Merge pull request #4670 from hysunflower/update_ocr_scripts_for_benchmark

Update ocr scripts for benchmark

benchmark/run_benchmark_det.sh

@@ -6,27 +6,35 @@ function _set_params(){
     run_mode=${1:-"sp"}          # 单卡sp|多卡mp
     batch_size=${2:-"64"}
     fp_item=${3:-"fp32"}         # fp32|fp16
-    max_iter=${4:-"10"}       # 可选，如果需要修改代码提前中断
-    model_name=${5:-"model_name"}
+    max_epoch=${4:-"10"}         # 可选，如果需要修改代码提前中断
+    model_item=${5:-"model_item"}
     run_log_path=${TRAIN_LOG_DIR:-$(pwd)}  # TRAIN_LOG_DIR 后续QA设置该参数
-
+#   日志解析所需参数
+    base_batch_size=${batch_size}
+    mission_name="OCR"
+    direction_id="0"
+    ips_unit="images/sec"
+    skip_steps=2                 # 解析日志，有些模型前几个step耗时长，需要跳过                                    (必填)
+    keyword="ips:"               # 解析日志，筛选出数据所在行的关键字                                             (必填)
+    index="1"
+    model_name=${model_item}_${run_mode}_bs${batch_size}_${fp_item}        # model_item 用于yml文件名匹配，model_name 用于数据入库前端展示
 #   以下不用修改   
     device=${CUDA_VISIBLE_DEVICES//,/ }
     arr=(${device})
     num_gpu_devices=${#arr[*]}
-    log_file=${run_log_path}/${model_name}_${run_mode}_bs${batch_size}_${fp_item}_${num_gpu_devices}
+    log_file=${run_log_path}/${model_item}_${run_mode}_bs${batch_size}_${fp_item}_${num_gpu_devices}
 }
 function _train(){
     echo "Train on ${num_gpu_devices} GPUs"
     echo "current CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES, gpus=$num_gpu_devices, batch_size=$batch_size"
 
-    train_cmd="-c configs/det/${model_name}.yml -o Train.loader.batch_size_per_card=${batch_size} Global.epoch_num=${max_iter} Global.eval_batch_step=[0,20000] Global.print_batch_step=2"   
+    train_cmd="-c configs/det/${model_item}.yml -o Train.loader.batch_size_per_card=${batch_size} Global.epoch_num=${max_epoch} Global.eval_batch_step=[0,20000] Global.print_batch_step=2"
     case ${run_mode} in
       sp) 
-        train_cmd="python3.7 tools/train.py "${train_cmd}""
+        train_cmd="python tools/train.py "${train_cmd}""
         ;;
       mp)
-        train_cmd="python3.7 -m paddle.distributed.launch --log_dir=./mylog --gpus=$CUDA_VISIBLE_DEVICES tools/train.py ${train_cmd}"
+        train_cmd="python -m paddle.distributed.launch --log_dir=./mylog --gpus=$CUDA_VISIBLE_DEVICES tools/train.py ${train_cmd}"
         ;;
       *) echo "choose run_mode(sp or mp)"; exit 1;
     esac
@@ -46,17 +54,7 @@ function _train(){
     fi
 }
 
-function _analysis_log(){
-    analysis_cmd="python3.7 benchmark/analysis.py --filename ${log_file}  --mission_name ${model_name} --run_mode ${run_mode} --direction_id 0 --keyword 'ips:' --base_batch_size ${batch_size} --skip_steps 1 --gpu_num ${num_gpu_devices}  --index 1  --model_mode=-1  --ips_unit=samples/sec"
-    eval $analysis_cmd
-}
-
-function _kill_process(){
-    kill -9 `ps -ef|grep 'python3.7'|awk '{print $2}'`
-}
-
-
+source ${BENCHMARK_ROOT}/scripts/run_model.sh      # 在该脚本中会对符合benchmark规范的log使用analysis.py 脚本进行性能数据解析;该脚本在连调时可从benchmark repo中下载https://github.com/PaddlePaddle/benchmark/blob/master/scripts/run_model.sh;如果不联调只想要产出训练log可以注掉本行,提交时需打开
 _set_params $@
-_train
-_analysis_log
-_kill_process
\ No newline at end of file
+#_train      # 如果只想产出训练log,不解析,可取消注释
+_run         # 该函数在run_model.sh中,执行时会调用_train; 如果不联调只想要产出训练log可以注掉本行,提交时需打开

benchmark/run_det.sh

+#!/bin/bash
 # 提供可稳定复现性能的脚本，默认在标准docker环境内py37执行： paddlepaddle/paddle:latest-gpu-cuda10.1-cudnn7  paddle=2.1.2  py=37
 # 执行目录: ./PaddleOCR
 # 1 安装该模型需要的依赖 (如需开启优化策略请注明)
-python3.7 -m pip install -r requirements.txt
+python -m pip install -r requirements.txt
 # 2 拷贝该模型需要数据、预训练模型
 wget -P ./train_data/  https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar && cd train_data  && tar xf icdar2015.tar && cd ../
 wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_pretrained.pdparams
@@ -17,11 +18,13 @@ for model_mode in ${model_mode_list[@]}; do
           for bs_item in ${bs_list[@]}; do
             echo "index is speed, 1gpus, begin, ${model_name}"
             run_mode=sp
-            CUDA_VISIBLE_DEVICES=0 bash benchmark/run_benchmark_det.sh ${run_mode} ${bs_item} ${fp_item} 2 ${model_mode}     #  (5min)
+            log_name=ocr_${model_mode}_${run_mode}_bs${bs_item}_${fp_item}
+            CUDA_VISIBLE_DEVICES=0 bash benchmark/run_benchmark_det.sh ${run_mode} ${bs_item} ${fp_item} 1 ${model_mode} | tee ${log_path}/${log_name}_speed_1gpus 2>&1    #  (5min)
             sleep 60
             echo "index is speed, 8gpus, run_mode is multi_process, begin, ${model_name}"
             run_mode=mp
-            CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash benchmark/run_benchmark_det.sh ${run_mode} ${bs_item} ${fp_item} 2 ${model_mode} 
+            log_name=ocr_${model_mode}_${run_mode}_bs${bs_item}_${fp_item}
+            CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash benchmark/run_benchmark_det.sh ${run_mode} ${bs_item} ${fp_item} 2 ${model_mode} | tee ${log_path}/${log_name}_speed_8gpus8p 2>&1
             sleep 60
             done
       done