Reviews (1-3 of 3)
January 18, 2019
Score 8 out of 10
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
Read Rounak Jangir's full review
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
October 17, 2018
Score 9 out of 10
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
Read Raghuvar Prajapati's full review
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.
September 17, 2018
Score 9 out of 10
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.
Read Gaurav Yadav's full review
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.