '{print $10}'|sed 's/,//g'|sed '/^$/d' >> $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+
+#最后一个迭代loss值，不需要修改
+ActualLoss=`awk 'END {print}' $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainAccuracy = ${train_accuracy}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+
+sed -i "/AttributeError/d" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log
+sed -i "/MLL/d" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log
\ No newline at end of file