1. Home
  2. Machine Learning Tools
  3. TensorFlow Reviews
  4. User Review of TensorFlow
My perception of the first year with TensorFlow
September 25, 2018

My perception of the first year with TensorFlow

Jose Machicao, MSc | TrustRadius Reviewer
Score 7 out of 10
Vetted Review
Verified User

Overall Satisfaction with TensorFlow

Currently, we use machine-learning models to develop solutions for our clients. But sometimes the usual models (decision tree, naive Bayes, random forest) are not helping us to find a suitable model, or it generates too many levels of modeling. Sometimes we use the pre-build neural networks included in some libraries. We are not yet experts in TensorFlow, but using Keras, it helped us to arrive to predictive models in a shorter time and with more accuracy.
  • Modeling for complex problems with large amounts of data
  • Modeling when the client is not interested in building the model patiently in levels
  • Guiding what we are doing wrong with other models
  • Too many lines of code for some actions
  • Not very intuitive for non-programming engineers
  • Less modeling time
  • More certainty about a model, and therefore fewer levels of modeling
TensorFlow is much more complete to model
It is better when there is a lot of data available and the complexity of variables is high—for instance, when nobody has modeled that problem before. If there is not enough data, it does not work, or if it works, it is not going to help to model reality. It is also very good to test the performance of any other model even if the TensorFlow model itself is not going to be the solution for the client.