What is the best alternative to Theano?

Question

Built By the Slant team

Find the best product instantly.

4.7 star rating

Try it now - it's free

score 35 · Answer 1

TensorFlow

Top Pro

Ensured continued support

TensorFlow is developed and maintained by Google. It's the engine behind a lot of features found in Google applications, such as: recognizing spoken words translating from one language to another improving Internet search results Making it a crucial component in a lot of Google applications. As such, continued support and development is ensured in the long-term, considering how important it is to the current maintainers. See More

Top Con

Not fully open source

For now, Google has only open sourced parts of the AI engine, namely some algorithms that run atop it. The advanced hardware infrastructure that drives this engine is not "open source". See More

Top Pro

Visualization suite available

Google has made a powerful suite of visualizations available for both network topology and performance. See More

Top Pro

Easily spin up sessions without restarting the program

TensorFlow can run with multiple GPUs. This makes it easy to spin up sessions and run the code on different machines without having to stop or restart the program. See More

Top Pro

Python has a lot of powerful scientific libraries available

Other than having an easy syntax, using Python also gives developers a wide range of some of the most powerful libraries for scientific calculations (NumPy, SciPy, Pandas) without having to switch languages. See More

Top Pro

Safe choice

Safest choice out there. See More

Top Pro

Great debugging potential

You can introduce and retrieve the results of discretionary data on any edge of the graph. You can also combine this with TensorBoard (suite of visualization tools) to get pretty and easy to understand graph visualizations, making debugging even simpler. See More

Top Pro

Written in Python, which is regarded as a really pleasant language to read and develop in

TensorFlow is written in Python, with the parts that are crucial for performance implemented in C++. But all of the high-level abstractions and development is done in Python. See More

Specs

License:Apache License 2.0

See All Experiences

35 3

score 19 · Answer 2

Keras

Top Pro

Runs on top of Theano, TensorFlow or CNTK

You can choose the back-end for Keras. Simply change the backend field to "theano", "tensorflow", or "cntk". Theano was discontinued in 2017, so TensorFlow or CNTK would be the better choice. See More

Top Con

Little customization compared to other frameworks

Keras is a high-level API. It's difficult to customize your model past a point. If you want to build something beyond the application-level, use Theano or TensorFlow. (Keras runs on top of either one of these anyways) See More

Top Pro

Simple to use

Top Pro

Can be used to write really short pieces of code

Keras enforces minimalism as much as possible. Because of this, it's possible to write a small Neural Network in just a couple of lines of code. See More

Top Pro

Really straightforward for someone who is familiar with deep learning

Top Pro

Quite modular

When using Keras you don't have to pull every part of the framework on your project. For example, you can only use training algorithms and not layer implementations. So it works more like a collection of libraries. See More

Specs

License:MIT

See All Experiences

19 0

score 5 · Answer 3

Torch

Top Pro

Easy switch between CPU and GPU

It takes little more than a type cast of your inputs to go from CPU to GPU computation. See More

Top Con

Not easily accessible to the academic community

Being written in Lua instead of the more widely used Python, it's not as accessible to academics as other solutions which are implemented in Python. With Python being one of the most widely used languages in scientific computing. See More

Top Pro

Lots of easy to combine modular pieces

Torch is a very modular framework. As such, you can choose which modules you need to implement and which modules to eliminate from your solution. See More

5 0

score 4 · Answer 4

Infer.NET

Top Con

No commercial license

Infer.NET is free for academic use. However, at this time, commercial use of Infer.NET is limited to Microsoft. No other commercial licenses are available. See More

Top Pro

Supports multiple inference algorithms

Infer.NET supports expectation propagation (including belief propagation as a special case), variational message passing (also known as variational Bayes), max product (for discrete models), and block Gibbs sampling. See More

Top Con

Closed source

Top Pro

Versatile

You can use Infer.NET to solve many different kinds of machine learning problems, from standard problems like classification, recommendation or clustering through to customised solutions to domain-specific problems. See More

Top Pro

Cross platform

Can be used on Windows (.NET), OSX or Linux (using mono) See More

4 0