Merge pull request #4155 from LDOUBLEV/add_det_benchmark

add det benchmark

benchmark/run_benchmark_det.sh

+#!/usr/bin/env bash
+set -xe
+# 运行示例：CUDA_VISIBLE_DEVICES=0 bash run_benchmark.sh ${run_mode} ${bs_item} ${fp_item} 500 ${model_mode}
+# 参数说明
+function _set_params(){
+    run_mode=${1:-"sp"}          # 单卡sp|多卡mp
+    batch_size=${2:-"64"}
+    fp_item=${3:-"fp32"}        # fp32|fp16
+    max_iter=${4:-"500"}       # 可选，如果需要修改代码提前中断
+    model_name=${5:-"model_name"}
+    run_log_path=${TRAIN_LOG_DIR:-$(pwd)}  # TRAIN_LOG_DIR 后续QA设置该参数
+
+#   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}
+}
+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}
+               -o Global.epoch_num=${max_iter} "   
+    case ${run_mode} in
+      sp) 
+        train_cmd="python3.7 tools/train.py "${train_cmd}""
+        ;;
+      mp)
+        train_cmd="python3.7 -m paddle.distributed.launch --log_dir=./mylog --gpus=$CUDA_VISIBLE_DEVICES tools/train.py ${train_cmd}"
+        ;;
+      *) echo "choose run_mode(sp or mp)"; exit 1;
+    esac
+# 以下不用修改
+    timeout 15m ${train_cmd} > ${log_file} 2>&1
+    if [ $? -ne 0 ];then
+            echo -e "${model_name}, FAIL"
+        export job_fail_flag=1
+    else
+        echo -e "${model_name}, SUCCESS"
+        export job_fail_flag=0
+    fi
+    kill -9 `ps -ef|grep 'python3.7'|awk '{print $2}'`
+
+    if [ $run_mode = "mp" -a -d mylog ]; then
+        rm ${log_file}
+        cp mylog/workerlog.0 ${log_file}
+    fi
+}
+
+_set_params $@
+_train
+

benchmark/run_det.sh

+# 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：需说明
+cd 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
+# 2 拷贝该模型需要数据、预训练模型
+wget -p ./tain_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
+# 3 批量运行（如不方便批量，1，2需放到单个模型中）
+
+model_mode_list=(det_mv3_db det_r50_vd_east)
+fp_item_list=(fp32)
+bs_list=(256 128)
+for model_mode in ${model_mode_list[@]}; do
+      for fp_item in ${fp_item_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.sh ${run_mode} ${bs_item} ${fp_item} 10 ${model_mode}     #  (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.sh ${run_mode} ${bs_item} ${fp_item} 10 ${model_mode} 
+            sleep 60
+            done
+      done
+done
+
+

configs/det/det_r50_vd_east.yml

@@ -8,7 +8,7 @@ Global:
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [4000, 5000]
   cal_metric_during_train: False
-  pretrained_model: ./pretrain_models/ResNet50_vd_pretrained/
+  pretrained_model: ./pretrain_models/ResNet50_vd_pretrained
   checkpoints: 
   save_inference_dir:
   use_visualdl: False