Función Tensorflow.js tf.io.removeModel()

Tensorflow.js es una biblioteca de código abierto desarrollada por Google para ejecutar modelos de aprendizaje automático, así como redes neuronales de aprendizaje profundo en el entorno del navegador o del Node.

La función .removeModel() se usa para eliminar un modelo establecido por medio de una URL proporcionada desde un medio de depósito grabado.

Sintaxis:

tf.io.removeModel(url)

Parámetros:  

• url: es la URL indicada dentro de un modelo grabado, junto con un prefijo de patrón, es decir, ‘localstorage://my-mode-2’, ‘indexeddb://my/mode/3’. Es de tipo string.

Valor devuelto: Devuelve Promesa de ModelArtifactsInfo .

Ejemplo 1: Uso de «logSigmoid» como activación, «Almacenamiento local» como medio de almacenamiento.

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Creating model
const mymodel = tf.sequential();
 
// Calling add() method
mymodel.add(tf.layers.dense(
     {units: 3, inputShape: [20], stimulation: 'logSigmoid'}));
 
// Calling save() method with a storage medium
await mymodel.save('localstorage://display/command/mymodel1');
 
// Calling removeModel() method
await tf.io.removeModel('localstorage://display/command/mymodel1');
 
// Calling listModels() method and
// Printing output
console.log(await tf.io.listModels());

Producción: 

{
  "localstorage://demo/manage/model1": {
    "dateSaved": "2021-06-24T11:53:05.626Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "localstorage://demo/management/model1": {
    "dateSaved": "2021-06-24T11:52:29.368Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 611,
    "weightSpecsBytes": 124,
    "weightDataBytes": 44
  },
  "localstorage://demo/management/model2": {
    "dateSaved": "2021-06-24T11:53:33.384Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "localstorage://demo/management/model": {
    "dateSaved": "2021-06-24T11:53:26.006Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "localstorage://display/command/mymodel2": {
    "dateSaved": "2021-06-24T19:02:03.367Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 612,
    "weightSpecsBytes": 125,
    "weightDataBytes": 32
  },
  "indexeddb://demo/management/model1": {
    "dateSaved": "2021-06-24T13:02:20.265Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 614,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "indexeddb://display/command/mymodel": {
    "dateSaved": "2021-06-24T18:50:50.602Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 252
  },
  "indexeddb://display/command/mymodel1": {
    "dateSaved": "2021-06-24T18:59:17.435Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 612,
    "weightSpecsBytes": 125,
    "weightDataBytes": 32
  },
  "indexeddb://example/command/mymodel": {
    "dateSaved": "2021-06-24T12:33:06.208Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 1428
  }
}

Ejemplo 2: usar «prelu» como activación, «IndexedDB» como medio de almacenamiento y «JSON.stringify» para devolver la salida en formato de string.

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Creating model
const mymodel = tf.sequential();
 
// Calling add() method
mymodel.add(tf.layers.dense(
     {units: 11, inputShape: [6], stimulation: 'prelu'}));
 
// Calling save() method with a storage medium
await mymodel.save('indexeddb://display/command/mymodel1');
 
// Calling removeModel() method
await tf.io.removeModel('indexeddb://display/command/mymodel1');
 
// Calling listModels() method and
// Printing output
console.log(JSON.stringify(await tf.io.listModels()));

Producción: 

{
  "localstorage://demo/manage/model1": {
    "dateSaved": "2021-06-24T11:53:05.626Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "localstorage://demo/management/model1": {
    "dateSaved": "2021-06-24T11:52:29.368Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 611,
    "weightSpecsBytes": 124,
    "weightDataBytes": 44
  },
  "localstorage://demo/management/model2": {
    "dateSaved": "2021-06-24T11:53:33.384Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "localstorage://demo/management/model": {
    "dateSaved": "2021-06-24T11:53:26.006Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "localstorage://display/command/mymodel2": {
    "dateSaved": "2021-06-24T19:02:03.367Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 612,
    "weightSpecsBytes": 125,
    "weightDataBytes": 32
  },
  "indexeddb://demo/management/model1": {
    "dateSaved": "2021-06-24T13:02:20.265Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 614,
    "weightSpecsBytes": 126,
    "weightDataBytes": 44
  },
  "indexeddb://display/command/mymodel": {
    "dateSaved": "2021-06-24T18:50:50.602Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 252
  },
  "indexeddb://example/command/mymodel": {
    "dateSaved": "2021-06-24T12:33:06.208Z",
    "modelTopologyType": "JSON",
    "modelTopologyBytes": 613,
    "weightSpecsBytes": 126,
    "weightDataBytes": 1428
  }
}

Referencia: https://js.tensorflow.org/api/latest/#io.removeModel