add paddle2onnx_infer chain

test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+model_name:GeneralRecognitionV2_PPLCNetV2_base
+python:python3.7
+2onnx: paddle2onnx
+--model_dir:./deploy/models/general_PPLCNetV2_base_pretrained_v1.0_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./deploy/models/general_PPLCNetV2_base_pretrained_v1.0_infer/inference.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/PP-ShiTuV2/general_PPLCNetV2_base_pretrained_v1.0_infer.tar
+inference:./python/predict_rec.py
+Global.use_onnx:True
+Global.rec_inference_model_dir:./models/general_PPLCNetV2_base_pretrained_v1.0_infer
+Global.use_gpu:False
+-c:configs/inference_rec.yaml
\ No newline at end of file

test_tipc/prepare.sh

@@ -321,6 +321,7 @@ if [[ ${MODE} = "paddle2onnx_infer" ]]; then
     inference_model_url=$(func_parser_value "${lines[10]}")
     tar_name=${inference_model_url##*/}
 
+    ${python_name} -m pip install onnx
     ${python_name} -m pip install paddle2onnx
     ${python_name} -m pip install onnxruntime
     if [[ ${model_name} =~ "GeneralRecognition" ]]; then
@@ -337,14 +338,12 @@ if [[ ${MODE} = "paddle2onnx_infer" ]]; then
         rm -rf val_list.txt
         ln -s demo_test.txt val_list.txt
         cd ../../
-        eval "wget -nc $model_url_value --no-check-certificate"
-        mv general_PPLCNet_x2_5_pretrained_v1.0.pdparams GeneralRecognition_PPLCNet_x2_5_pretrained.pdparams
     fi
     cd deploy
     mkdir models
     cd models
     wget -nc ${inference_model_url}
-    tar xf ${tar_name}
+    eval "tar -xf ${tar_name}"
     cd ../../
 fi