- written in javascript - Use with tensorflow.js as a replacement to your python hyperparameters library
- use from cdn or npm - Link hpjs in your html file from a cdn, or install in your project with npm
- versatile - Utilize multiple parameters and multiple search algorithms (grid search, random, bayesian)
$ npm install hyperparameters import * as hpjs from 'hyperparameters'; - Randomly returns one of the options
- Return a random integer in the range [0, upper)
- Returns a single value uniformly between
lowandhighi.e. any value betweenlowandhighhas an equal probability of being selected
- returns a quantized value of
hp.uniformcalculated asround(uniform(low, high) / q) * q
- Returns a value
exp(uniform(low, high))so the logarithm of the return value is uniformly distributed.
- Returns a value
round(exp(uniform(low, high)) / q) * q
- Returns a real number that's normally-distributed with mean mu and standard deviation sigma
- Returns a value
round(normal(mu, sigma) / q) * q
- Returns a value
exp(normal(mu, sigma))
- Returns a value
round(exp(normal(mu, sigma)) / q) * q
import { RandomState } from 'hyperparameters'; example:
const rng = new RandomState(12345); console.log(rng.randrange(0, 5, 0.5)); import { sample } from 'hyperparameters'; example:
import * as hpjs from 'hyperparameters'; const space = { x: hpjs.normal(0, 2), y: hpjs.uniform(0, 1), choice: hpjs.choice([ undefined, hp.uniform('float', 0, 1), ]), array: [ hpjs.normal(0, 2), hpjs.uniform(0, 3), hpjs.choice([false, true]), ], obj: { u: hpjs.uniform(0, 3), v: hpjs.uniform(0, 3), w: hpjs.uniform(-3, 0) } }; console.log(hpjs.sample.randomSample(space)); import * as hpjs from 'hyperparameters'; const trials = hpjs.fmin(optimizationFunction, space, estimator, max_estimates, options); example:
import * as hpjs from 'hyperparameters'; const fn = x => ((x ** 2) - (x + 1)); const space = hpjs.uniform(-5, 5); fmin(fn, space, hpjs.search.randomSearch, 1000, { rng: new hpjs.RandomState(123456) }) .then(trials => console.log(result.argmin)); - include (latest) version from cdn
<script src="https://cdn.jsdelivr.net/npm/hyperparameters@latest/dist/hyperparameters.min.js" />
- create search space
const space = { optimizer: hpjs.choice(['sgd', 'adam', 'adagrad', 'rmsprop']), epochs: hpjs.quniform(50, 250, 50), }; - create tensorflow.js train function. Parameters are optimizer and epochs. input and output data passed as second argument
const trainModel = async ({ optimizer, epochs }, { xs, ys }) => { // Create a simple model. const model = tf.sequential(); model.add(tf.layers.dense({ units: 1, inputShape: [1] })); // Prepare the model for training: Specify the loss and the optimizer. model.compile({ loss: 'meanSquaredError', optimizer }); // Train the model using the data. const h = await model.fit(xs, ys, { epochs }); return { model, loss: h.history.loss[h.history.loss.length - 1] }; }; - create optimization function
const modelOpt = async ({ optimizer, epochs }, { xs, ys }) => { const { loss } = await trainModel({ optimizer, epochs }, { xs, ys }); return { loss, status: hpjs.STATUS_OK }; }; - find optimal hyperparameters
const trials = await hpjs.fmin( modelOpt, space, hpjs.search.randomSearch, 10, { rng: new hpjs.RandomState(654321), xs, ys } ); const opt = trials.argmin; console.log('best optimizer',opt.optimizer); console.log('best no of epochs', opt.epochs); - install hyperparameters in your package.json
$ npm install hyperparameters - import hyperparameters
import * as tf from '@tensorflow/tfjs'; import * as hpjs from 'hyperparameters'; - create search space
const space = { optimizer: hpjs.choice(['sgd', 'adam', 'adagrad', 'rmsprop']), epochs: hpjs.quniform(50, 250, 50), }; - create tensorflow.js train function. Parameters are optimizer and epochs. input and output data passed as second argument
const trainModel = async ({ optimizer, epochs }, { xs, ys }) => { // Create a simple model. const model = tf.sequential(); model.add(tf.layers.dense({ units: 1, inputShape: [1] })); // Prepare the model for training: Specify the loss and the optimizer. model.compile({ loss: 'meanSquaredError', optimizer }); // Train the model using the data. const h = await model.fit(xs, ys, { epochs }); return { model, loss: h.history.loss[h.history.loss.length - 1] }; }; - create optimization function
const modelOpt = async ({ optimizer, epochs }, { xs, ys }) => { const { loss } = await trainModel({ optimizer, epochs }, { xs, ys }); return { loss, status: hpjs.STATUS_OK }; }; - find optimal hyperparameters
const trials = await hpjs.fmin( modelOpt, space, hpjs.search.randomSearch, 10, { rng: new hpjs.RandomState(654321), xs, ys } ); const opt = trials.argmin; console.log('best optimizer',opt.optimizer); console.log('best no of epochs', opt.epochs); MIT © Atanas Stoyanov & Martin Stoyanov