Keras

Keras


5 / 5
11 reviews


Average Ratings

11 Reviews

  • 5 / 5
    Overall

  • 4.5 / 5
    Ease of Use

  • 4.5 / 5
    Customer Service

Product Details

Vendor has not completed this information.


About Keras

Open source neural network library, written in Python, that supports both recurrent networks and convolutional networks.


Spotlight-media-placeholder

Keras Features

  • Convolutional Neural Networks
  • Document Classification
  • Image Segmentation
  • ML Algorithm Library
  • Model Training
  • Neural Network Modeling
  • Self-Learning
  • Visualization

Keras Reviews Recently Reviewed!


A great library for training Deep Neural Networks

May 02, 2018
5/5
Overall

3 / 5
Ease of Use

3 / 5
Features & Functionality
Likelihood to Recommend: 10.0/10 Not
Likely
Extremely
Likely

Pros: Python is easy to use and extensible. The modularity of these libraries is the future of building complex machine learning models. Keras is one of the better frameworks out there right now. It allows us to train deep neural nets at a reasonable rate. Keras is compatible with Apple's Core ML which is very useful for our moblie app development.

Cons: Keras is a little limited in what it can handle. Luckily there are other frameworks popping up every day to supplement any shortcomings.

Overall: Keras is fully compatible with Core ML - this allows our dev team to build complex mobile applications on the latest iOS devices.

Capterra-loader

keras - an easy way to develop machine learning models

Oct 06, 2018
5/5
Overall

5 / 5
Ease of Use

4 / 5
Features & Functionality

4 / 5
Customer Support

5 / 5
Value for Money
Likelihood to Recommend: 9.0/10 Not
Likely
Extremely
Likely

Pros: It has made machine learning and deep learning implementation very easy as compared to tensorflow. Implementing deep learning models using tensorflow is very difficult, you have to take care of each and every variables but if you are using keras it's very easy to do this. With just few lines of code you can develop a deep learning model. Keras also provide lots of functionality for data processing like converting to one hot encoding and lot other.

Cons: As it provides lots of easy way to implement algorithm but it restricts you to use those functionality only. If you want to build good algorithm with lot of optimization, you can't do everything with keras.

Capterra-loader

Best wrapper library for tensorflow an theano -- very easy to use

Jul 18, 2018
5/5
Overall

5 / 5
Ease of Use

5 / 5
Features & Functionality

5 / 5
Customer Support

5 / 5
Value for Money
Likelihood to Recommend: 9.0/10 Not
Likely
Extremely
Likely

Pros: While writing the neural network with tensorflow, we need to take care of every thing like input layer size, output layer size, bias vector size. We have to design the whole layer itself.

But with this library, it can be done in just one line. Also it has lots of inbuilt feature for data processing which makes it very usable. And it's support for both tensorflow and theano, makes it more advance.

Cons: It is best wrapper library over tensorflow, but it restrict you to use their implemented algorithm. Although, you can configure the inbuilt functionality, but then it would be better to do that with tensorflow only.

Overall: have made writing neural network implementation very easy

The more accessible brother of TensorFlow

Jun 28, 2018
5/5
Overall

5 / 5
Ease of Use

4 / 5
Features & Functionality
Likelihood to Recommend: 10.0/10 Not
Likely
Extremely
Likely

Pros: It's very, very easy to build most traditional DL algorithms and train them, even with some modifications.

Cons: Developing new algorithms might be somewhat more cumbersome than with some of the alternatives, as Keras stays at a pretty high level of abstraction.

Nice framework fo NNs

Apr 12, 2018
4/5
Overall

2 / 5
Ease of Use

4 / 5
Features & Functionality
Likelihood to Recommend: 7.0/10 Not
Likely
Extremely
Likely

Pros: A lot of built-in layer types, easy way to connect them. Our team is using it with Theano and TensorFlow

Cons: Sometimes you need to do something more complex and Keras is not able to handle it. It is the second you need to switch to Lasagne.

