#!/bin/bash

dataline=$(cat ${FILENAME})
# parser params
IFS=$'\n'
lines=(${dataline})
function func_parser(){
    strs=$1
    IFS=":"
    array=(${strs})
    tmp=${array[1]}
    echo ${tmp}
}
IFS=$'\n'
# The training params
train_model_list=$(func_parser "${lines[0]}")
gpu_list=$(func_parser "${lines[1]}")
auto_cast_list=$(func_parser "${lines[2]}")
slim_trainer_list=$(func_parser "${lines[3]}")
python=$(func_parser "${lines[4]}")
# inference params
inference=$(func_parser "${lines[5]}")
devices=$(func_parser "${lines[6]}")
use_mkldnn_list=$(func_parser "${lines[7]}")
cpu_threads_list=$(func_parser "${lines[8]}")
rec_batch_size_list=$(func_parser "${lines[9]}")
gpu_trt_list=$(func_parser "${lines[10]}")
gpu_precision_list=$(func_parser "${lines[11]}")


for train_model in ${train_model_list[*]}; do 
    if [ ${train_model} = "det" ];then
        model_name="det"
        yml_file="configs/det/det_mv3_db.yml"
        img_dir=""
    elif [ ${train_model} = "rec" ];then
        model_name="rec"
        yml_file="configs/rec/rec_mv3_none_bilstm_ctc.yml"
        img_dir=""
    fi

    # eval 
    for slim_trainer in ${slim_trainer_list[*]}; do 
        if [ ${slim_trainer} = "norm" ]; then
            if [ ${model_name} = "model_name" ]; then
                eval_model_name="ch_ppocr_mobile_v2.0_det_infer"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar
            else 
                eval_model_name="ch_ppocr_mobile_v2.0_rec_infer"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar
            fi 
        elif [ ${slim_trainer} = "quant" ]; then
            if [ ${model_name} = "model_name" ]; then
                eval_model_name="ch_ppocr_mobile_v2.0_det_quant_infer"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_quant_train.tar
            else
                eval_model_name="ch_ppocr_mobile_v2.0_rec_quant_infer"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_quant_train.tar
            fi 
        elif [ ${slim_trainer} = "distill" ]; then
            if [ ${model_name} = "model_name" ]; then
                eval_model_name="ch_ppocr_mobile_v2.0_det_distill_infer"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_distill_train.tar
            else
                eval_model_name="ch_ppocr_mobile_v2.0_rec_distill_infer"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_distill_train.tar
            fi 
        elif [ ${slim_trainer} = "prune" ]; then
            if [ ${model_name} = "model_name" ]; then
                eval_model_name="ch_ppocr_mobile_v2.0_det_prune_train"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_train.tar
            else
                eval_model_name="ch_ppocr_mobile_v2.0_rec_prune_train"
                wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_prune_train.tar
            fi
        fi

    echo ${python} tools/eval.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_model_dir=${log_path}/${model_name}
    echo ${python} tools/export_model.py -c ${yml_file} -o Global.pretrained_model=${eval_model_name} Global.save_inference_dir=${log_path}/${eval_model_name}_infer
    if [ $? -eq 0 ]; then
        echo -e "\033[33m training of $model_name successfully!\033[0m" | tee -a ${save_log}/train.log
    else
        cat ${save_log}/train.log
        echo -e "\033[33m training of $model_name failed!\033[0m" | tee -a ${save_log}/train.log
    fi
    if [ "${model_name}" = "det" ]; then 
        export rec_batch_size_list=( "1" )
        inference="tools/infer/predict_det.py"
        det_model_dir=${log_path}/${eval_model_name}_infer
        rec_model_dir=""
    elif [ "${model_name}" = "rec" ]; then
        inference="tools/infer/predict_rec.py"
        rec_model_dir=${log_path}/${eval_model_name}_infer
        det_model_dir=""
    fi
    # inference 
    for device in ${devices[*]}; do 
        if [ ${device} = "cpu" ]; then
            for use_mkldnn in ${use_mkldnn_list[*]}; do
                for threads in ${cpu_threads_list[*]}; do
                    for rec_batch_size in ${rec_batch_size_list[*]}; do    
                        echo ${python} ${inference} --enable_mkldnn=${use_mkldnn} --use_gpu=False --cpu_threads=${threads} --benchmark=True --det_model_dir=${det_model_dir} --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir}  --image_dir=${img_dir}  --save_log_path=${log_path}/${model_name}_${slim_trainer}_cpu_usemkldnn_${use_mkldnn}_cputhreads_${threads}_recbatchnum_${rec_batch_size}_infer.log
                        # ${python} ${inference} --enable_mkldnn=${use_mkldnn} --use_gpu=False --cpu_threads=${threads} --benchmark=True --det_model_dir=${save_log}/export_inference/ --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir}  --image_dir=${img_dir}  2>&1 | tee ${log_path}/${model_name}_${slim_trainer}_cpu_usemkldnn_${use_mkldnn}_cputhreads_${threads}_recbatchnum_${rec_batch_size}_infer.log
                    done
                done
            done
        else 
            for use_trt in ${gpu_trt_list[*]}; do
                for precision in ${gpu_precision_list[*]}; do
                    if [ ${use_trt} = "False" ] && [ ${precision} != "fp32" ]; then
                        continue
                    fi
                    for rec_batch_size in ${rec_batch_size_list[*]}; do
                        # echo "${model_name}  ${det_model_dir} ${rec_model_dir}, use_trt: ${use_trt}   use_fp16: ${use_fp16}"
                        echo ${python} ${inference} --use_gpu=True --use_tensorrt=${use_trt}  --precision=${precision} --benchmark=True --det_model_dir=${log_path}/${eval_model_name}_infer --rec_batch_num=${rec_batch_size} --rec_model_dir=${rec_model_dir} --image_dir=${img_dir} --save_log_path=${log_path}/${model_name}_${slim_trainer}_gpu_usetensorrt_${use_trt}_usefp16_${precision}_recbatchnum_${rec_batch_size}_infer.log
                    done
                done
            done
        fi
    done
done