Overall Satisfaction with TensorFlow
I have used this tool for building a recommendation system. We have built a system to recommend flights to users so we used TensorFlow to build that. I personally have used this tool in a different sector like doing image processing, building an image recognition algorithm and implementing neural networks etc. This is being used by a part of our company not by the whole or across the company.
- TensorFlow is very powerful to build the neural networks, it gives you the power to write your own implementation with full customisation.
- It has inbuilt methods which helps a lot when it comes to writing your own implementation of neural networks
- It has lots of inbuilt methods to do the data processing like reading data from a directory as classes using an image data generator etc.
- First and biggest con is that it has a very tense learning curve. Understanding the concept of a tensor, a dynamic graph is difficult and takes a lot of time to learn
- As compared to Keras, TensorFlow takes a lot of time to build and implement a neural network. You have to write everything by yourself.
- It helps us to solve our recommendation problem. Using this we have built a flight recommendation engine.
- There is no negative ROI - it's free and a very good tool to use. But as I mentioned, for me it took quite time to learn it.
- Modifying the pre-written code can be challenging, first, you need to understand each and every parameter of the implemented algorithm and then you can only modify that and that's not easy.