diff --git a/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/examples/run_fwfm_profiling.py b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/examples/run_fwfm_profiling.py
new file mode 100644
index 0000000000000000000000000000000000000000..ed6eb14282232811a09e914e81a5302ea4d17a59
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/examples/run_fwfm_profiling.py
@@ -0,0 +1,124 @@
+#
+# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ============================================================================
+# Copyright 2021 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+from npu_bridge.npu_init import *
+from tensorflow import keras
+import pandas as pd
+from sklearn.metrics import log_loss, roc_auc_score
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder, MinMaxScaler
+
+from deepctr.models import FwFM
+from deepctr.feature_column import  SparseFeat, DenseFeat, get_feature_names
+
+import argparse
+import os
+
+def main():
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--data_dir', default="./",
+                        help='data path for train')
+    parser.add_argument('--precision_mode', default='allow_fp32_to_fp16',
+                        help='allow_fp32_to_fp16/force_fp16/ '
+                             'must_keep_origin_dtype/allow_mix_precision.')
+    parser.add_argument('--profiling', default=False,
+                        help='if or not profiling for performance debug, default is False')
+    parser.add_argument('--profiling_dump_path', default="/home/data",
+                        help='the path to save profiling data')
+    args = parser.parse_args()
+
+    sess_config = tf.ConfigProto()
+    custom_op = sess_config.graph_options.rewrite_options.custom_optimizers.add()
+    sess_config.graph_options.rewrite_options.remapping = RewriterConfig.OFF
+    sess_config.graph_options.rewrite_options.memory_optimization = RewriterConfig.OFF
+    custom_op.name = "NpuOptimizer"
+    custom_op.parameter_map["precision_mode"].s = tf.compat.as_bytes(args.precision_mode)
+    custom_op.parameter_map["profiling_mode"].b = True
+    custom_op.parameter_map["profiling_options"].s = tf.compat.as_bytes('{"output":"./profiling","training_trace":"on","task_trace":"on","fp_point":"","bp_point":"","aic_metrics":"PipeUtilization"}')
+    #if args.profiling:
+    #    custom_op.parameter_map["profiling_mode"].b = True
+    #    custom_op.parameter_map["profiling_options"].s = tf.compat.as_bytes(
+    #        '{"output":"' + args.profiling_dump_path + '", \
+    #                      "training_trace":"on", \
+    #                      "task_trace":"on", \
+    #                      "aicpu":"on", \
+    #                      "aic_metrics":"PipeUtilization",\
+    #                      "fp_point":"concatenate_1/concat", \
+    #                      "bp_point":"training/Adam/gradients/gradients/AddN_83"}')
+
+    npu_keras_sess = set_keras_session_npu_config(config=sess_config)
+    data = pd.read_csv(os.path.join(args.data_dir, 'criteo_sample.txt'))
+
+    sparse_features = ['C' + str(i) for i in range(1, 27)]
+    dense_features = ['I' + str(i) for i in range(1, 14)]
+
+    data[sparse_features] = data[sparse_features].fillna('-1', )
+    data[dense_features] = data[dense_features].fillna(0, )
+    target = ['label']
+
+    # 1.Label Encoding for sparse features,and do simple Transformation for dense features
+    for feat in sparse_features:
+        lbe = LabelEncoder()
+        data[feat] = lbe.fit_transform(data[feat])
+    mms = MinMaxScaler(feature_range=(0, 1))
+    data[dense_features] = mms.fit_transform(data[dense_features])
+
+    # 2.count #unique features for each sparse field,and record dense feature field name
+
+    fixlen_feature_columns = [SparseFeat(feat, vocabulary_size=data[feat].nunique(),embedding_dim=4)
+                           for i,feat in enumerate(sparse_features)] + [DenseFeat(feat, 1,)
+                          for feat in dense_features]
+
+    dnn_feature_columns = fixlen_feature_columns
+    linear_feature_columns = fixlen_feature_columns
+
+    feature_names = get_feature_names(linear_feature_columns + dnn_feature_columns)
+
+    # 3.generate input data for model
+
+    train, test = train_test_split(data, test_size=0.2)
+    train_model_input = {name:train[name] for name in feature_names}
+    test_model_input = {name:test[name] for name in feature_names}
+
+    # 4.Define Model,train,predict and evaluate
+    model = FwFM(linear_feature_columns, dnn_feature_columns, dnn_hidden_units=(100,100), task='binary')
+    model.compile("adam", "binary_crossentropy",
+                  metrics=['binary_crossentropy'], )
+
+    history = model.fit(train_model_input, train[target].values,
+                        batch_size=128, epochs=10, verbose=1, validation_split=0.2, )
+    pred_ans = model.predict(test_model_input, batch_size=8)
+    print("test LogLoss", round(log_loss(test[target].values, pred_ans), 4))
+    print("test AUC", round(roc_auc_score(test[target].values, pred_ans), 4))
+    close_session(npu_keras_sess)
+
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_ID3057_FwFM_performance_1p_RT2_profiling2.sh b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_ID3057_FwFM_performance_1p_RT2_profiling2.sh
new file mode 100644
index 0000000000000000000000000000000000000000..4d105d63746527b58ff261c1af4aefb0736b6538
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_ID3057_FwFM_performance_1p_RT2_profiling2.sh
@@ -0,0 +1,177 @@
+#!/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
+
+#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 $cur_path/../examples
+
+sed -i "s|epochs=10|epochs=5|g" run_fwfm_profiling.py
+
+for((RANK_ID=$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_profiling.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 ))
+
+a=`find /usr/local/Ascend/ -name acp | awk -F 'acp' '{print $1}'`
+cd $a
+./msprof --parse=on --output=$cur_path/../examples/profiling
+./msprof --export=on --output=$cur_path/../examples/profiling
+
+
+sed -i "s|epochs=5|epochs=10|g" run_fwfm_profiling.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}_${RANK_SIZE}'p'_'RT2'_'profiling2'_'perf'
+
+##获取性能数据，不需要修改
+#吞吐量
+
+ActualFPS=${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
\ No newline at end of file