Capterra-loader

Best wrapper library for tensor flow

Jul 26, 2018
5/5
Overall

5 / 5
Ease of Use

5 / 5
Features & Functionality

5 / 5
Customer Support

5 / 5
Value for Money
Likelihood to Recommend: 9.0/10 Not
Likely
Extremely
Likely

Pros: I think keras is the best wrapper library for tensor flow. Writing the neural network and other deep learning algorithm in tensorflow is a bit difficult. But with the use of writing all those is very easy. Like you can add convolution layer in just one line. You don't have to worry about the dimension of weight matrix of bias vector, Keras take care of that most of the time.

Cons: I think it doesn't have any drawbacks. But one think is that if you want to write your own implementation then you have to go back to tensor flow.

Overall: Best wrapper library for Theano and Tensorflow

A great python library for deep learning - used extensively by our innovation team.

Mar 07, 2018
5/5
Overall

5 / 5
Ease of Use

5 / 5
Features & Functionality

5 / 5
Customer Support

5 / 5
Value for Money
Likelihood to Recommend: 10.0/10 Not
Likely
Extremely
Likely

Pros: Keras is the best library for deep learning machine learning models. It is modular, minimalist and extensible. Python really is the future for machine learning models. It is fast and very advanced in its capability.

Cons: Learning curve is intense, this is to be expected with emerging technologies so that is the least of our concerns.

Overall: Keras is one of the only real solutions to deep learning and looks great doing it. This is an extensible and very effective solution to building complex machine learning models.

Best python library for Convolutional Neural Networks

Aug 24, 2018
5/5
Overall

5 / 5
Ease of Use

5 / 5
Features & Functionality
Likelihood to Recommend: 10.0/10 Not
Likely
Extremely
Likely

Pros: Keras is a Python wrapper library around Google's machine learning framework Tensorflow, and it's so good such that Tensorflow now has a Keras implementation. Keras's syntax is very straightforward and easy to pick up, which simplifies the process of building neural networks and makes other people's code very interpretable.

NNs are often complex and require a lot of tweaking get right, and the way Keras is designed makes it easy to modify your models. Another obvious benefit is that since it's in Python, you can use other libraries such as Pandas and Scikit Learn concurrently with Keras. It also supports GPUs, which is a major plus when dealing with huge datasets.

Cons: Nothing! Maybe have more examples in their documentation that doesn't involve the MNIST dataset.

Capterra-loader

Is great using a GPU to make fastest calculations.

May 05, 2018
5/5
Overall

5 / 5
Ease of Use

4 / 5
Features & Functionality

4 / 5
Customer Support

5 / 5
Value for Money
Likelihood to Recommend: 10.0/10 Not
Likely
Extremely
Likely

Pros: I was using it in Python, with models trained, in a few lines of code i obtained data with a webcamera, the same code worked with CPU and GPU without make changes.

Cons: When I use many models of tensor flow linked with keras, it's become a little slow and make need use of GPU to obtain 10fps with a GTX 1050 Ti

Overall: I obtained calculations in real-time of facial expressions to complete a project. It make the development more robust and faster.

Keras is the go-to tool for deep learning

Aug 02, 2018
5/5
Overall

5 / 5
Ease of Use

5 / 5
Features & Functionality
Likelihood to Recommend: 10.0/10 Not
Likely
Extremely
Likely

Pros: I like how easy to use this tool is and how it can run in conjunction with a number of other products like MCT, Theano, etc.

Cons: There isn't anything I dislike about it to be honest - I think it's the leading tool for deep learning in Python!

Really easy for a programming novice

Aug 08, 2018
5/5
Overall

5 / 5
Ease of Use

4 / 5
Features & Functionality
Likelihood to Recommend: 8.0/10 Not
Likely
Extremely
Likely

Pros: The API and the documentation is really easy to understand. It's great to use for someone with not an extensive programming experience.

Cons: If they could add the dynamic graph creations like in pytorch, it'd be great!