9

Quite an open-ended question.

Just pretty curious whats the current difference if I want to deploy a machine learning (object detection) model on the browser, perhaps on a webapp to begin with (to be viewed on a phone).

From what I know, both tensorflowjs and tensorflowlite are compatible for such a deployment. (I've heard tensorflowlite is superior but, curious to find the pros and cons if any)

What are the main differences between them? Will tensorflowjs be a good choice too?

Gabriel
  • 438
  • 1
  • 5
  • 16

1 Answers1

11

main difference of tensorflow-lite against tensorflow.js is that you can not train new or existing model using tensorflow lite,but with tensorflow.js you can.

Hence tensorflowlite is only for inference to do on small capacity device(e.g. IOT)

moreover tensorflow.js work with nodejs/typescript and/or browser environment only.

enter image description here

divyang4481
  • 1,584
  • 16
  • 32
  • 1
    Is this answer up-to-date? I did a quick research and https://codelabs.developers.google.com/codelabs/tfjs-training-classfication/index.html#5 this page shows how to train a model using tensorflow.js – iRestMyCaseYourHonor Dec 28 '20 at 09:49