Régulateur inconnu: L2 dans tensorflowjs

Question

J'ai formé un modèle en python en utilisant model

reg = 0.000001
model = Sequential()
model.add(Dense(24, activation='tanh', name='input_dense', input_shape=input_shape))
model.add(GRU(24, activation='tanh', recurrent_activation='sigmoid', return_sequences=True, kernel_regularizer=regularizers.l2(reg), recurrent_regularizer=regularizers.l2(reg), reset_after=False))
model.add(Flatten())
model.add(Dense(2, activation='softmax'))

Mais quand j'ai converti ce modèle en utilisant "tensorflowjs_converter --input_format keras" et chargé dans le navigateur, j'ai obtenu une erreur

Rejet non géré (erreur): Régulariseur inconnu: L2. Cela peut être dû à l'une des raisons suivantes:

1. Le régulariseur est défini en Python, auquel cas il doit être porté vers TensorFlow.js ou votre code JavaScript.
2. Le régulariseur personnalisé est défini en JavaScript, mais n'est pas enregistré correctement avec tf.serialization.registerClass ().

Le contenu du fichier model.json est

{
 "format": "layers-model",
 "generatedBy": "keras v2.4.0",
 "convertedBy": "TensorFlow.js Converter v2.3.0",
 "modelTopology": {
  "keras_version": "2.4.0",
  "backend": "tensorflow",
  "model_config": {
   "class_name": "Sequential",
   "config": {
    "name": "sequential",
    "layers": [
     {
      "class_name": "InputLayer",
      "config": {
       "batch_input_shape": [null, 22, 13],
       "dtype": "float32",
       "sparse": false,
       "ragged": false,
       "name": "input_dense_input"
      }
     },
     {
      "class_name": "Dense",
      "config": {
       "name": "input_dense",
       "trainable": true,
       "batch_input_shape": [null, 22, 13],
       "dtype": "float32",
       "units": 24,
       "activation": "tanh",
       "use_bias": true,
       "kernel_initializer": {
        "class_name": "GlorotUniform",
        "config": { "seed": null }
       },
       "bias_initializer": { "class_name": "Zeros", "config": {} },
       "kernel_regularizer": null,
       "bias_regularizer": null,
       "activity_regularizer": null,
       "kernel_constraint": null,
       "bias_constraint": null
      }
     },
     {
      "class_name": "GRU",
      "config": {
       "name": "gru",
       "trainable": true,
       "dtype": "float32",
       "return_sequences": true,
       "return_state": false,
       "go_backwards": false,
       "stateful": false,
       "unroll": false,
       "time_major": false,
       "units": 24,
       "activation": "tanh",
       "recurrent_activation": "sigmoid",
       "use_bias": true,
       "kernel_initializer": {
        "class_name": "GlorotUniform",
        "config": { "seed": null }
       },
       "recurrent_initializer": {
        "class_name": "Orthogonal",
        "config": { "gain": 1.0, "seed": null }
       },
       "bias_initializer": { "class_name": "Zeros", "config": {} },
       "kernel_regularizer": {
        "class_name": "L2",
        "config": { "l2": 9.999999974752427e-7 }
       },
       "recurrent_regularizer": {
        "class_name": "L2",
        "config": { "l2": 9.999999974752427e-7 }
       },
       "bias_regularizer": null,
       "activity_regularizer": null,
       "kernel_constraint": null,
       "recurrent_constraint": null,
       "bias_constraint": null,
       "dropout": 0.0,
       "recurrent_dropout": 0.0,
       "implementation": 2,
       "reset_after": false
      }
     },
     {
      "class_name": "Flatten",
      "config": {
       "name": "flatten",
       "trainable": true,
       "dtype": "float32",
       "data_format": "channels_last"
      }
     },
     {
      "class_name": "Dense",
      "config": {
       "name": "dense",
       "trainable": true,
       "dtype": "float32",
       "units": 2,
       "activation": "softmax",
       "use_bias": true,
       "kernel_initializer": {
        "class_name": "GlorotUniform",
        "config": { "seed": null }
       },
       "bias_initializer": { "class_name": "Zeros", "config": {} },
       "kernel_regularizer": null,
       "bias_regularizer": null,
       "activity_regularizer": null,
       "kernel_constraint": null,
       "bias_constraint": null
      }
     }
    ]
   }
  },
  "training_config": {
   "loss": "categorical_crossentropy",
   "metrics": ["accuracy"],
   "weighted_metrics": null,
   "loss_weights": null,
   "optimizer_config": {
    "class_name": "Nadam",
    "config": {
     "name": "Nadam",
     "learning_rate": 0.0020000000949949026,
     "decay": 0.004000000189989805,
     "beta_1": 0.8999999761581421,
     "beta_2": 0.9990000128746033,
     "epsilon": 1e-7
    }
   }
  }
 },
 "weightsManifest": [
  {
   "paths": ["group1-shard1of1.bin"],
   "weights": [
    { "name": "dense/kernel", "shape": [528, 2], "dtype": "float32" },
    { "name": "dense/bias", "shape": [2], "dtype": "float32" },
    { "name": "gru/gru_cell/kernel", "shape": [24, 72], "dtype": "float32" },
    {
     "name": "gru/gru_cell/recurrent_kernel",
     "shape": [24, 72],
     "dtype": "float32"
    },
    { "name": "gru/gru_cell/bias", "shape": [72], "dtype": "float32" },
    { "name": "input_dense/kernel", "shape": [13, 24], "dtype": "float32" },
    { "name": "input_dense/bias", "shape": [24], "dtype": "float32" }
   ]
  }
 ]
}

Answer 1

Option 1

Il n'y a pas de classes L1et L2; ce ne sont que des interfaces (plus ici )

Il existe une classe L1L2qui prendra la configuration et retournera le bon régulariseur. Vous pouvez remplacer manuellement toutes les occurrences de L2à L1L2.

Option 2

Enregistrer une classe L2

class L2 {

    static className = 'L2';

    constructor(config) {
       return tf.regularizers.l1l2(config)
    }
}
tf.serialization.registerClass(L2);

// now load the model