From 4b38721b7c942449f49a80deedb65d2ec79380e2 Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 02:29:21 +0000 Subject: [PATCH 1/9] add TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh. --- .../gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh new file mode 100644 index 000000000..e69de29bb -- Gitee From 44b88db7713d7e93817205efba2e82d1170ef8c9 Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 02:29:31 +0000 Subject: [PATCH 2/9] add --- .../test/train_performance_1p.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh index 0bfe40830..a1ec82bc5 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh @@ -147,7 +147,7 @@ echo "Final Performance TrainingTime : $TrainingTime" echo "Final Performance images/sec : $FPS" #输出训练精度,需要模型审视修改 -train_accuracy=`grep psnr: $cur_path/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $NF}'` +train_accuracy=`grep psnr: $cur_path/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $NF}'|awk -F ":" '{print $2}'` #打印,不需要修改 echo "Final Train Accuracy : ${train_accuracy}" @@ -165,7 +165,7 @@ ActualFPS=${FPS} #单迭代训练时长 #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' $cur_path/test/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|awk -F "=" '{print $2}' >> $cur_path/test/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt +grep 'down_mse:' $cur_path/test/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|awk '{print $9}'|awk -F ":" '{print $2}' >> $cur_path/test/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt #最后一个迭代loss值,不需要修改 ActualLoss=`awk 'END {print}' $cur_path/test/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt` -- Gitee From f2e04c18d62e4abe796683df4c316939498c62d2 Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 02:35:50 +0000 Subject: [PATCH 3/9] add --- .../test/train_full_1p.sh | 182 ++++++++++++++++++ .../test/train_performance_1p.sh | 10 +- 2 files changed, 187 insertions(+), 5 deletions(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh index e69de29bb..a1ec82bc5 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh @@ -0,0 +1,182 @@ +#!/bin/bash + +#当前路径,不需要修改 +cur_path=`pwd`/../ + +#集合通信参数,不需要修改 + +export RANK_SIZE=1 +export JOB_ID=10087 +RANK_ID_START=0 + + +# 数据集路径,保持为空,不需要修改 +data_path='' +#预训练模型地址 +ckpt_path='' + +#设置默认日志级别,不需要改 +export ASCEND_GLOBAL_LOG_LEVEL=3 +#export ASCEND_DEVICE_ID=4 + +#基础参数,需要模型审视修改 +#网络名称,同目录名称 +Network="GFLmser_ID0206_for_TensorFlow" +#训练epoch +train_epochs= +#训练batch_size +batch_size=140 +#训练step +train_steps= +#学习率 +learning_rate=le-5 + +#TF2.X独有,需要模型审视修改 +export NPU_LOOP_SIZE=${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 " + 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 + --ckpt_path model + -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}/test/output/overflow_dump + mkdir -p ${over_dump_path} + elif [[ $para == --data_dump_flag* ]];then + data_dump_flag=`echo ${para#*=}` + data_dump_path=${cur_path}/test/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}/test/output/profiling + mkdir -p ${profiling_dump_path} + elif [[ $para == --data_path* ]];then + data_path=`echo ${para#*=}` + elif [[ $para == --ckpt_path* ]];then + ckpt_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 $cur_path/ +for((RANK_ID=$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 ${cur_path}/test/output/${ASCEND_DEVICE_ID} ];then + rm -rf ${cur_path}/test/output/${ASCEND_DEVICE_ID} + mkdir -p ${cur_path}/test/output/$ASCEND_DEVICE_ID/ckpt + else + mkdir -p ${cur_path}/test/output/$ASCEND_DEVICE_ID/ckpt + fi + # 绑核,不需要的绑核的模型删除,需要的模型审视修改 + let a=RANK_ID*12 + let b=RANK_ID+1 + let c=b*12-1 + #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 + # sed -i "/_C.CACHE_DATA_FILENAMES_CACHE_PATH/s@"data/imagenet/"@"${data_path}/imagenet/"@g" config.py + # sed -i "/Squeezenet.save/s@"./ckpt/epoch_80.h5"@"${cur_path}/test/output/$ASCEND_DEVICE_ID/ckpt/epoch_80.h5"@g" train_npu.py + # sed -i "s@"./data/squeezenet_weights_tf_dim_ordering_tf_kernels.h5"@"${data_path}/squeezenet_weights_tf_dim_ordering_tf_kernels.h5"@g" models/squeezenet.py + # python3 train_npu.py > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 + # sed -i "s@"${data_path}/imagenet/"@"data/imagenet/"@g" config.py + # sed -i "s@"${cur_path}/test/output/$ASCEND_DEVICE_ID/ckpt/epoch_80.h5"@"./ckpt/epoch_80.h5"@g" train_npu.py + # sed -i "s@"${data_path}/squeezenet_weights_tf_dim_ordering_tf_kernels.h5"@"./data/squeezenet_weights_tf_dim_ordering_tf_kernels.h5"@g" models/squeezenet.py + python3 main_li.py \ + --data_dir=${data_path}/data \ + --ckpt_dir=$cur_path/new_ckpt \ + --epochs=1 \ + --batch_num_less=135 \ + --print_interval=10 > ${cur_path}/test/output/${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 +TrainingTime=`grep 'fps:' $cur_path/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $2}'` +FPS=`grep 'fps:' $cur_path/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $4}'` +#`awk 'BEGIN{printf "%.2f\n",'${batch_size}'*1000/'${TrainingTime}'}'` +#打印,不需要修改 +echo "Final Performance TrainingTime : $TrainingTime" +echo "Final Performance images/sec : $FPS" + +#输出训练精度,需要模型审视修改 +train_accuracy=`grep psnr: $cur_path/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $NF}'|awk -F ":" '{print $2}'` + +#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}_${RANK_SIZE}'p'_'perf' + +##获取性能数据,不需要修改 +#吞吐量 +ActualFPS=${FPS} +#单迭代训练时长 + +#从train_$ASCEND_DEVICE_ID.log提取Loss到train_${CaseName}_loss.txt中,需要根据模型审视 +grep 'down_mse:' $cur_path/test/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|awk '{print $9}'|awk -F ":" '{print $2}' >> $cur_path/test/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt +#最后一个迭代loss值,不需要修改 +ActualLoss=`awk 'END {print}' $cur_path/test/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt` + +#关键信息打印到${CaseName}.log中,不需修改 +echo "Network = ${Network}" > $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "RankSize = ${RANK_SIZE}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "BatchSize = ${BatchSize}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "DeviceType = ${DeviceType}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "CaseName = ${CaseName}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "ActualFPS = ${ActualFPS}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "TrainingTime = ${TrainingTime}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "ActualLoss = ${ActualLoss}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log +echo "TrainAccuracy = ${train_accuracy}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log \ No newline at end of file diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh index a1ec82bc5..64a48d751 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh @@ -127,8 +127,8 @@ do --data_dir=${data_path}/data \ --ckpt_dir=$cur_path/new_ckpt \ --epochs=1 \ - --batch_num_less=135 \ - --print_interval=10 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 + --batch_num_less=140 \ + --print_interval=100 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 done wait @@ -147,10 +147,10 @@ echo "Final Performance TrainingTime : $TrainingTime" echo "Final Performance images/sec : $FPS" #输出训练精度,需要模型审视修改 -train_accuracy=`grep psnr: $cur_path/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $NF}'|awk -F ":" '{print $2}'` +#train_accuracy=`grep psnr: $cur_path/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk 'END {print $NF}'|awk -F ":" '{print $2}'` #打印,不需要修改 -echo "Final Train Accuracy : ${train_accuracy}" +#echo "Final Train Accuracy : ${train_accuracy}" echo "E2E Training Duration sec : $e2e_time" #性能看护结果汇总 @@ -179,4 +179,4 @@ echo "ActualFPS = ${ActualFPS}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${Cas echo "TrainingTime = ${TrainingTime}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log echo "ActualLoss = ${ActualLoss}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log -echo "TrainAccuracy = ${train_accuracy}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log \ No newline at end of file +#echo "TrainAccuracy = ${train_accuracy}" >> $cur_path/test/output/$ASCEND_DEVICE_ID/${CaseName}.log \ No newline at end of file -- Gitee From dad83d2ba222f11de4cee6ea1108f3bdfc9da257 Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 02:38:40 +0000 Subject: [PATCH 4/9] add --- .../gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh index a1ec82bc5..bafb2379d 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh @@ -127,7 +127,7 @@ do --data_dir=${data_path}/data \ --ckpt_dir=$cur_path/new_ckpt \ --epochs=1 \ - --batch_num_less=135 \ + --batch_num_less=140 \ --print_interval=10 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 done wait -- Gitee From 28f942bec3655b0c67de06f59d9298798061b95e Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 02:38:55 +0000 Subject: [PATCH 5/9] add --- .../gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh index bafb2379d..5625b9074 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh @@ -157,7 +157,7 @@ echo "E2E Training Duration sec : $e2e_time" #训练用例信息,不需要修改 BatchSize=${batch_size} DeviceType=`uname -m` -CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'perf' +CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'acc' ##获取性能数据,不需要修改 #吞吐量 -- Gitee From e3e613e343ee605388b4968390532e5304eb94f9 Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 06:19:59 +0000 Subject: [PATCH 6/9] add --- .../contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/main_li.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/main_li.py b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/main_li.py index a4d62d7b0..cb4692907 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/main_li.py +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/main_li.py @@ -166,7 +166,7 @@ def train(): _down, down_mse_loss = session.run([model.down_train_op, model.down_mse_loss], feed_dict) global_step += 1 - if global_step % args.print_interval == 1: #300 + if global_step % args.print_interval == 0: #300 psnr = test(session, model, test_set) d_cost, g_cost, down_mse_loss, rs = session.run([ model.discrim_cost, model.generator_cost, model.down_mse_loss,merged], feed_dict) with open(os.path.join(args.ckpt_dir, 'log.txt'), 'a', encoding='utf-8') as f: -- Gitee From 27f32bd1ca870acf6eadfff8470c8e877bef028f Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 06:35:36 +0000 Subject: [PATCH 7/9] add --- .../GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh index 64a48d751..56f53afc5 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh @@ -127,7 +127,7 @@ do --data_dir=${data_path}/data \ --ckpt_dir=$cur_path/new_ckpt \ --epochs=1 \ - --batch_num_less=140 \ + --batch_num_less=200 \ --print_interval=100 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 done wait -- Gitee From 2ade274f321d7f0e91a32b26e14556460bef67dc Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 07:45:27 +0000 Subject: [PATCH 8/9] add --- .../test/train_performance_1p.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh index 56f53afc5..4405410ea 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_performance_1p.sh @@ -127,8 +127,8 @@ do --data_dir=${data_path}/data \ --ckpt_dir=$cur_path/new_ckpt \ --epochs=1 \ - --batch_num_less=200 \ - --print_interval=100 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 + --batch_num_less=220 \ + --print_interval=2 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 done wait -- Gitee From a6cd9669aba13b3498292f02020c7426d9cd975b Mon Sep 17 00:00:00 2001 From: chunchun5958 Date: Mon, 28 Mar 2022 07:51:38 +0000 Subject: [PATCH 9/9] add --- .../GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh index 5625b9074..bd5e428cf 100644 --- a/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh +++ b/TensorFlow/contrib/cv/gflmser/GFLmser_ID0206_for_TensorFlow/test/train_full_1p.sh @@ -126,9 +126,9 @@ do python3 main_li.py \ --data_dir=${data_path}/data \ --ckpt_dir=$cur_path/new_ckpt \ - --epochs=1 \ - --batch_num_less=140 \ - --print_interval=10 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 + --epochs=300 \ + --batch_num_less=0 \ + --print_interval=300 > ${cur_path}/test/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 done wait -- Gitee