diff --git a/deploy/slim/quantization/export_model.py b/deploy/slim/quantization/export_model.py
index 87d2f333..d94e5303 100755
--- a/deploy/slim/quantization/export_model.py
+++ b/deploy/slim/quantization/export_model.py
@@ -101,7 +101,7 @@ def main():
     quanter = QAT(config=quant_config)
     quanter.quantize(model)
 
-    init_model(config, model, logger)
+    init_model(config, model)
     model.eval()
 
     # build metric
diff --git a/test/ocr_det_params.txt b/test/ocr_det_params.txt
index da7e034b..bdfd4d4f 100644
--- a/test/ocr_det_params.txt
+++ b/test/ocr_det_params.txt
@@ -17,7 +17,7 @@ distill_train:null
 eval:tools/eval.py -c configs/det/det_mv3_db.yml -o 
 
 Global.save_inference_dir:./output/
-Global.checkpoints:
+Global.pretrained_model:
 norm_export:tools/export_model.py -c configs/det/det_mv3_db.yml -o 
 quant_export:deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o 
 fpgm_export:deploy/slim/prune/export_prune_model.py
diff --git a/test/test.sh b/test/test.sh
index a75aed42..f2ac3f8b 100644
--- a/test/test.sh
+++ b/test/test.sh
@@ -101,7 +101,7 @@ function func_inference(){
             for use_mkldnn in ${use_mkldnn_list[*]}; do
                 for threads in ${cpu_threads_list[*]}; do
                     for batch_size in ${batch_size_list[*]}; do
-                        _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}"
+                        _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log"
                         command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${cpu_threads_key}=${threads} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir}  ${save_log_key}=${_save_log_path} --benchmark=True"
                         eval $command
                         status_check $? "${command}" "${status_log}"
@@ -115,7 +115,7 @@ function func_inference(){
                         continue
                     fi
                     for batch_size in ${batch_size_list[*]}; do
-                        _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}"
+                        _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
                         command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_trt_key}=${use_trt} ${precision_key}=${precision} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir}  ${save_log_key}=${_save_log_path}  --benchmark=True"
                         eval $command
                         status_check $? "${command}" "${status_log}"
@@ -136,6 +136,7 @@ for gpu in ${gpu_list[*]}; do
         env=""
     elif [ ${#gpu} -le 1 ];then
         env="export CUDA_VISIBLE_DEVICES=${gpu}"
+        eval ${env}
     elif [ ${#gpu} -le 15 ];then
         IFS=","
         array=(${gpu})
@@ -215,9 +216,10 @@ for gpu in ${gpu_list[*]}; do
             status_check $? "${export_cmd}" "${status_log}"
 
             #run inference
-            echo $env
+            eval $env
             save_infer_path="${save_log}"
             func_inference "${python}" "${inference_py}" "${save_infer_path}" "${LOG_PATH}" "${infer_img_dir}"
+            eval "unset CUDA_VISIBLE_DEVICES"
         done
     done
 done
diff --git a/test1/table/README_ch.md b/test1/table/README_ch.md
index 03f002f9..5c3c9a28 100644
--- a/test1/table/README_ch.md
+++ b/test1/table/README_ch.md
@@ -19,7 +19,29 @@
 
 
 ### 2.1 训练
-TBD
+#### 数据准备  
+训练数据使用公开数据集[PubTabNet](https://arxiv.org/abs/1911.10683)，可以从[官网](https://github.com/ibm-aur-nlp/PubTabNet)下载。PubTabNet数据集包含约50万张表格数据的图像，以及图像对应的html格式的注释。
+
+#### 启动训练  
+*如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false*
+```shell
+# 单机单卡训练
+python3 tools/train.py -c configs/table/table_mv3.yml
+# 单机多卡训练，通过 --gpus 参数设置使用的GPU ID
+python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/table/table_mv3.yml
+```
+
+上述指令中，通过-c 选择训练使用configs/table/table_mv3.yml配置文件。有关配置文件的详细解释，请参考[链接](./config.md)。
+
+#### 断点训练
+
+如果训练程序中断，如果希望加载训练中断的模型从而恢复训练，可以通过指定Global.checkpoints指定要加载的模型路径：
+```shell
+python3 tools/train.py -c configs/table/table_mv3.yml -o Global.checkpoints=./your/trained/model
+```
+
+**注意**：`Global.checkpoints`的优先级高于`Global.pretrain_weights`的优先级，即同时指定两个参数时，优先加载`Global.checkpoints`指定的模型，如果`Global.checkpoints`指定的模型路径有误，会加载`Global.pretrain_weights`指定的模型。
+
 
 ### 2.2 评估
 先cd到PaddleOCR/ppstructure目录下
diff --git a/tools/infer/utility.py b/tools/infer/utility.py
index e464722f..bf05a0db 100755
--- a/tools/infer/utility.py
+++ b/tools/infer/utility.py
@@ -164,7 +164,7 @@ def create_predictor(args, mode, logger):
         config.enable_use_gpu(args.gpu_mem, 0)
         if args.use_tensorrt:
             config.enable_tensorrt_engine(
-                precision_mode=inference.PrecisionType.Float32,
+                precision_mode=precision,
                 max_batch_size=args.max_batch_size,
                 min_subgraph_size=args.min_subgraph_size)
             # skip the minmum trt subgraph