2

I'm using tensorflow js in node and trying to encode my inputs.

const tf = require('@tensorflow/tfjs-node');
const argparse = require('argparse');
const use = require('@tensorflow-models/universal-sentence-encoder');

These are imports, the suggested import statement (ES6) isn't permitted for me in my node environment? Though they seem to work fine here.

const encodeData = (tasks) => {
  const sentences = tasks.map(t => t.input);
  let model = use.load();
  let embeddings = model.embed(sentences);
  console.log(embeddings.shape);
  return embeddings;  // `embeddings` is a 2D tensor consisting of the 512-dimensional embeddings for each sentence.
};

This code produces an error that model.embed is not a function. Why? How do I properly implement an encoder in node.js?

srilekha palepu - Intel
  • 2,017
  • 9
  • 22
Stephan
  • 155
  • 13

1 Answers1

3

load returns a promise that resolve to the model

use.load().then(model => {
  // use the model here
  let embeddings = model.embed(sentences);
   console.log(embeddings.shape);
})

If you would rather use await, the load method needs to be in an enclosing async function

const encodeData = async (tasks) => {
  const sentences = tasks.map(t => t.input);
  let model = await use.load();
  let embeddings = model.embed(sentences);
  console.log(embeddings.shape);
  return embeddings;  // `embeddings` is a 2D tensor consisting of the 512-dimensional embeddings for each sentence.
};
edkeveked
  • 17,989
  • 10
  • 55
  • 93
  • 2
    Wow, I'm shocked I didn't realize this. Model was undefined because USE hadn't finished loading yet. I guess im still not used to asynchronous programming. Thank you. – Stephan Dec 26 '19 at 06:17