test_train_inference_python.sh 13.6 KB
Newer Older
L
lzzyzlbb 已提交
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 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249
#!/bin/bash
source test_tipc/common_func.sh

FILENAME=$1
# MODE be one of ['lite_train_lite_infer' 'lite_train_whole_infer' 'whole_train_whole_infer', 'whole_infer']
MODE=$2

dataline=$(awk 'NR==1, NR==51{print}'  $FILENAME)

# parser params
IFS=$'\n'
lines=(${dataline})
# The training params
model_name=$(func_parser_value "${lines[1]}")
python=$(func_parser_value "${lines[2]}")
gpu_list=$(func_parser_value "${lines[3]}")

autocast_list=$(func_parser_value "${lines[5]}")
epoch_key=$(func_parser_key "${lines[6]}")
epoch_num=$(func_parser_params "${lines[6]}")
save_model_key=$(func_parser_key "${lines[7]}")
train_batch_key=$(func_parser_key "${lines[8]}")
train_batch_value=$(func_parser_params "${lines[8]}")
pretrain_model_key=$(func_parser_key "${lines[9]}")
pretrain_model_value=$(func_parser_value "${lines[9]}")
train_model_name=$(func_parser_value "${lines[10]}")
train_infer_img_dir=$(func_parser_value "${lines[11]}")
train_param_key1=$(func_parser_key "${lines[12]}")
train_param_value1=$(func_parser_value "${lines[12]}")

trainer_list=$(func_parser_value "${lines[14]}")

trainer_norm=$(func_parser_key "${lines[15]}")
norm_trainer=$(func_parser_value "${lines[15]}")

trainer_key1=$(func_parser_key "${lines[19]}")
trainer_value1=$(func_parser_value "${lines[19]}")
trainer_key2=$(func_parser_key "${lines[20]}")
trainer_value2=$(func_parser_value "${lines[20]}")

eval_py=$(func_parser_value "${lines[23]}")
eval_key1=$(func_parser_key "${lines[24]}")
eval_value1=$(func_parser_value "${lines[24]}")

save_infer_key=$(func_parser_key "${lines[27]}")
export_weight=$(func_parser_value "${lines[28]}")
norm_export=$(func_parser_value "${lines[29]}")

inference_dir=$(func_parser_value "${lines[35]}")

# parser inference model 
infer_model_dir_list=$(func_parser_value "${lines[36]}")
infer_export_list=$(func_parser_value "${lines[37]}")
infer_is_quant=$(func_parser_value "${lines[38]}")
# parser inference 
inference_py=$(func_parser_value "${lines[39]}")
use_gpu_key=$(func_parser_key "${lines[40]}")
use_gpu_list=$(func_parser_value "${lines[40]}")
use_mkldnn_key=$(func_parser_key "${lines[41]}")
use_mkldnn_list=$(func_parser_value "${lines[41]}")
cpu_threads_key=$(func_parser_key "${lines[42]}")
cpu_threads_list=$(func_parser_value "${lines[42]}")
batch_size_key=$(func_parser_key "${lines[43]}")
batch_size_list=$(func_parser_value "${lines[43]}")
use_trt_key=$(func_parser_key "${lines[44]}")
use_trt_list=$(func_parser_value "${lines[44]}")
precision_key=$(func_parser_key "${lines[45]}")
precision_list=$(func_parser_value "${lines[45]}")
infer_model_key=$(func_parser_key "${lines[46]}")
image_dir_key=$(func_parser_key "${lines[47]}")
infer_img_dir=$(func_parser_value "${lines[47]}")
save_log_key=$(func_parser_key "${lines[48]}")
infer_key1=$(func_parser_key "${lines[50]}")
infer_value1=$(func_parser_value "${lines[50]}")

