benchmark_train.sh 8.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93
#!/bin/bash
source test_tipc/utils_func.sh

# set env
python=python
export model_branch=`git symbolic-ref HEAD 2>/dev/null | cut -d"/" -f 3`
export model_commit=$(git log|head -n1|awk '{print $2}')
export str_tmp=$(echo `pip list|grep paddlepaddle-gpu|awk -F ' ' '{print $2}'`)
export frame_version=${str_tmp%%.post*}
export frame_commit=$(echo `${python} -c "import paddle;print(paddle.version.commit)"`)

# run benchmark sh
# Usage:
# bash run_benchmark_train.sh config.txt params
# or
# bash run_benchmark_train.sh config.txt

function func_parser_params(){
    strs=$1
    IFS="="
    array=(${strs})
    tmp=${array[1]}
    echo ${tmp}
}

function func_sed_params(){
    filename=$1
    line=$2
    param_value=$3
    params=`sed -n "${line}p" $filename`
    IFS=":"
    array=(${params})
    key=${array[0]}
    new_params="${key}:${param_value}"
    IFS=";"
    cmd="sed -i '${line}s/.*/${new_params}/' '${filename}'"
    eval $cmd
}

function set_gpu_id(){
    string=$1
    _str=${string:1:6}
    IFS="C"
    arr=(${_str})
    M=${arr[0]}
    P=${arr[1]}
    gn=`expr $P - 1`
    gpu_num=`expr $gn / $M`
    seq=`seq -s "," 0 $gpu_num`
    echo $seq
}

function get_repo_name(){
    IFS=";"
    cur_dir=$(pwd)
    IFS="/"
    arr=(${cur_dir})
    echo ${arr[-1]}
}

FILENAME=$1
# copy FILENAME as new
new_filename="./test_tipc/benchmark_train.txt"
cmd=`yes|cp $FILENAME $new_filename`
FILENAME=$new_filename
# MODE must be one of ['benchmark_train']
MODE=$2
PARAMS=$3
# bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_benchmark.txt  benchmark_train dynamic_bs8_null_DP_N1C1
IFS=$'\n'
# parser params from train_benchmark.txt
dataline=`cat $FILENAME`
# parser params
IFS=$'\n'
lines=(${dataline})
model_name=$(func_parser_value "${lines[1]}")

# 获取benchmark_params所在的行数
line_num=`grep -n "train_benchmark_params" $FILENAME  | cut -d ":" -f 1`
# for train log parser
batch_size=$(func_parser_value "${lines[line_num]}")
line_num=`expr $line_num + 1`
fp_items=$(func_parser_value "${lines[line_num]}")
line_num=`expr $line_num + 1`
epoch=$(func_parser_value "${lines[line_num]}")

line_num=`expr $line_num + 1`
profile_option_key=$(func_parser_key "${lines[line_num]}")
profile_option_params=$(func_parser_value "${lines[line_num]}")
profile_option="${profile_option_key}:${profile_option_params}"

line_num=`expr $line_num + 1`
flags_value=$(func_parser_value "${lines[line_num]}")
94 95 96 97 98 99 100 101 102
if [ ${flags_value} != "null" ];then
    # set flags
    IFS=";"
    flags_list=(${flags_value})
    for _flag in ${flags_list[*]}; do
        cmd="export ${_flag}"
        eval $cmd
    done
fi
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165

# set log_name
repo_name=$(get_repo_name )
SAVE_LOG=${BENCHMARK_LOG_DIR:-$(pwd)}   # */benchmark_log
mkdir -p "${SAVE_LOG}/benchmark_log/"
status_log="${SAVE_LOG}/benchmark_log/results.log"

# The number of lines in which train params can be replaced.
line_python=3
line_gpuid=4
line_precision=6
line_epoch=7
line_batchsize=9
line_profile=13
line_eval_py=24
line_export_py=30

func_sed_params "$FILENAME" "${line_eval_py}" "null"
func_sed_params "$FILENAME" "${line_export_py}" "null"
func_sed_params "$FILENAME" "${line_python}"  "${python}"

# if params
if  [ ! -n "$PARAMS" ] ;then
    # PARAMS input is not a word.
    IFS="|"
    batch_size_list=(${batch_size})
    fp_items_list=(${fp_items})
    device_num_list=(N1C4)
    run_mode="DP"
else
    # parser params from input: modeltype_bs${bs_item}_${fp_item}_${run_mode}_${device_num}
    IFS="_"
    params_list=(${PARAMS})
    model_type=${params_list[0]}
    batch_size=${params_list[1]}
    batch_size=`echo  ${batch_size} | tr -cd "[0-9]" `
    precision=${params_list[2]}
    run_mode=${params_list[3]}
    device_num=${params_list[4]}
    IFS=";"

    if [ ${precision} = "null" ];then
        precision="fp32"
    fi

    fp_items_list=($precision)
    batch_size_list=($batch_size)
    device_num_list=($device_num)
fi

