From 9a55759bc4e9f5bf196da9efb39f691b197413b1 Mon Sep 17 00:00:00 2001
From: 18118216380 <3224925783@qq.com>
Date: Mon, 30 May 2022 16:35:38 +0800
Subject: [PATCH 1/2] 5-30

---
 .../test/train_full_64p.sh                    | 175 +++++++++++++++++
 .../test/train_full_64p.sh                    | 171 ++++++++++++++++
 .../test/train_full_64p.sh                    | 183 ++++++++++++++++++
 3 files changed, 529 insertions(+)
 create mode 100644 PyTorch/built-in/cv/classification/MobileNetV3-Large_ID1784_for_PyTorch/test/train_full_64p.sh
 create mode 100644 PyTorch/built-in/cv/classification/ResNet50_for_PyTorch/test/train_full_64p.sh
 create mode 100644 PyTorch/dev/cv/image_classification/InceptionV4_ID0444_for_PyTorch/test/train_full_64p.sh

diff --git a/PyTorch/built-in/cv/classification/MobileNetV3-Large_ID1784_for_PyTorch/test/train_full_64p.sh b/PyTorch/built-in/cv/classification/MobileNetV3-Large_ID1784_for_PyTorch/test/train_full_64p.sh
new file mode 100644
index 0000000000..16e195255e
--- /dev/null
+++ b/PyTorch/built-in/cv/classification/MobileNetV3-Large_ID1784_for_PyTorch/test/train_full_64p.sh
@@ -0,0 +1,175 @@
+#!/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=64
+export JOB_ID=10087
+RANK_ID_START=0
+
+# 数据集路径,保持为空,不需要修改
+data_path="/npu/traindata/imagenet_pytorch/"
+conf_path=""
+server_index=""
+fix_node_ip=""
+devicesnum=""
+
+#设置默认日志级别,不需要修改
+export ASCEND_GLOBAL_LOG_LEVEL=3
+
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="MobileNetV3-Large_ID1784_for_PyTorch"
+#训练epoch
+train_epochs=600
+#训练batch_size
+batch_size=8192
+#训练step
+train_steps=`expr 1281167 / ${batch_size}`
+#学习率
+learning_rate=0.064
+
+
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+
+
+if [[ $1 == --help || $1 == --h ]];then
+   echo "usage:./train_performance_1p.sh --data_path=data_dir --batch_size=1024 --learning_rate=0.04"
+   exit 1
+fi
+
+for para in $*
+do
+    if [[ $para == --data_path* ]];then
+      data_path=`echo ${para#*=}`
+    elif [[ $para == --batch_size* ]];then
+      batch_size=`echo ${para#*=}`
+    elif [[ $para == --learning_rate* ]];then
+      learning_rate=`echo ${para#*=}`
+    elif [[ $para == --fix_node_ip* ]];then
+	    fix_node_ip=`echo ${para#*=}`
+	elif [[ $para == --devicesnum* ]];then
+	    devicesnum=`echo ${para#*=}`
+    elif [[ $para == --conf_path* ]];then
+        conf_path=`echo ${para#*=}`
+    elif [[ $para == --server_index* ]];then
+        server_index=`echo ${para#*=}`
+    fi
+done
+
+one_node_ip=`find $conf_path -name "server_*0.info"|awk -F "server_" '{print $2}'|awk -F "_" '{print $1}'`
+linux_num=`find $conf_path -name "server_*.info" |wc -l`
+   
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+export HCCL_IF_IP=$fix_node_ip
+export MASTER_ADDR=$one_node_ip
+export MASTER_PORT=29688
+export HCCL_WHITELIST_DISABLE=1
+device_num=${#devicesnum}
+devices_num=`awk 'BEGIN{printf "%.0f\n",'${device_num}'-1}'`
+
+NPUS=($(seq 0 $devices_num))
+rank_server=`awk 'BEGIN{printf "%.0f\n",'${device_num}'*'${server_index}'}'`
+export NPU_WORLD_SIZE=`awk 'BEGIN{printf "%.0f\n",'${device_num}'*'${linux_num}'}'`
+ 
+cd $cur_path
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+RANK_ID_START=0
+rank=0