LOG_PATH="./test_tipc/output"
mkdir -p ${LOG_PATH}
status_log="${LOG_PATH}/results_python.log"

function func_inference(){
    IFS='|'
    _python=$1
    _script=$2
    _model_dir=$3
    _log_path=$4
    _img_dir=$5
    _flag_quant=$6
    # inference 
    for use_gpu in ${use_gpu_list[*]}; do
        if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then
            for use_mkldnn in ${use_mkldnn_list[*]}; do
                if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then
                    continue
                fi
                for threads in ${cpu_threads_list[*]}; do
                    for batch_size in ${batch_size_list[*]}; do
                        for precision in ${precision_list[*]}; do
                            set_precision=$(func_set_params "${precision_key}" "${precision}")
                            
                            _save_log_path="${_log_path}/python_infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_precision_${precision}_batchsize_${batch_size}.log"
                            set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
                            set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
                            set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
                            set_cpu_threads=$(func_set_params "${cpu_threads_key}" "${threads}")
                            set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
                            set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}")
                            command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${set_model_dir} > ${_save_log_path} 2>&1 "
                            eval $command
                            last_status=${PIPESTATUS[0]}
                            eval "cat ${_save_log_path}"
                            status_check $last_status "${command}" "${status_log}"
                        done
                    done
                done
            done
        elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then
            for use_trt in ${use_trt_list[*]}; do
                for precision in ${precision_list[*]}; do
                    if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then
                        continue
                    fi 
                    if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
                        continue
                    fi
                    if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then
                        continue
                    fi
                    for batch_size in ${batch_size_list[*]}; do
                        _save_log_path="${_log_path}/python_infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
                        set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
                        set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
                        set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
                        set_tensorrt=$(func_set_params "${use_trt_key}" "${use_trt}")
                        set_precision=$(func_set_params "${precision_key}" "${precision}")
                        set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
                        set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}")
                        command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} ${set_infer_params1} > ${_save_log_path} 2>&1 "
                        eval $command
                        last_status=${PIPESTATUS[0]}
                        eval "cat ${_save_log_path}"
                        status_check $last_status "${command}" "${status_log}"
                        
                    done
                done
            done
        else
            echo "Does not support hardware other than CPU and GPU Currently!"
        fi
    done
}

if [ ${MODE} = "whole_infer" ]; then
    GPUID=$3
    if [ ${#GPUID} -le 0 ];then
        env=" "
    else
        env="export CUDA_VISIBLE_DEVICES=${GPUID}"
    fi
    # set CUDA_VISIBLE_DEVICES
    eval $env
    export Count=0
    IFS="|"
    infer_run_exports=(${infer_export_list})
    infer_quant_flag=(${infer_is_quant})
    for infer_model in ${infer_model_dir_list[*]}; do
        # run export
        if [ ${infer_run_exports[Count]} != "null" ];then
            save_infer_dir=$(dirname $infer_model)
            set_export_weight=$(func_set_params "${export_weight}" "${infer_model}")
            set_save_infer_key="${save_infer_key} ${save_infer_dir}"
            export_cmd="${python} ${infer_run_exports[Count]} ${set_export_weight} ${set_save_infer_key}"
            echo ${infer_run_exports[Count]} 
            echo  $export_cmd
            eval $export_cmd
            status_export=$?
            status_check $status_export "${export_cmd}" "${status_log}"
        else
            save_infer_dir=${infer_model}
        fi
        #run inference
        func_inference "${python}" "${inference_py}" "${save_infer_dir}" "${LOG_PATH}" "${infer_img_dir}"
        Count=$(($Count + 1))
    done
else
    IFS="|"
    export Count=0
    USE_GPU_KEY=(${train_use_gpu_value})
    for gpu in ${gpu_list[*]}; do
        train_use_gpu=${USE_GPU_KEY[Count]}
        Count=$(($Count + 1))
        ips=""
        if [ ${gpu} = "-1" ];then
            env=""
        elif [ ${#gpu} -le 1 ];then
            env="export CUDA_VISIBLE_DEVICES=${gpu}"
            eval ${env}
        elif [ ${#gpu} -le 15 ];then
            IFS=","
            array=(${gpu})
            env="export CUDA_VISIBLE_DEVICES=${gpu}"
            IFS="|"
        else
            IFS=";"
            array=(${gpu})
            ips=${array[0]}
            gpu=${array[1]}
            IFS="|"
            env=" "
        fi
        for autocast in ${autocast_list[*]}; do 
            if [ ${autocast} = "amp" ]; then
                set_amp_config="Global.use_amp=True Global.scale_loss=1024.0 Global.use_dynamic_loss_scaling=True"
            else
                set_amp_config=" "
            fi          
            for trainer in ${trainer_list[*]}; do 
                flag_quant=False
                run_train=${norm_trainer}
                run_export=${norm_export}
                
