* Use the features of MobileNet as a classifier. * @param {HTMLVideoElement || p5.Video} video - Optional. * An HTML video element or a p5.j

* classify * @param {*} _input * @param {*} _cb

* Classifies the given input and takes a callback to handle the results * @param {HTMLImageElement | HTMLCanvasElement | object | function | number

* classify * @param {*} _input * @param {*} _cb

* Load and flatten an array of arrays, an array of objects, or a string * path to a csv. * @param {string || array || object} inputData

* copy

* //////////////////////////////////////////////////////////// * Metadata prep * ////////////////////////////////////////////////////////////

* STEP 6 * Remove existing projects, then fill the db * @param {*} filledProjectList * @param {*} user

* Encodes a string based on the loaded tokenizer if the withTokenizer:true * @param {*} textString * @param {*} callback

* findEntries * recursively attempt to find the entries * or data array for the given json object * @param {*} _data

* // TODO: convert ys into strings, if the task is classification // if (this.config.architecture.task === "classification" && typeof output.ys[pr

* format all the sketches using the formatSketchForStorage()

* Generates content in a stateless manner, based on some initial text * (known as a "seed"). Returns a string. * @param {options} options - A

* @public * Get a dictionary with the tensors for all variables in the manifest. * * @return {Promise<Record<string, tf.Tensor>>}

* @public * Lazy-load the contents of the manifest.json file. * * @return {Promise<Manifest>}

* Find closest centroids to each observation and store as attribute.

* Calculate the Euclidian distance between two tensors. * @param {tf.tensor} tensor1 * @param {tf.tensor} tensor2

* getOneHotMeta * @param {*} _inputsMeta * @param {*} _dataRaw * @param {*} xsOrYs

* Find closest neighbours to each observation.

* get parts from landmarks * @param {*} result

* Load dataset, and run model. * @param {string || array || object} dataset

* loadData * @param {*} options * @param {*} callback

* MAKE * Get all the sketches from the ml5-examples repo * Get the p5 examples * Dive down into each sketch and get all the files * Format the ske

* Given an image or video, returns an array of objects containing pose * estimations using single or multi-pose detection. * @param {HTMLVid

* Scores the sentiment of given text with a value between 0 ("negative") and 1 ("positive"). * @param {String} text - string of text to predict.

* @return {Promise<handposeCore.AnnotatedPrediction[]>} an array of predictions.

* predict * @param {*} _input * @param {*} _cb

* returns the prediction as an array * @param {*} _inputs

* @return {Promise<facemeshCore.AnnotatedPrediction[]>} an array of predictions.

* predict * @param {*} _input * @param {*} _cb

* predictMultiple * @param {*} _input * @param {*} _cb

* synchronous predict * @param {*} _input