Page Comparison

This is the command line tool from das-element for .

It contains the API (supporting Python 2 & 3) and the classification of image, sequence and movie files.

Tip
You can deploy it on your render farm to use it in a post-render process for labeling tagging of elements

Versions

There are two command line tool (CLI) versions with a different range of features and file size.

...

Table of Contents

How To

...

language	bash

...

cli

This version is optimized to receive data from the database or update an element.
Smaller in file size and fast to use, but has a reduced set of features.

Code Block

  get-categories                 Get all categories of the library
  get-category                   Get category entity
  get-element-by-id              Get element entity from element ID
  get-element-by-name            Get element entity from element name
  get-element-by-uuid            Get element entity from element UUID
  get-elements                   Get all elements of the library
  get-libraries                  Get all libraries data for current config
  get-library-template-mappings  Get all library template mappings
  get-tag                        Get tag entity
  get-tags                       Get all tags of the library
  license                        Show license
  update                         Updates database entity

cli_full

Includes all features of the CLI, like ingesting files, rendering proxies or running a machine learning model.
This version has larger in file size and is slower.

Code Block

  delete-element                 Delete element
  get-categories                 Get all categories of the library
  get-category                   Get category entity
  get-element-by-id              Get element entity from element ID
  get-element-by-name            Get element entity from element name
  get-element-by-uuid            Get element entity from element UUID
  get-elements                   Get all elements of the library
  get-libraries                  Get all libraries data for current config
  get-library-template-mappings  Get all library template mappings
  get-meaningful-frame           Validate meaningful thumbnail frame number
  get-paths-from-disk            Get all file paths from a given folder.
  get-tag                        Get tag entity
  get-tags                       Get all tags of the library
  info                           Show machine learning model info
  ingest                         Ingest new element
  license                        Show license
  predict                        Predict the category for a give file path.
  render-element-proxies         Render the proxy files for an element...
  update                         Updates database entity

...

Installation

Save the software to your preferred location. That’s all!

On Linux make sure to run this command to make the file executable:

Code Block
chmod +x das-element-cli_{version}_lin

API

To learn more about the application programming interface (API) follow this link here.

Documentation

docu.api.das-element.com

Python API

https://github.com/das-element/python-api

How To machine learning prediction

Info
Each version will be shipped with the model inside. Use the `info` flag to get the version number

Simple usage

Code Block

language	bash

das-element-cli.exe {file}

Code Block

language	bash

# Linux & Mac
das-element-cli predict /path/to/file.#.exr

# Windows
C:\das-element-cli.exe predict C:\path\to\file.#.exr

# result:
{"/path/to/file.#.exr": [{"labeltag": "fire", "description": "rapid oxidation of a material", "value": "Q3196"}]}

Info

Valid file paths are …

single file (single image or movie file):
- /path/to/file.exr
- /path/to/file.mov
sequence of files
- /path/to/sequence.#.exr
- /path/to/sequence.%04d.exr
directory
- the software will crawl the folder structure to find any media files or sequences

Multiple files

You can pass multiple file paths to the software.
classifier

Code Block

language	bash

das-element-cli.exe predict {file1} {file2} {file3}

Code Block

language	bash

classifierdas-element-cli.exe predict /path/to/files.#.exr /path/to/another/file.mov

# result:
{"/path/to/files.#.exr": [{"labeltag": "fire", "description": "rapid oxidation of a material", "value": "Q3196"}],
"/path/to/another/file.mov": [{"labeltag": "torch", "description": "stick with a flaming end used as a source of light", "value": "Q327954"}]}

Multiple results

Get the top X predicted categories by using the flag: --top {number}

Code Block

language	powershell

classifierdas-element-cli.exe predict --top 3 /path/to/file.mov

# result:
{"/path/to/file.mov": [
      {"labeltag": "torch", "description": "stick with a flaming end used as a source of light", "value": "Q327954"},
      {"labeltag": "fire", "description": "rapid oxidation of a material", "value": "Q3196"},
      {"labeltag": "flame", "description": "visible, gaseous part of a fire", "value": "Q235544"}
]}

Python Example

Here is an example code snippet that you could use in your python code.

Code Block

language	py

# print the top 3 labeltag predictions for a given file path

import json
import subprocess

path = '/path/to/file.mov'
command = ['./classifierdas-element-cli.exe', 'predict', '--top', '3', path]
process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
output, error = process.communicate()

if process.returncode != 0:
    print('Something went wrong: {} - Error: {}'.format(path, error))
else:
    result = json.loads(output)
    for path, predictions in result.items():
        wikidata_ids = [item['value'] for item in  predictions]  # list of IDs from wikidata
        readable_labelstags = [item['labeltag'] for item in predictions]  # list of human readable labelstags
        print('For path: "{}" predicted the labels:tags {}'.format(path, ', '.join(readable_labelstags)))

# result:
# For path: "/path/to/file.mov" predicted the labelstags: torch, flame, fire

Software info

Get information about the current software version and the categories that can be classified.

Code Block

language	bash

das-element-cli.exe info

key	description
`id`	the identifier for the class from Wikidata
`human-readable`	meaningful readable tag
`synonym`	a list of different words for this class

Result Format

For each file path you get an a list of predictions for labelstags.

Info
The result is in JSON format. The default string format is Unicode. File path gets returned as PosixPath with forwards slash, even for Windows.

Code Block

language	json

{'/path/to/file.mov': [{
                          'value': 'Q327954',
                          'labeltag': 'torch',
                          'description': 'stick with a flaming end used as a source of light'
                          'parents': "parents": [{'id': 'Q3196', 'name': 'fire'}, {'id': 'Q235544', 'name': 'flame'}]
                        }]}

key	description
`value`	identifier value - see here for more details

label

`tag`	human readable text of this category
`description`	description text for this category
`parents`	the parent tags based on the category hierarchy structure

Flags for prediction

These are the flags that can be set for the prediction.

flag	description

--

info

Shows information of the software.
List all categories that this version of the model can classify.

id - the identifier for the class from Wikidata
human-readable - readable label
synonym - a list of different words for this class

--top {number}

Get the top X predictions of labels

--debug

debugging mode

predict --top {number}

Get the top X predictions of tags.

Info
The first two predictions are probably the most significant ones.

predict --model

File path to another model file (.wit)
Each version will be shipped with a model file inside the executable

predict --filmstrip_frames

Set the number of frames of a filmstrip for a sequence of images or movie files.
default value: 36

higher value: takes longer, but this might give you more different tags
lower value: faster, but might return less tags

Info
Example: for a sequence of 1000 frames only a number of frames get validated. This helps to speed up the process and still gets you a good result.

Troubleshooting

issue	solution
MacOS shows unidentified developer for 'ffprobe'	For MacOS you should add the ffprobe to your trusted applications if you want to use the software. We use the ffmpeg and ffprobe build from MacOS from the following source: https://evermeet.cx/ffmpeg/
Windows startup is quite slow	Unfortunately that is an issue with Window that can not be fixed at the moment.

Version	Old Version 15	New Version Current
Changes made by	Jonas Kluger	Jonas Kluger
Saved on	Jan 24, 2021	May 10, 2024

Versions Compared

Key

Versions

How To

cli

cli_full

Installation

API

Documentation

Python API

How To machine learning prediction

Simple usage

Multiple files

Multiple results

Python Example

Software info

Result Format

Flags for prediction

Troubleshooting