* Applies the model to the manually entered hand value and updates the UI with * the model's prediction.

* Remove the locally saved model from IndexedDB.

* Finds and removes all of the text predictions added by this extension, and * removes them from the DOM. Note: This does not undo the containerizati

* Render the latent space by z vectors through the VAE and rendering * the result. * * Handles only 2D latent spaces

* Train a model with dataset, then save the model to a local folder.

* Run the model in case of image detection, and return detector results.

* Save the model to IndexedDB.

* Save the model in IndexedDB. * * @returns ModelInfo from the saving, if the saving succeeds.

* Scale the gradient values using normalized reward values and compute average. * * The gradient values are scaled by the normalized reward values.

Create a Keras model for the seq2seq translation. Args: num_encoder_tokens: Total number of distinct tokens in the inputs to the encoder. num

Create a Keras model for the seq2seq translation. Args: num_encoder_tokens: Total number of distinct tokens in the inputs to the encoder.

* Loads the pretrained model and metadata, and registers the predict * and retrain functions with the UI.

* Loads the pretrained model and metadata, and registers the predict * function with the UI.

* Loads the pretrained model and metadata, and registers the translation * function with the UI.

* Show predictions on a number of test examples. * * @param {tf.Model} model The model to be used for making the predictions.

* Get a slice of the training text data. * * @param {number} startIndex * @param {number} endIndex * @param {bool} useIndices Whether to r

* Calculate the standard deviation of a vector. * * @param {Array} vector The vector represented as an Array of Numbers. * * @returns {number} The

* Play a game for one step. * * - Use the current best action to forward one step in the game. * - Accumulate to the cumulative reward. * - Determ

* On click on a test image.

* Produces a short text string summarizing the prediction * Input prediction should be a list of {className: string, prediction: float} * objects.

* Get length of the training text data. * * @returns {number} Length of training text data.

* Split an input string into tokens, we use the same tokenization function * as we did during training. * @param {string} input * * @return {strin

* Compile and train the given model. * * @param {tf.Model} model The model to train. * @param {onIterationCallback} onIteration A callback to execu

* Sets up and trains the classifier.

* Train the auto encoder * * @param {number[][]} images Flattened images for VAE training. * @param {object} vaeOpts Options for the VAE model, inc

Train a Keras model for Iris data classification and save result as JSON. Args: epochs: Number of epochs to traing the Keras model for. art

* Train the combined ACGAN for one step. * * In this step, only the weights of the generator are updated. * * @param {number} batchSize Size of th

* Train the discriminator for one step. * * In this step, only the weights of the discriminator are updated. The * generator is not involved. * *

* Train a `tf.Model` to recognize Iris flower type. * * @param trainDataset A tf.Dataset object yielding features and targets. The * features mus

* Train a `tf.Model` to recognize Iris flower type. * * @param xTrain Training feature data, a `tf.Tensor` of shape * [numTrainExamples, 4]. The

* Trains a the provided model on the provided dataset using model.fitDataset. * Schedules a callback at the end of every epoch to update the UI with