.TH "DLMODEL_SOURCE" "1" "October 2017" "DLMobelBox" "User Commands"

.SH NAME
dlmodel_source \- create a structured deep learning model directory

.SH SYNOPSIS
.B dlmodel_source

.SH DESCRIPTION
.PP
.B dlmodel_source
helps to create a structured deep learning (DL) model directory via CLI. Please refer to the specification section below for more details.
.PP
The structured directory will be created in /tmp.
.PP
Questions for collecting model information:
.TP
.RB "Package name"
The name of the DL package, e.g. inception.
.TP
.RB "Package version"
The version of the DL package, e.g. 3.
.TP
.RB "Modle filepath"
Absolute or relative path of the model file.
.TP
.RB "Label filepath"
Absolute or relative path of the label file.
.TP
.RB "Config name"
Name of the config data source (see config filepath below). If there is not any config, leave it blank.
.TP
.RB "Config filepath"
Absolute or relative path of the config file.
.TP
.RB "Inference engine"
The inference engine supporting the DL model's format.

.SH MODEL DIRECTORY STRUCTURE
.PP
Example of a structured DL model directory:
.sp
.nf
    <modelname-version>
    |-- <model-file>
    |-- <label-file>
    |-- <optional-config-files>
    |-- LICENSE    # optional currently
    `-- meta.json
.fi

.SH METADATA FORMAT OF MODEL PACKAGE
.PP
Metadata, meta.json, describes all the details in the structured model directory.
.PP
Example of meta.json
.sp
.nf
    # Note: model directory name is fight-detection-1.0.0
    {
        "name": "fight-detection",
        "version": "1.0.0",
        "inference-engine": "tensorflow",
        "model": "model.pb",
        "label": "labels.txt",
        # optional configs
        "config": {
            "<optional-key>": "<optional-value>",
            "<optional-key>": "<optional-value>",
            ...
        },
        "checksums-sha256": {
            "model.pb": "<sha256sum>",
            "labels.txt": "<sha256sum>",
            "<optional-file-path>": "<sha256sum>",
            ...
        }
    }
.fi

.SH SEE ALSO
.PP
.BR dlmodel2deb (1)