                if [ ${run_train} = "null" ]; then
                    continue
                fi
                set_autocast=$(func_set_params "${autocast_key}" "${autocast}")
                set_epoch=$(func_set_params "${epoch_key}" "${epoch_num}")
                set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}")
                set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}")
                set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}")
                set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${train_use_gpu}")
                if [ ${#ips} -le 26 ];then
                    save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
                    nodes=1
                else
                    IFS=","
                    ips_array=(${ips})
                    IFS="|"
                    nodes=${#ips_array[@]}
                    save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}_nodes_${nodes}"
                fi
                set_save_model=$(func_set_params "${save_model_key}" "${save_log}")
                if [ ${#gpu} -le 2 ];then  # train with cpu or single gpu
                    cmd="${python} ${run_train} ${set_use_gpu}  ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config} "
                elif [ ${#ips} -le 26 ];then  # train with multi-gpu
                    cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}"
                else     # train with multi-machine
                    cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}"
                fi
                # run train
                eval "unset CUDA_VISIBLE_DEVICES"
L
lzzyzlbb 已提交
250
                export FLAGS_cudnn_deterministic=True
L
lzzyzlbb 已提交
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
                eval $cmd
                echo $cmd
                status_check $? "${cmd}" "${status_log}"

                set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${train_model_name}")
                # save norm trained models to set pretrain for pact training and fpgm training 
                
                # run eval 
                if [ ${eval_py} != "null" ]; then
                    set_eval_params1=$(func_set_params "${eval_key1}" "${eval_value1}")
                    eval_cmd="${python} ${eval_py} ${set_eval_pretrain} ${set_use_gpu} ${set_eval_params1}" 
                    eval $eval_cmd
                    status_check $? "${eval_cmd}" "${status_log}"
                fi
                # run export model
                if [ ${run_export} != "null" ]; then 
                    # run export model
                    save_infer_path="${save_log}"
                    set_export_weight="${save_log}/${train_model_name}"
                    set_export_weight_path=$( echo ${set_export_weight})
                    set_save_infer_key="${save_infer_key} ${save_infer_path}"
                    export_cmd="${python} ${run_export}  ${set_export_weight_path} ${set_save_infer_key}"
                    eval "$export_cmd"
                    status_check $? "${export_cmd}" "${status_log}"
                    
                    #run inference
                    eval $env
                    save_infer_path="${save_log}"
                    if [ ${inference_dir} != "null" ] && [ ${inference_dir} != '##' ]; then
                        infer_model_dir="${save_infer_path}/${inference_dir}"
                    else
                        infer_model_dir=${save_infer_path}
                    fi
                    func_inference "${python}" "${inference_py}" "${infer_model_dir}" "${LOG_PATH}" "${train_infer_img_dir}" "${flag_quant}"
                    
                    eval "unset CUDA_VISIBLE_DEVICES"
                fi
            done  # done with:    for trainer in ${trainer_list[*]}; do 
        done      # done with:    for autocast in ${autocast_list[*]}; do 
    done          # done with:    for gpu in ${gpu_list[*]}; do
fi  # end if [ ${MODE} = "infer" ]; then