+for((RANK_ID=$RANK_ID_START;RANK_ID<8;RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $RANK_ID"
+    export RANK_ID=$RANK_ID
+    export ASCEND_DEVICE_ID=$RANK_ID
+    ASCEND_DEVICE_ID=$RANK_ID
+    export RANK=`awk 'BEGIN{printf "%.0f\n",'${rank}'+'${rank_server}'}'`
+
+    #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，不需要的绑核的模型删除，需要模型审视修改
+    
+	nohup python3 ${cur_path}/../main.py \
+        --arch=mobilenet \
+        --data=${data_path} \
+        --batch_size=${batch_size} \
+        --learning-rate=${learning_rate} \
+        --epochs=$train_epochs \
+        --apex \
+        --apex-opt-level='O1' \
+        --workers=128 \
+        --print-freq=1 \
+        --distributed \
+		--lr-step-size=2 \
+		--lr-gamma=0.973 \
+		--wd=0.00001 \
+        --world-size=1 \
+        --dist-rank=0 > $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log 2>&1 &
+    let rank++
+done
+wait
+#训练结束时间，不需要修改
+end_time=$(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 -a 'img/s'  $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk '{print $9}'|awk 'END {print}'`
+#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 '* Prec@1' $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print}'|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}_${RANK_SIZE}'p'_'acc'
+
+##获取性能数据，不需要修改
+#吞吐量
+ActualFPS=${FPS}
+#单迭代训练时长
+TrainingTime=`awk 'BEGIN{printf "%.2f\n", '${batch_size}'*1000/'${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 Epoch: $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log| awk '{print $14}' >> $cur_path/output/$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
diff --git a/PyTorch/built-in/cv/classification/ResNet50_for_PyTorch/test/train_full_64p.sh b/PyTorch/built-in/cv/classification/ResNet50_for_PyTorch/test/train_full_64p.sh
new file mode 100644
index 0000000000..e0dd9e8b76
--- /dev/null
+++ b/PyTorch/built-in/cv/classification/ResNet50_for_PyTorch/test/train_full_64p.sh
@@ -0,0 +1,171 @@
+#!/bin/bash
+
+################基础配置参数，需要模型审视修改##################
+# 必选字段(必须在此处定义的参数): Network batch_size RANK_SIZE
+# 网络名称，同目录名称
+Network="ResNet50_for_PyTorch"
+# 训练batch_size
+batch_size=4096
+# 训练使用的npu卡数
+export RANK_SIZE=64
+export RANK_ID_START=0
+# 数据集路径,保持为空,不需要修改
+data_path=""
+conf_path=""
+server_index=""
+fix_node_ip=""
+
+# 训练epoch 90
+train_epochs=90
+# 加载数据进程数
+workers=128
+
+# 参数校验，data_path为必传参数，其他参数的增删由模型自身决定；此处新增参数需在上面有定义并赋值
+for para in $*
+do
+    if [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    elif [[ $para == --conf_path* ]];then
+            conf_path=`echo ${para#*=}`
+    elif [[ $para == --server_index* ]];then
+            server_index=`echo ${para#*=}`
+    elif [[ $para == --fix_node_ip* ]];then
+            fix_node_ip=`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
+
+one_node_ip=`find $conf_path -name "server_*0.info"|awk -F "server_" '{print $2}'|awk -F "_" '{print $1}'`
+linux_num=`find $conf_path -name "server_*.info" |wc -l`
+
+export HCCL_IF_IP=$fix_node_ip
+export MASTER_ADDR=$one_node_ip
+
+###############指定训练脚本执行路径###############
+# cd到与test文件夹同层级目录下执行脚本，提高兼容性；test_path_dir为包含test文件夹的路径
+cur_path=`pwd`
+cur_path_last_dirname=${cur_path##*/}
+if [ x"${cur_path_last_dirname}" == x"test" ];then
+    test_path_dir=${cur_path}
+    cd ..
