运行docker容器错误：找不到可服务模型的基本路径/ models / model

Question

当我尝试使用docker映像运行docker容器时出现问题：tensorflow / serving。

1. 我运行cmd：

docker run --name=tf_serving -it tensorflow/serving

2. 结果是：

2019-10-28 04:23:56.858540: I tensorflow_serving/model_servers/server_core.cc:462] Adding/updating models.
2019-10-28 04:23:56.858571: I tensorflow_serving/model_servers/server_core.cc:573]  (Re-)adding model: model
2019-10-28 04:23:56.858852: E tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:362] FileSystemStoragePathSource encountered a filesystem access error: Could not find base path /models/model for servable model

I've digging to resolve it but still there. Could anyone please have any idea for this, thanks so much!

Answer 1

您应提供保存的模型路径。服务容器将在其/models目录中找到所有模型。您可以将-v用于docker run命令。这样做：

docker run --name=tf_serving -it -v /path/to/saved_model:/models/saved_model tensorflow/serving