.TH "GCLOUD_AI\-PLATFORM_JOBS_SUBMIT_PREDICTION" 1



.SH "NAME"
.HP
gcloud ai\-platform jobs submit prediction \- start an AI Platform batch prediction job



.SH "SYNOPSIS"
.HP
\f5gcloud ai\-platform jobs submit prediction\fR \fIJOB\fR \fB\-\-data\-format\fR=\fIDATA_FORMAT\fR \fB\-\-input\-paths\fR=\fIINPUT_PATH\fR,[\fIINPUT_PATH\fR,...] \fB\-\-output\-path\fR=\fIOUTPUT_PATH\fR \fB\-\-region\fR=\fIREGION\fR (\fB\-\-model\fR=\fIMODEL\fR\ |\ \fB\-\-model\-dir\fR=\fIMODEL_DIR\fR) [\fB\-\-batch\-size\fR=\fIBATCH_SIZE\fR] [\fB\-\-labels\fR=[\fIKEY\fR=\fIVALUE\fR,...]] [\fB\-\-max\-worker\-count\fR=\fIMAX_WORKER_COUNT\fR] [\fB\-\-runtime\-version\fR=\fIRUNTIME_VERSION\fR] [\fB\-\-signature\-name\fR=\fISIGNATURE_NAME\fR] [\fB\-\-version\fR=\fIVERSION\fR] [\fIGCLOUD_WIDE_FLAG\ ...\fR]



.SH "DESCRIPTION"

Start an AI Platform batch prediction job.



.SH "POSITIONAL ARGUMENTS"

.RS 2m
.TP 2m
\fIJOB\fR

Name of the batch prediction job.


.RE
.sp

.SH "REQUIRED FLAGS"

.RS 2m
.TP 2m
\fB\-\-data\-format\fR=\fIDATA_FORMAT\fR

Data format of the input files. \fIDATA_FORMAT\fR must be one of:

.RS 2m
.TP 2m
\fBtext\fR
Text and JSON files; for text files, see
https://www.tensorflow.org/guide/datasets#consuming_text_data, for JSON files,
see
https://cloud.google.com/ai\-platform/prediction/docs/overview#batch_prediction_input_data
.TP 2m
\fBtf\-record\fR
TFRecord files; see
https://www.tensorflow.org/guide/datasets#consuming_tfrecord_data
.TP 2m
\fBtf\-record\-gzip\fR
GZIP\-compressed TFRecord files.
.RE
.sp


.TP 2m
\fB\-\-input\-paths\fR=\fIINPUT_PATH\fR,[\fIINPUT_PATH\fR,...]

Cloud Storage paths to the instances to run prediction on.

Wildcards (\f5*\fR) accepted at the \fBend\fR of a path. More than one path can
be specified if multiple file patterns are needed. For example,

.RS 2m
gs://my\-bucket/instances*,gs://my\-bucket/other\-instances1
.RE

will match any objects whose names start with \f5instances\fR in
\f5my\-bucket\fR as well as the \f5other\-instances1\fR bucket, while

.RS 2m
gs://my\-bucket/instance\-dir/*
.RE

will match any objects in the \f5instance\-dir\fR "directory" (since directories
aren't a first\-class Cloud Storage concept) of \f5my\-bucket\fR.

.TP 2m
\fB\-\-output\-path\fR=\fIOUTPUT_PATH\fR

Cloud Storage path to which to save the output. Example: gs://my\-bucket/output.

.TP 2m
\fB\-\-region\fR=\fIREGION\fR

The Compute Engine region to run the job in.

.TP 2m

Exactly one of these must be specified:


.RS 2m
.TP 2m
\fB\-\-model\fR=\fIMODEL\fR

Name of the model to use for prediction.

.TP 2m
\fB\-\-model\-dir\fR=\fIMODEL_DIR\fR

Cloud Storage location where the model files are located.


.RE
.RE
.sp

.SH "OPTIONAL FLAGS"

.RS 2m
.TP 2m
\fB\-\-batch\-size\fR=\fIBATCH_SIZE\fR

The number of records per batch. The service will buffer batch_size number of
records in memory before invoking TensorFlow. Defaults to 64 if not specified.

.TP 2m
\fB\-\-labels\fR=[\fIKEY\fR=\fIVALUE\fR,...]

List of label KEY=VALUE pairs to add.

Keys must start with a lowercase character and contain only hyphens (\f5\-\fR),
underscores (\f5_\fR), lowercase characters, and numbers. Values must contain
only hyphens (\f5\-\fR), underscores (\f5_\fR), lowercase characters, and
numbers.

.TP 2m
\fB\-\-max\-worker\-count\fR=\fIMAX_WORKER_COUNT\fR

The maximum number of workers to be used for parallel processing. Defaults to 10
if not specified.

.TP 2m
\fB\-\-runtime\-version\fR=\fIRUNTIME_VERSION\fR

AI Platform runtime version for this job. Must be specified unless
\-\-master\-image\-uri is specified instead. It is defined in documentation
along with the list of supported versions:
https://cloud.google.com/ai\-platform/prediction/docs/runtime\-version\-list

.TP 2m
\fB\-\-signature\-name\fR=\fISIGNATURE_NAME\fR

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/compat/v1/saved_model/signature_constants,
which is "serving_default". Only applies to TensorFlow models.

.TP 2m
\fB\-\-version\fR=\fIVERSION\fR

Model version to be used.

This flag may only be given if \-\-model is specified. If unspecified, the
default version of the model will be used. To list versions for a model, run

.RS 2m
$ gcloud ai\-platform versions list
.RE


.RE
.sp

.SH "GCLOUD WIDE FLAGS"

These flags are available to all commands: \-\-access\-token\-file, \-\-account,
\-\-billing\-project, \-\-configuration, \-\-flags\-file, \-\-flatten,
\-\-format, \-\-help, \-\-impersonate\-service\-account, \-\-log\-http,
\-\-project, \-\-quiet, \-\-trace\-token, \-\-user\-output\-enabled,
\-\-verbosity.

Run \fB$ gcloud help\fR for details.



.SH "NOTES"

These variants are also available:

.RS 2m
$ gcloud alpha ai\-platform jobs submit prediction
.RE

.RS 2m
$ gcloud beta ai\-platform jobs submit prediction
.RE