Question

看过this的github问题和this的stackoverflow帖子，我曾希望这可以正常工作。

好像传入环境变量MODEL_CONFIG_FILE毫无影响。我正在通过docker-compose运行此程序，但是使用docker-run也遇到了同样的问题。

错误：

I tensorflow_serving/model_servers/server.cc:82] Building single TensorFlow model file config:  model_name: model model_base_path: /models/model
I tensorflow_serving/model_servers/server_core.cc:461] Adding/updating models.
I tensorflow_serving/model_servers/server_core.cc:558]  (Re-)adding model: model
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

Dockerfile

FROM tensorflow/serving:nightly

COPY ./models/first/ /models/first
COPY ./models/second/ /models/second

COPY ./config.conf /config/config.conf

ENV MODEL_CONFIG_FILE=/config/config.conf

撰写文件

version: '3'

services:
  serving:
    build: .
    image: testing-models
    container_name: tf

配置文件

model_config_list: {
  config: {
    name:  "first",
    base_path:  "/models/first",
    model_platform: "tensorflow",
    model_version_policy: {
        all: {}
    }
  },
  config: {
    name:  "second",
    base_path:  "/models/second",
    model_platform: "tensorflow",
    model_version_policy: {
        all: {}
    }
  }
}

Answer 1

我在Windows上遇到git bash的this双斜线问题。

因此，我通过kotlin中的command将@ KrisR89提到的参数传递给了

。

新的docker-compose如下所示，并可以与提供的docker-compose一起使用：

dockerfile

Answer 2

没有名为“ MODEL_CONFIG_FILE”的docker环境变量（这是一个tensorflow / serving变量，请参阅docker image link），因此docker image仅使用默认的docker环境变量（“ MODEL_NAME = model”和“ MODEL_BASE_PATH = / models”），并在docker映像启动时运行模型“ / models / model”。在“ tensorflow / serving”启动时，应将“ config.conf”用作输入。尝试改为运行以下内容：

nmap

Answer 3

该错误是由于服务无法找到您的模型。

I tensorflow_serving/model_servers/server.cc:82] Building single TensorFlow model file config:  model_name: model model_base_path: /models/model
I tensorflow_serving/model_servers/server_core.cc:461] Adding/updating models.
I tensorflow_serving/model_servers/server_core.cc:558]  (Re-)adding model: model
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

您的docker compose文件未在容器中装载您的模型文件。因此，服务部门找不到您的模型。

version: '3'
services:
  serving:
    build: .
    image: testing-models
    container_name: tf

将模型文件从主机安装到容器。我认为您可以这样做：

version: "3"
services:
        serving:
                image: tensorflow/serving:latest
                restart: unless-stopped
                ports:
                        - 8501:8501
                volumes:
                        - ${FIRST_MODEL_PATH <HOST>}:/models/${FIRST_MODEL_NAME}
                        - ${SECOND_MODEL_PATH <HOST>}:/models/${SECOND_MODEL_NAME}
                        - <HOST PATH>/models.config:/models/models.config
                command: --model_config_file=/models/models.config

将{PATH}和{MODEL_NAME}替换为您的路径和型号名称。

models.config文件密钥versions应该设置。

model_config_list: {
  config: {
    name:  "first",
    base_path:  "/models/first",
    model_platform: "tensorflow",
    model_version_policy: {
        versions: 1
        versions: 2
    }
  },
  config: {
    name:  "second",
    base_path:  "/models/second",
    model_platform: "tensorflow",
    model_version_policy: {
        versions: 1
        versions: 2
    }
  }
}

您可以看到此serving official document

使用Docker服务多个Tensorflow模型

3 个答案: