Skip to main content
TrustRadius
Keras

Keras

Overview

What is Keras?

Keras is a Python deep learning library

Read more
Recent Reviews

TrustRadius Insights

Keras, a popular machine learning library, has been utilized by multiple individuals in my company for various use cases. Specifically, it …
Continue reading

Keras Review

9 out of 10
November 10, 2020
My general experience is positive. It may give some new software engineers a marginally misshaped Idea of how things work - since it is …
Continue reading
Read all reviews
Return to navigation

Pricing

View all pricing
N/A
Unavailable

What is Keras?

Keras is a Python deep learning library

Entry-level set up fee?

  • No setup fee

Offerings

  • Free Trial
  • Free/Freemium Version
  • Premium Consulting/Integration Services

Would you like us to let the vendor know that you want pricing?

6 people also want pricing

Alternatives Pricing

What is Databricks Lakehouse Platform?

Databricks in San Francisco offers the Databricks Lakehouse Platform (formerly the Unified Analytics Platform), a data science platform and Apache Spark cluster manager. The Databricks Unified Data Service aims to provide a reliable and scalable platform for data pipelines, data lakes, and data…

What is IBM SPSS Modeler?

IBM SPSS Modeler is a visual data science and machine learning (ML) solution designed to help enterprises accelerate time to value by speeding up operational tasks for data scientists. Organizations can use it for data preparation and discovery, predictive analytics, model management and…

Return to navigation

Product Details

What is Keras?

Keras is a Python deep learning library

Keras Technical Details

Operating SystemsUnspecified
Mobile ApplicationNo
Return to navigation

Comparisons

View all alternatives
Return to navigation

Reviews and Ratings

(18)

Community Insights

TrustRadius Insights are summaries of user sentiment data from TrustRadius reviews and, when necessary, 3rd-party data sources. Have feedback on this content? Let us know!

Keras, a popular machine learning library, has been utilized by multiple individuals in my company for various use cases. Specifically, it has been successfully employed during hackathons and machine learning projects. While not used company-wide, Keras is favored by specific departments like the data science team.

One of the main use cases of Keras is implementing neural networks, particularly for image recognition and other machine learning tasks. It has proven effective for applications such as image processing and basic classification. Additionally, Keras has been used to develop data science models, including neural networks and NLP models like LSTM. Users have found Keras to be a great starting point for beginners in machine learning, as it simplifies the process of building neural networks.

Keras is often integrated with TensorFlow in the Data & AIML department, where it serves as a high-level API for model designing, training, evaluation, and inference/prediction. It plays a crucial role in the production environment by incorporating into a final Model As Service product. This allows various business applications to consume its prediction output for making important decisions. Overall, Keras has demonstrated its value in diverse machine learning applications within our organization.

Easy to use: Many users have found Keras to be easy to use, especially when implementing neural networks and deep learning models. They appreciate that with just one line of code, they can add a layer to the neural network with all its configurations.

Wide range of built-in features: Users appreciate that Keras provides a wide range of built-in features such as cov2d, conv2D, and maxPooling layers. This allows for fast development without the need to write everything from scratch.

Convenient mobile implementation: Several reviewers have mentioned that they find it convenient that Keras offers functionality to develop models on mobile devices. This is particularly helpful for users who require mobile implementation.

Cons:

  1. Limited Customization Options: Some users have expressed that Keras does not provide much power for configuring models, limiting their ability to modify or implement their own basic algorithms as it works at a high level of abstraction.
  2. Lack of Pre-trained Models: Several reviewers have mentioned that Keras lacks pre-defined trained models, which are available in other deep learning libraries.
  3. Documentation and Error Handling: Users have found the errors thrown by Keras to be unhelpful for debugging, making it difficult to determine the root cause of issues. Additionally, documentation on advanced topics like distributed training is not clear and lacks real code examples according to some users.

Users often recommend Keras as a great starting point for beginners and small scale projects. They advise newcomers to begin with Keras to gain a better understanding of deep learning, while also emphasizing the importance of reading the documentation and exploring the provided examples. Users suggest that it's helpful to have a foundational knowledge of basic machine learning concepts before diving into Keras. Additionally, Keras is highly recommended for quickly prototyping new ideas and gaining insights into neural networks, although it may not be suitable for more complex models.

Attribute Ratings

Reviews

(1-6 of 6)
Companies can't remove reviews or game the system. Here's why
Score 8 out of 10
Vetted Review
Verified User
Incentivized
Keras is being used together with TensorFlow, in our new Data & AIML department. Many business use cases are implemented on top of it. We use Keras as high level API, responsible for model designing, model training, model evaluation and model inference/prediction. It is part of our final Model As Service product, deployed in our production environment, allowing various business application [to] consume its prediction output and take the important decision as early as possible.
  • As the high level API, clean and neat, allowing the data scientists to develop the standard deep learning model very quickly (using the mature and existed algorithm module blocks)
  • Seamlessly integrate with [a] couple of Deep Learning framework, although we only use TensorFlow, and since TF2.0 Keras has become the 1st class native API
  • Keras model itself is not thread safe, and the documentation regarding how the multi thread works during the prediction time is not quite clear and enough, we still need [to] tweak the TensorFlow old (session + graph) way to support our Model As Service, in the high concurrent scenario, but with limited memory constraint.
  • Some API and default implementation still has a lot [of] improvement room, for example, the checkpoint callback, only saves the "best" model, natively can not save all other metadata of the "best" model, we currently have to extend that by ourselves to meet our project requirement.
  • Some advanced topic, like distributed training, documentation is not so clear and very hard to find the real code example.
Keras is quite perfect, if the aim is to build the standard Deep Learning model, and materialize it to serve the real business use case, while it is not suitable if the purpose is for research and a lot of non-standard try out and customization are required, in that case either directly goes to low level TensorFlow API or Pytorch
November 10, 2020

Keras Review

Score 9 out of 10
Vetted Review
Verified User
My general experience is positive. It may give some new software engineers a marginally misshaped Idea of how things work - since it is genuinely simple to building an amazing neural network with it, yet it could likewise urge them to burrow further. Building even a basic NN with C without any preparation would disappoint most fledglings, so this is a decent spot for understudies to begin - accepting that they're likewise examining hypothesis.
  • 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.
  • 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.
On the off chance that you are new to Deep learning and need to figure out how to code, Keras is a decent beginning, since it is easy to use and very handy to learn API.
Score 8 out of 10
Vetted Review
Verified User
Incentivized
Keras isn't utilized over the entire association, however it is being utilized by a portion of our specialties. In those offices, the vast majority of them are utilizing it to do some sort of AI task, which fundamentally incorporates planning and actualizing the neural organization. I have utilized this for loads of reasons. Every one of them was in AI fields, similar to picture preparing, essential grouping, and considerably more.
  • 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.
  • 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.
I would suggest using it when anybody needs to rapidly build up a neural network for the organization. Or if a client is tackling any AI issue that incorporates machine learning--image classification, face recognition, or doing some content examination which incorporates LSTM or some other calculation. It is not recommended if you want to change the algorithm internally, as it won't allow you to do so.
Rounak Jangir | TrustRadius Reviewer
Score 8 out of 10
Vetted Review
Verified User
Incentivized
Keras is not used across the whole organization, but it is being used by some of our departments only. And in those departments, most of them are using it to do some kind of machine learning task, which basically includes designing and implementing the neural network. I have used this for lots of reasons. All of them were of machine learning fields, like image processing, basic classification, and much more.
  • 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
  • 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
There are a lot of other libraries in competition with Keras, like TensorFlow, tfLearn, Theano and lot more. If you are new to the deep learning field and want to learn things quickly with implementation then I think you should start with Keras. Once you have good enough knowledge about deep learning concepts then you can shift to some other library, most probably to TensorFlow which gives you the power to write and customize whole neural network
Raghuvar Prajapati | TrustRadius Reviewer
Score 9 out of 10
Vetted Review
Verified User
Incentivized
Keras is being used to develop data science models for predictions that include implementing neural networks and others as well. It is not being used by all of us in our company but only by the data science team. We have used this not only for prediction, but for building NLP models as well. We have used this to implement LSTM. Basically, we use this to understand the natural language and to process that.
  • 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.
  • 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
Scenarios where it is well suited include implementing deep learning algorithms. It is also good for natural language processing. It has some in built functions that are very useful for developing deep learning models. To build basic machine learning algorithms, which includes clustering and PCM, it may not be as good.
Gaurav Yadav | TrustRadius Reviewer
Score 9 out of 10
Vetted Review
Verified User
Incentivized
Keras is being used during hackathon in my current company. And it's not used by across the company. Basically, during hackathon lots of people are working on machine learning projects that includes deep learning as well. So, there are lots of people who are using Keras for neural network implementation. And I have used this in my during my college and in company as well. We have used Keras to implement neural network for image recognition and in other things as well.
  • 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.
  • 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.
I would recommend it for use when anyone wants to quickly develop a neural network. Or if a user is solving any machine learning problem that includes deep learning. And this kind of problem will be like image recognition, face recognition, doing some text analysis using deep learning which includes LSTM or some other algorithm.
Return to navigation