Microsoft custom vision vs Tensorflow model?

Question

I am planning to implement my own image classifier model using TensorFlow instead of a custom vision platform.

what is the biggest difference between custom vision(https://www.customvision.ai/) vs TensorFlow?

Answer 1

There are many differences as these are inherently complete different products with different goals.

• customvision

[+] cloud deployment comes out of the box (including a rest API)
[+] labelling tool to add data and label them
[-] you have no control over the learning algorithm
[-] difficult to run your model locally/completely for free

• tensorflow (or any framework really)

[-] you need deploy your model yourself
[-] you need to manage your data yourself
[+] you have full control over your network and how you train it
[+] you can embed your model into your code, run it locally, whatever you feel like