PyTorch vs TensorFlow! Which one is better at image processing applciations?


#1

I am trying to build an image processing application using the CB Django Webapp. I have used Caffe + Digits and OpenCV(seperately) in my previous projects but not TensoreFlow or PyTorch.

Which one is better to get started with and more mature and robust for CV applications?


#2

After a careful analysis, I believe TensorFlow is a little bit harder to use compared to pytorch, but tensorflow is matured library for production grade systems. PyTorch is more of research and academia level at the moment. Any comments?


#3

I recommend you build using a pretrained Tensorflow model for your application. Training costs will be too high if you try to train your own models and there’s no point in reinventing the wheel (that’s the point of Crowdbotics!).

Looks like you’re making an image captioning application. I recommend you use one of these two open-source models:


The first one will work out of the box with Crowdbotics; the second one requires you to run some code first. Both of these will plug in nicely into our standard generated Django app. Over time we’ll add these as hot-pluggable modules like our others.