TrustRadius: an HG Insights company

Keras

Score7 out of 10

19 Reviews and Ratings

Get a Demo

What is Keras?

Keras is a Python deep learning library

Categories & Use Cases

Reviews

What users are saying about Keras.
View all reviews

Keras Review

Saurabh Kumar
Software Engineer in Engineering at Dunzo (1001-5000 employees employees)

Pros

  • Until we have IDEs that can make an interpretation of our idea into code, I don't think making Deep Learning models could be made a lot simpler.
  • It's makes the process easy for building the Neural Network.
  • Doesn't require to have strong background in Deep Learning.

Cons

  • I didn't face any issue so far.
  • The only thing, you can't modify everything in this. So it's not recommended for constructing highly optimised algorithms.

Return on Investment

  • Really good for beginners.
  • Easy to use.
  • Strong community and customer support.

Alternatives Considered

TensorFlow

Usability

Other Software Used

TensorFlow, Amazon Tensor Flow, Theano

Rapidly build neural network

Incentivized
Rakesh Kumar
Software Engineer in Engineering at Vahak (201-500 employees employees)

Pros

  • Easy to use. We can implement neural networks easily.
  • There is a lot of built-in utility that makes the task easier.
  • It also supports TensorFlow.

Cons

  • We can't modify everything that we want to.
  • Some built-in model can be included as a part of this library.
  • Resource requirement is quite high for using this library.

Return on Investment

  • Easy and faster way to develop neural network.
  • It would be much better if it is available in Java.
  • It doesn't allow you to modify the internal things.

Alternatives Considered

TensorFlow

Usability

Other Software Used

TensorFlow, Caffe Deep Learning Framework, Amazon Deep Learning AMIs

Best wrapper library for TensorFlow and Theano

Incentivized
Rounak JangirView profile
Ab Initio Developer in Research & Development at Tata Consultancy Services (10,001+ employees employees)

Pros

  • Performs well when you are doing some implementation which requires neural network implementation and some other deep learning models
  • It has lots of inbuilt tools which you can have clean your data before processing
  • It supports Tensorflow as its backend, so it can easily use GPU

Cons

  • As it is a kind of wrapper library it won't allow you to modify everything of its backend
  • Unlike other deep learning libraries, it lacks a pre-defined trained model to use
  • Errors thrown are not always very useful for debugging. Sometimes it is difficult to know the root cause just with the logs

Return on Investment

  • It helped me in learning the basic concept of deep learning by having hands-on experience.
  • It has helped us to implement our NN with very little time.
  • It doesn't give you the whole power to customize your neural network. If you want that then you have to shift to TensorFLow

Alternatives Considered

TensorFlow, Caffe Deep Learning Framework and Theano

Other Software Used

MongoDB, Datadog, Sentry

Best wrapper library for TensorFlow and Theano.

Incentivized
Gaurav YadavView profile
Software Developer in Engineering at COVIAM (201-500 employees employees)

Pros

  • One of the reason to use Keras is that it is easy to use. Implementing neural network is very easy in this, with just one line of code we can add one layer in the neural network with all it's configurations.
  • It provides lot of inbuilt thing like cov2d, conv2D, maxPooling layers. So it makes fast development as you don't need to write everything on your own. It comes with lot of data processing libraries in it like one hot encoder which also makes your development easy and fast.
  • It also provides functionality to develop models on mobile device.

Cons

  • As Keras works at a high level of abstraction, it limits the user to use it's own implemented algorithm. It doesn't give complete power to user to modify or implementing their own basic algorithm.
  • Sometimes it is slow on GPU as compared to the pure tensorflow.
  • Other than the above two cons, I don't think it has any negatives.

Return on Investment

  • It made our development faster and easy as well.
  • Sometime, when we need to change the basic algorithm, when we need to configure the neural network configuration then it doesn't allow us to modify that.
  • As it comes with lot of inbuilt features of data processing, it is easy to process the data.

Alternatives Considered

TensorFlow and Caffe Deep Learning Framework

Other Software Used

TensorFlow, Theano, Caffe Deep Learning Framework

Best wrapper library for TensorFlow

Incentivized
Raghuvar PrajapatiView profile
Data Scientist in Information Technology at Pensieve (11-50 employees employees)

Pros

  • Implementing neural networks and deep learning models is easy with this.
  • Data processing is easy with Python and Keras. Keras helps a lot and has a good collection of functions to do data processing.
  • It has good integration with other devices like Android.

Cons

  • With Keras you don't have much power to configure your model. So, if it can be possible to do the customization to the deep level, then it will be good.
  • It is only available for Python, doesn't have other language support.
  • Would love to see dynamic chart creation, like PyTorch

Return on Investment

  • Good and easy way to develop neural network models
  • Doesn't provide support for language other than Python
  • Developed a natural language processing model that is quite easy and efficient

Alternatives Considered

TensorFlow and MATLAB

Other Software Used

Splunk Enterprise, New Relic Infrastructure, MATLAB