我通常使用以下命令运行 TensorFlow Serving Docker 映像：
docker run -p 8500:8500 \
--mount type=bind,source=/mnt/docker/models,target=/models \
--mount type=bind,source=/mnt/docker/configs/models.config,target=/models/models.config \
-t tensorflow/serving \
--model_config_file=/models/models.config &
sleep 2m
我想从 Azure 上的 Docker Hub 部署相同的映像作为容器实例，使用az create并传递与上面相同的命令行参数
我已经多次尝试并遇到了几个错误
例如run: 1: run: docker: not found
这样做的正确方法是什么？
我发现最好的方法是通过命令行，无论是从您的操作系统终端还是从 azure 门户。docker 不能直接访问 AFAIK。
如果使用门户，请跳过此步骤
1 登录
从 OS 终端（您需要已azure cli安装）；
https://docs.microsoft.com/en-us/cli/azure/install-azure-cli?view=azure-cli-latest
az login
2 创建容器
从此时起，您可以在门户和终端中使用相同的命令。
然后你必须使用 azure 命令创建你的容器
az container create
-g {RESOURCE GROUP TO USE} // you'll need a resource group to contain the container group
-n {NAME FOR CONTAINER GROUP} // this is just a name for the container group
--image tensorflow/serving // guessing this is what you would like to mount to docker
--ip-address public //may need to access it externally at start
--ports 8500 8501 // you will need to access to REST OR gRPC or both
--cpu 1 // core count, in whole numbers
--memory 2.5 // float in GBs
--dns-name-label my-tf-server // to have a static address over the network
3 安装驱动
如果您需要安装一个 azure 文件系统来读取模型，这些将是您所需要的
--azure-file-volume-account-name {ACC NAME}
--azure-file-volume-account-key {ACC KEY} // you probably should use an env variable to make it secure
--azure-file-volume-share-name {my-file-system} // file share name to mount
--azure-file-volume-mount-path /models // path to mount to
4 自定义启动命令
这是在您需要输入自定义启动命令以加载自定义模型或配置文件的情况下
--command-line "tensorflow_model_server --port=8500 --rest_api_port=8501 --model_config_file=/models/models.config"
其余部分由 azure 自己处理 :) 有关更多信息，您可以查看此信息；
https://docs.microsoft.com/en-us/cli/azure/container?view=azure-cli-latest#az-container-start
5 更多关于 tf-serving 标志的信息
这是您可以与--command-line模型服务器的标志一起使用的标志的完整列表
usage: tensorflow_model_server
Flags:
--port=8500 int32 Port to listen on for gRPC API
--grpc_socket_path="" string If non-empty, listen to a UNIX socket for gRPC API on the given path. Can be either relative or absolute path.
--rest_api_port=0 int32 Port to listen on for HTTP/REST API. If set to zero HTTP/REST API will not be exported. This port must be different than the one specified in --port.
--rest_api_num_threads=16 int32 Number of threads for HTTP/REST API processing. If not set, will be auto set based on number of CPUs.
--rest_api_timeout_in_ms=30000 int32 Timeout for HTTP/REST API calls.
--enable_batching=false bool enable batching
--batching_parameters_file="" string If non-empty, read an ascii BatchingParameters protobuf from the supplied file name and use the contained values instead of the defaults.
--model_config_file="" string If non-empty, read an ascii ModelServerConfig protobuf from the supplied file name, and serve the models in that file. This config file can be used to specify multiple models to serve and other advanced parameters including non-default version policy. (If used, --model_name, --model_base_path are ignored.)
--model_name="default" string name of model (ignored if --model_config_file flag is set)
--model_base_path="" string path to export (ignored if --model_config_file flag is set, otherwise required)
--max_num_load_retries=5 int32 maximum number of times it retries loading a model after the first failure, before giving up. If set to 0, a load is attempted only once. Default: 5
--load_retry_interval_micros=60000000 int64 The interval, in microseconds, between each servable load retry. If set negative, it doesn't wait. Default: 1 minute
--file_system_poll_wait_seconds=1 int32 Interval in seconds between each poll of the filesystem for new model version. If set to zero poll will be exactly done once and not periodically. Setting this to negative value will disable polling entirely causing ModelServer to indefinitely wait for a new model at startup. Negative values are reserved for testing purposes only.
--flush_filesystem_caches=true bool If true (the default), filesystem caches will be flushed after the initial load of all servables, and after each subsequent individual servable reload (if the number of load threads is 1). This reduces memory consumption of the model server, at the potential cost of cache misses if model files are accessed after servables are loaded.
--tensorflow_session_parallelism=0 int64 Number of threads to use for running a Tensorflow session. Auto-configured by default.Note that this option is ignored if --platform_config_file is non-empty.
--tensorflow_intra_op_parallelism=0 int64 Number of threads to use to parallelize the executionof an individual op. Auto-configured by default.Note that this option is ignored if --platform_config_file is non-empty.
--tensorflow_inter_op_parallelism=0 int64 Controls the number of operators that can be executed simultaneously. Auto-configured by default.Note that this option is ignored if --platform_config_file is non-empty.
--ssl_config_file="" string If non-empty, read an ascii SSLConfig protobuf from the supplied file name and set up a secure gRPC channel
--platform_config_file="" string If non-empty, read an ascii PlatformConfigMap protobuf from the supplied file name, and use that platform config instead of the Tensorflow platform. (If used, --enable_batching is ignored.)
--per_process_gpu_memory_fraction=0.000000 float Fraction that each process occupies of the GPU memory space the value is between 0.0 and 1.0 (with 0.0 as the default) If 1.0, the server will allocate all the memory when the server starts, If 0.0, Tensorflow will automatically select a value.
--saved_model_tags="serve" string Comma-separated set of tags corresponding to the meta graph def to load from SavedModel.