+    cur_path=`pwd`
+else
+    test_path_dir=${cur_path}/test
+fi
+
+
+#################创建日志输出目录，不需要修改#################
+
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    export ASCEND_DEVICE_ID=$RANK_ID
+    echo "Device ID: $ASCEND_DEVICE_ID"
+
+
+
+    #创建DeviceID输出目录，不需要修改
+    if [ -d ${test_path_dir}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${test_path_dir}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${test_path_dir}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${test_path_dir}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+
+    echo run process ${RANK_ID}
+
+    #SOLVER.MAX_ITER 82000 \
+    #执行训练脚本，以下传参不需要修改，其他需要模型审视修改
+done
+
+#################启动训练脚本#################
+# 训练开始时间，不需要修改
+start_time=$(date +%s)
+# 非平台场景时source 环境变量
+check_etp_flag=`env | grep etp_running_flag`
+etp_flag=`echo ${check_etp_flag#*=}`
+if [ x"${etp_flag}" != x"true" ];then
+    source ${test_path_dir}/env_npu.sh
+fi
+
+export NODE_RANK=${server_index}
+export NPU_WORLD_SIZE=`awk 'BEGIN{printf "%.0f\n",8*'${linux_num}'}'`
+
+nohup python3.7 ./DistributedResnet50/main_apex_d76_npu.py \
+        --data ${data_path} \
+        --addr=$one_node_ip \
+        --seed=49 \
+        --workers=${workers} \
+        --learning-rate=1.6 \
+        --warmup=8 \
+        --label-smoothing=0.1 \
+        --mom=0.9 \
+        --weight-decay=1.0e-04  \
+        --static-loss-scale=128 \
+        --print-freq=1 \
+        --dist-url='tcp://127.0.0.1:50000' \
+        --dist-backend='hccl' \
+        --multiprocessing-distributed \
+        --world-size=8 \
+        --rank=0 \
+        --benchmark=0 \
+        --device='npu' \
+        --epochs=${train_epochs} \
+        --batch-size=${batch_size} > ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+
+wait
+
+
+##################获取训练数据################
+# 训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+# 训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'acc'
+
+# 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
+grep "FPS@all" ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | awk '{print $11}' >> ${test_path_dir}/output/$ASCEND_DEVICE_ID/train_${CaseName}_fps.log
+FPS=`cat ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${CaseName}_fps.log | awk '{a+=$1} END {if (NR != 0) printf("%.3f",a*8/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 '* Acc@1'  ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print}'|awk -F "Acc@1" '{print $NF}'|awk -F " " '{print $1}'`
+# 打印，不需要修改
+echo "Final Train Accuracy : ${train_accuracy}"
+echo "E2E Training Duration sec : $e2e_time"
+
+# 性能看护结果汇总
+# 获取性能数据，不需要修改
+# 吞吐量
+ActualFPS=${FPS}
+# 单迭代训练时长
+TrainingTime=`awk 'BEGIN{printf "%.2f\n", '${batch_size}'*1000/'${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 Epoch: ${test_path_dir}/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|grep -v Test|awk -F "Loss" '{print $NF}' | awk -F " " '{print $1}' >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+
+# 最后一个迭代loss值，不需要修改
+ActualLoss=`awk 'END {print}'  ${test_path_dir}/output/$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}" >  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainAccuracy = ${train_accuracy}" >> ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >>  ${test_path_dir}/output/$ASCEND_DEVICE_ID/${CaseName}.log
\ No newline at end of file
diff --git a/PyTorch/dev/cv/image_classification/InceptionV4_ID0444_for_PyTorch/test/train_full_64p.sh b/PyTorch/dev/cv/image_classification/InceptionV4_ID0444_for_PyTorch/test/train_full_64p.sh
new file mode 100644
index 0000000000..db4f0a9bab
--- /dev/null
+++ b/PyTorch/dev/cv/image_classification/InceptionV4_ID0444_for_PyTorch/test/train_full_64p.sh
@@ -0,0 +1,183 @@
+#!/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 HCCL_WHITELIST_DISABLE=1
+export RANK_SIZE=64
+export JOB_ID=10087
+RANK_ID_START=0
+# source env.sh
+# 数据集路径,保持为空,不需要修改
+data_path=""
+conf_path=""
+server_index=""
+fix_node_ip=""
+devicesnum=""
+
+#设置默认日志级别,不需要修改
+# export ASCEND_GLOBAL_LOG_LEVEL=3
+
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="InceptionV4_ID0444_for_PyTorch"
+#训练epoch
+train_epochs=240
+#训练batch_size
+batch_size=2048
+#训练step
+train_steps=`expr 1281167 / ${batch_size}`
+#学习率
+learning_rate=0.045
+
+
+
+#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
+
+
+if [[ $1 == --help || $1 == --h ]];then
+   echo "usage:./train_performance_1p.sh --data_path=data_dir --batch_size=1024 --learning_rate=0.04"
+   exit 1
+fi
+
+for para in $*
+do
+    if [[ $para == --data_path* ]];then
+      data_path=`echo ${para#*=}`
+    elif [[ $para == --batch_size* ]];then
+      batch_size=`echo ${para#*=}`
+    elif [[ $para == --learning_rate* ]];then
+      learning_rate=`echo ${para#*=}`
+    elif [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --fix_node_ip* ]];then
+	    fix_node_ip=`echo ${para#*=}`
+	elif [[ $para == --devicesnum* ]];then
+	    devicesnum=`echo ${para#*=}`
+    elif [[ $para == --conf_path* ]];then
+        conf_path=`echo ${para#*=}`
+    elif [[ $para == --server_index* ]];then
+        server_index=`echo ${para#*=}`
+    fi
+done
+
+one_node_ip=`find $conf_path -name "server_*0.info"|awk -F "server_" '{print $2}'|awk -F "_" '{print $1}'`
+linux_num=`find $conf_path -name "server_*.info" |wc -l`
+
+PREC=""
+if [[ $precision_mode == "amp" ]];then
+  PREC="--amp"
+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
+ 
+cd $cur_path
+
+#设置环境变量，不需要修改
+echo "Device ID: $ASCEND_DEVICE_ID"
+export RANK_ID=$RANK_ID
+
+if [ -d $cur_path/output ];then
+   rm -rf $cur_path/output/*
+   mkdir -p $cur_path/output/$ASCEND_DEVICE_ID
+else
+   mkdir -p $cur_path/output/$ASCEND_DEVICE_ID
+fi
+wait
+
+export HCCL_IF_IP=$fix_node_ip
+export MASTER_ADDR=$one_node_ip
+export MASTER_PORT=29688
+export HCCL_WHITELIST_DISABLE=1
+device_num=${#devicesnum}
+devices_num=`awk 'BEGIN{printf "%.0f\n",'${device_num}'-1}'`
+
+NPUS=($(seq 0 $devices_num))
+rank_server=`awk 'BEGIN{printf "%.0f\n",'${device_num}'*'${server_index}'}'`
+export NPU_WORLD_SIZE=`awk 'BEGIN{printf "%.0f\n",'${device_num}'*'${linux_num}'}'`
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+nohup python3.7 ${cur_path}/../main-8p.py \
+	  -a inception_v4 \
+  	${PREC} \
+  	--loss-scale 128 \
+    --data ${data_path} \
+    --addr=$one_node_ip \
+    --seed=49 \
+    --workers=184 \
+    --learning-rate=${learning_rate} \
+    --mom=0.9 \
+    --weight-decay=1.0e-04  \
+    --print-freq=30 \
+    --dist-url='tcp://127.0.0.1:50000' \
+    --dist-backend='hccl' \
+    --multiprocessing-distributed \
+    --world-size=8 \
+    --rank=${server_index} \
+    --device='npu' \
+    --epochs=$train_epochs \
+  	--label-smoothing=0.1 \
+    --batch-size=${batch_size} > $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log 2>&1 &
+wait
+#训练结束时间，不需要修改
+end_time=$(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 -a 'FPS'  $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk -F " " '{print $NF}'|awk 'END {print}'`
+fps=`grep Epoch: ${cur_path}/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|grep -v Test|awk -F "FPS" '{print $2}'|awk -F " " '{print $1}' | tail -n +2|awk '{sum+=$1} END {print sum/NR}' | sed s/[[]:space:]//g `
+FPS=`awk 'BEGIN{printf "%.2f\n",'${fps}'*64}'`
+#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 '* Acc@1' $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print}'|awk -F "Acc@1" '{print $NF}'|awk -F " " '{print $1}'`
+
+#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}_${RANK_SIZE}'p'_'acc'
+
+##获取性能数据，不需要修改
+#吞吐量
+ActualFPS=${FPS}
+#单迭代训练时长
+TrainingTime=`awk 'BEGIN{printf "%.2f\n", '${batch_size}'*1000/'${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 Epoch: $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|grep -v Test|awk -F "Loss" '{print $NF}' | awk -F " " '{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
+echo "TrainAccuracy = ${train_accuracy}" >> ${cur_path}/output/$ASCEND_DEVICE_ID/${CaseName}.log
\ No newline at end of file
-- 
Gitee


From 252aa46831455deefe5c408bce0e2c3e27132edc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E7=8E=8B=E5=9B=BD=E5=BA=86?= <3224925783@qq.com>
Date: Mon, 30 May 2022 11:30:36 +0000
Subject: [PATCH 2/2] update
 ResNet152_ID0424_for_PyTorch/test/train_performance_8p.sh.

---
 .../ResNet152_ID0424_for_PyTorch/test/train_performance_8p.sh   | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/PyTorch/dev/cv/image_classification/ResNet152_ID0424_for_PyTorch/test/train_performance_8p.sh b/PyTorch/dev/cv/image_classification/ResNet152_ID0424_for_PyTorch/test/train_performance_8p.sh
index be0c9c48bf..15d7de6e8e 100644
--- a/PyTorch/dev/cv/image_classification/ResNet152_ID0424_for_PyTorch/test/train_performance_8p.sh
+++ b/PyTorch/dev/cv/image_classification/ResNet152_ID0424_for_PyTorch/test/train_performance_8p.sh
@@ -26,7 +26,7 @@ batch_size=2048
 #训练step
 #train_steps=`expr 1281167 / ${batch_size}`
 #学习率
-learning_rate=0.5
+learning_rate=0.1
 
 #TF2.X独有，需要模型审视修改
 #export NPU_LOOP_SIZE=${train_steps}
-- 
Gitee