gcloud beta ai-platform local predict

NAME
gcloud beta ai-platform local predict - run prediction locally
SYNOPSIS
gcloud beta ai-platform local predict --model-dir=MODEL_DIR (--json-instances=JSON_INSTANCES     | --json-request=JSON_REQUEST     | --text-instances=TEXT_INSTANCES) [--framework=FRAMEWORK] [--signature-name=SIGNATURE_NAME] [GCLOUD_WIDE_FLAG]
DESCRIPTION
(BETA) gcloud beta ai-platform local predict performs prediction locally with the given instances. It requires the TensorFlow SDK be installed locally. The output format mirrors gcloud ai-platform predict (online prediction).

You cannot use this command with custom prediction routines.

REQUIRED FLAGS
--model-dir=MODEL_DIR
Path to the model.
Exactly one of these must be specified:
--json-instances=JSON_INSTANCES
Path to a local file from which instances are read. Instances are in JSON format; newline delimited.

An example of the JSON instances file:

  {"images": [0.0, …, 0.1], "key": 3}
  {"images": [0.0, …, 0.1], "key": 2}
  …

This flag accepts "-" for stdin.

--json-request=JSON_REQUEST
Path to a local file containing the body of JSON request.

An example of a JSON request:

  {
    "instances": [
      {"x": [1, 2], "y": [3, 4]},
      {"x": [-1, -2], "y": [-3, -4]}
    ]
  }

This flag accepts "-" for stdin.

--text-instances=TEXT_INSTANCES
Path to a local file from which instances are read. Instances are in UTF-8 encoded text format; newline delimited.

An example of the text instances file:

  107,4.9,2.5,4.5,1.7
  100,5.7,2.8,4.1,1.3
  …

This flag accepts "-" for stdin.

OPTIONAL FLAGS
--framework=FRAMEWORK
The ML framework used to train this version of the model. If not specified, defaults to 'tensorflow'. FRAMEWORK must be one of: scikit-learn, tensorflow, xgboost.
--signature-name=SIGNATURE_NAME
The name of the signature defined in the SavedModel to use for this job. Defaults to DEFAULT_SERVING_SIGNATURE_DEF_KEY in https://www.tensorflow.org/api_docs/python/tf/saved_model/signature_constants, which is "serving_default". Only applies to TensorFlow models.
GCLOUD WIDE FLAGS
These flags are available to all commands: --account, --billing-project, --configuration, --flags-file, --flatten, --format, --help, --impersonate-service-account, --log-http, --project, --quiet, --trace-token, --user-output-enabled, --verbosity.

Run $ gcloud help for details.

NOTES
This command is currently in BETA and may change without notice. These variants are also available:
gcloud ai-platform local predict
gcloud alpha ai-platform local predict