28 thoughts on “Deep Learning Frameworks 2019”

  1. Hi siraj. Can I ask for a video Series? Here is the idea : train a neural network for predicting crypto market (maybe cntk this time please?), save the model and weights, then…. load the model in a c# winform application and use it to predict.

  2. I also dont see any commercial frameworks like MATLAB on the list. Just curious if you have looked at how it compares to these major frameworks?

  3. Shoutout to **dynet**, the even more-natural way to do variable-input modeling – lazy computation graph building (so, more efficient and readable than pytorch). It also has auto-minibatching, which saves a lot of unnecessary wrapping (but pytorch should include soon as well, I hear). Best of all, it works great on CPU, definitely compared to TF and pytorch.
    My choice for research prototyping.

  4. MATLAB is the easier…with all models ready to implement. A graphical tool to create new architectures. In 2 days I did in matlab what took me weeks to do using Tensorflow.

  5. My research is in optimizing NN for low latency and low power applications. So I have my own NN written in CUDA C++ (both forward and back propagation using different techniques). Which of these frameworks allow to easily integrate, test and compare customized NN written in CUDA C++ with the traditional ones available in their library?

Leave a Reply

Your email address will not be published. Required fields are marked *