IFS="|"
for batch_size in ${batch_size_list[*]}; do
    for precision in ${fp_items_list[*]}; do
        for device_num in ${device_num_list[*]}; do
            # sed batchsize and precision
            func_sed_params "$FILENAME" "${line_precision}" "$precision"
            func_sed_params "$FILENAME" "${line_batchsize}" "$MODE=$batch_size"
            func_sed_params "$FILENAME" "${line_epoch}" "$MODE=$epoch"
            gpu_id=$(set_gpu_id $device_num)

            if [ ${#gpu_id} -le 1 ];then
                log_path="$SAVE_LOG/profiling_log"
                mkdir -p $log_path
G
gmm 已提交
166
                log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_profiling"
167 168 169 170 171 172 173 174 175 176 177 178 179 180 181
                func_sed_params "$FILENAME" "${line_gpuid}" "0"  # sed used gpu_id
                # set profile_option params
                tmp=`sed -i "${line_profile}s/.*/${profile_option}/" "${FILENAME}"`

                # run test_train_inference_python.sh
                cmd="bash test_tipc/test_train_inference_python.sh ${FILENAME} benchmark_train > ${log_path}/${log_name} 2>&1 "
                echo $cmd
                eval $cmd
                eval "cat ${log_path}/${log_name}"

                # without profile
                log_path="$SAVE_LOG/train_log"
                speed_log_path="$SAVE_LOG/index"
                mkdir -p $log_path
                mkdir -p $speed_log_path
G
gmm 已提交
182 183
                log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_log"
                speed_log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_speed"
184 185 186 187 188 189 190 191 192 193
                func_sed_params "$FILENAME" "${line_profile}" "null"  # sed profile_id as null
                cmd="bash test_tipc/test_train_inference_python.sh ${FILENAME} benchmark_train > ${log_path}/${log_name} 2>&1 "
                echo $cmd
                job_bt=`date '+%Y%m%d%H%M%S'`
                eval $cmd
                job_et=`date '+%Y%m%d%H%M%S'`
                export model_run_time=$((${job_et}-${job_bt}))
                eval "cat ${log_path}/${log_name}"

                # parser log
G
gmm 已提交
194
                _model_name="${model_name}_bs${batch_size}_${precision}_${run_mode}"
195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216
                cmd="${python} ${BENCHMARK_ROOT}/scripts/analysis.py --filename ${log_path}/${log_name} \
                        --speed_log_file '${speed_log_path}/${speed_log_name}' \
                        --model_name ${_model_name} \
                        --base_batch_size ${batch_size} \
                        --run_mode ${run_mode} \
                        --fp_item ${precision} \
                        --keyword ips: \
                        --skip_steps 2 \
                        --device_num ${device_num} \
                        --speed_unit images/s \
                        --convergence_key loss: "
                echo $cmd
                eval $cmd
                last_status=${PIPESTATUS[0]}
                status_check $last_status "${cmd}" "${status_log}"
            else
                IFS=";"
                unset_env=`unset CUDA_VISIBLE_DEVICES`
                log_path="$SAVE_LOG/train_log"
                speed_log_path="$SAVE_LOG/index"
                mkdir -p $log_path
                mkdir -p $speed_log_path
G
gmm 已提交
217 218
                log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_log"
                speed_log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_speed"
219 220 221 222 223 224 225 226 227 228
                func_sed_params "$FILENAME" "${line_gpuid}" "$gpu_id"  # sed used gpu_id
                func_sed_params "$FILENAME" "${line_profile}" "null"  # sed --profile_option as null
                cmd="bash test_tipc/test_train_inference_python.sh ${FILENAME} benchmark_train > ${log_path}/${log_name} 2>&1 "
                echo $cmd
                job_bt=`date '+%Y%m%d%H%M%S'`
                eval $cmd
                job_et=`date '+%Y%m%d%H%M%S'`
                export model_run_time=$((${job_et}-${job_bt}))
                eval "cat ${log_path}/${log_name}"
                # parser log
G
gmm 已提交
229
                _model_name="${model_name}_bs${batch_size}_${precision}_${run_mode}"
230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249

                cmd="${python} ${BENCHMARK_ROOT}/scripts/analysis.py --filename ${log_path}/${log_name} \
                        --speed_log_file '${speed_log_path}/${speed_log_name}' \
                        --model_name ${_model_name} \
                        --base_batch_size ${batch_size} \
                        --run_mode ${run_mode} \
                        --fp_item ${precision} \
                        --keyword ips: \
                        --skip_steps 2 \
                        --device_num ${device_num} \
                        --speed_unit images/s \
                        --convergence_key loss: "
                echo $cmd
                eval $cmd
                last_status=${PIPESTATUS[0]}
                status_check $last_status "${cmd}" "${status_log}"
            fi
        done
    done
done