TensorFlow通过docker提供多种型号

Question

我无法通过TensorFlow在Windows 10计算机上通过docker运行2个或更多模型。

我做了一个models.config文件

model_config_list: {

config: {
    name: "ukpred2",
    base_path: "/models/my_models/ukpred2",
    model_platform: "tensorflow"
    },
config: {
    name: "model3",
    base_path: "/models/my_models/ukpred3",
    model_platform: "tensorflow"
    }
}

docker run -p 8501:8501 --mount type=bind,source=C:\Users\th3182\Documents\temp\models\,target=/models/my_models --mount type=bind,source=C:\Users\th3182\Documents\temp\models.config,target=/models/models.config -t tensorflow/serving --model_config_file=/models/models.config

在C:\Users\th3182\Documents\temp\models是2个文件夹ukpred2和ukpred3在这些文件夹中是从训练模型导出的文件夹，即1536668276，其中包含assets文件夹，variables文件夹和saved_model.ph文件。

我得到的错误是

2018-09-13 15:24:50.567686: I tensorflow_serving/model_servers/main.cc:157] Building single TensorFlow model file config:  model_name: model model_base_path: /models/model
2018-09-13 15:24:50.568209: I tensorflow_serving/model_servers/server_core.cc:462] Adding/updating models.
2018-09-13 15:24:50.568242: I tensorflow_serving/model_servers/server_core.cc:517]  (Re-)adding model: model
2018-09-13 15:24:50.568640: E tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:369] FileSystemStoragePathSource encountered a file-system access error: Could not find base path /models/model for servable model

我似乎无法通过上述改动来解决这个问题。但是我已经设法使用以下命令为单个模型服务

docker run -p 8501:8501 --mount type=bind,source=C:\Users\th3182\Documents\projects\Better_Buyer2\model2\export\exporter,target=/models/model2 -e MODEL_NAME=model2 -t tensorflow/serving

Answer 1

您必须等待下一个版本（1.11.0）才能生效。在此期间，您可以使用image tensorflow / serving：nightly或tensorflow / serving：1.11.0-rc0