未验证 提交 187b171c 编写于 作者: B Bin Lu 提交者: GitHub

Merge pull request #1663 from Intsigstephon/fix_release_cpp_serving_bug

[cherry-pick]fix cpp serving bug
......@@ -52,7 +52,7 @@ python3.7 python/predict_cls.py \
-c configs/inference_cls.yaml \
-o Global.use_onnx=True \
-o Global.use_gpu=False \
-o Global.inference_model_dir=./models/ResNet50_vd_infer \
-o Global.inference_model_dir=./models/ResNet50_vd_infer
```
结果如下:
......
......@@ -189,7 +189,7 @@ python3 -m paddle_serving_client.convert --dirname ./general_PPLCNet_x2_5_lite_v
--serving_server ./general_PPLCNet_x2_5_lite_v1.0_serving/ \
--serving_client ./general_PPLCNet_x2_5_lite_v1.0_client/
```
识别推理模型转换完成后,会在当前文件夹多出 `general_PPLCNet_x2_5_lite_v1.0_serving/``general_PPLCNet_x2_5_lite_v1.0_serving/` 的文件夹。分别修改 `general_PPLCNet_x2_5_lite_v1.0_serving/``general_PPLCNet_x2_5_lite_v1.0_client/` 目录下的 serving_server_conf.prototxt 中的 alias 名字: 将 `fetch_var` 中的 `alias_name` 改为 `features`
识别推理模型转换完成后,会在当前文件夹多出 `general_PPLCNet_x2_5_lite_v1.0_serving/``general_PPLCNet_x2_5_lite_v1.0_client/` 的文件夹。分别修改 `general_PPLCNet_x2_5_lite_v1.0_serving/``general_PPLCNet_x2_5_lite_v1.0_client/` 目录下的 serving_server_conf.prototxt 中的 alias 名字: 将 `fetch_var` 中的 `alias_name` 改为 `features`
修改后的 serving_server_conf.prototxt 内容如下:
```
feed_var {
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册