Skip to content

Commit

Permalink
Fix the dead links (#2934)
Browse files Browse the repository at this point in the history
  • Loading branch information
w5688414 authored Aug 1, 2022
1 parent 445ad52 commit 86a373e
Show file tree
Hide file tree
Showing 3 changed files with 2 additions and 4 deletions.
Binary file removed applications/neural_search/img/mem.png
Binary file not shown.
4 changes: 1 addition & 3 deletions applications/neural_search/recall/milvus/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -135,9 +135,7 @@ python3 embedding_insert.py
| ------------ | ------------ |
|1000万条|12min24s|

另外,Milvus提供了可视化的管理界面,可以很方便的查看数据,安装地址为[Milvus Enterprise Manager](https://zilliz.com/products/em).

![](../../img/mem.png)
另外,Milvus提供了可视化的管理界面,可以很方便的查看数据,安装地址为[Milvus Enterprise Manager](https://github.com/zilliztech/attu)


运行召回脚本:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ pip install faster_tokenizer

使用Paddle Serving做服务化部署时,需要将保存的inference模型转换为serving易于部署的模型。

用已安装的paddle_serving_client将静态图参数模型转换成serving格式。如何使用[静态图导出脚本](export_model.py)将训练后的模型转为静态图模型详见[模型静态图导出](../../README.md),模型地址--dirname根据实际填写即可。
用已安装的paddle_serving_client将静态图参数模型转换成serving格式。如何使用[静态图导出脚本](../../export_model.py)将训练后的模型转为静态图模型详见[模型静态图导出](../../README.md),模型地址--dirname根据实际填写即可。

```shell
python -m paddle_serving_client.convert --dirname ../../export --model_filename float32.pdmodel --params_filename float32.pdiparams
Expand Down

0 comments on commit 86a373e

Please sign in to comment.