TensorFlow Reviews

TensorFlow is great for most deep learning purposes. This is especially true in two domains:
1. Computer vision: image classification, object detection and image generation via generative adversarial networks
2. Natural language processing: text classification and generation.

The good community support often means that a lot of off-the-shelf models can be used to prove a concept or test an idea quickly. That, and Google's promotion of Colab means that ideas can be shared quite freely. Training, visualizing and debugging models is very easy in TensorFlow, compared to other platforms (especially the good old Caffe days).

In terms of productionizing, it's a bit of a mixed bag. In our case, most of our feature building is performed via Apache Spark. This means having to convert Parquet (columnar optimized) files to a TensorFlow friendly format i.e., protobufs. The lack of good JVM bindings mean that our projects end up being a mix of Python and Scala. This makes it hard to reuse some of the tooling and support we wrote in Scala. This is where MXNet shines better (though its Scala API could do with more work).

Best suited for deployment on the cloud with the subscription-based model for execution infrastructure. For startups or for companies that do not have a strong data science staff, learning Tensorflow is easy because of the libraries and online tutorials availability.

It can be avoided when your development stack is Microsoft, as using Azure may provide better integration. Also, if the work requires detailed customization of the algorithm, it may be easier to work directly with Python code and TensorFlow may not help.

TensorFlow is well-suited for complex model training with a large dataset using multiple GPU's and provides training time mode visualization for fast debugging of the architecture. If you are doing a proof of concept for new architecture then it would not be a good choice considering implementation complexity and development time.

Tensor Flow can be used for training the Machine Learning model and mobile application that utilizes trained model and the built-in camera for medical images analysis.
It's improving imaging analytics and pathology. Machine learning can supplement the skills of human radiologists by identifying subtler changes in imaging scans more quickly, potentially leading to earlier and more accurate diagnoses.

TensorFlow is a must for deep learning. If deep learning is not necessary then other machine learning packages such as scikit-learn are a more appropriate choice. We have found that TensorFlow can be very useful in performing anomaly detection on time series data. TensorFlow provides easy aAPI for generating LSTM and CNN neural networks.

There are lots of scenarios where TensorFlow can be used efficiently. One of them is image processing and video processing that include classification, recognition, etc. It can also be used for natural language processing and building chatbots. As TensorFlow has LSTM in built, it will be easy to use this for doing NLP stuff.

If someone wants to develop or work around deep learning (artificial neural network), then it is a good choice to use. It is also useful for natural language processing. Implementing the LSTM is easy with this. Some examples of where it can be used are image classification, video classification, creating chatbots, etc.

It is better when there is a lot of data available and the complexity of variables is high—for instance, when nobody has modeled that problem before. If there is not enough data, it does not work, or if it works, it is not going to help to model reality. It is also very good to test the performance of any other model even if the TensorFlow model itself is not going to be the solution for the client.

The best suited scenario is when you want to develop a deep learning model consisting of a deep neural network, like doing something around images/video, which may include convolution network. Other than this, it can also be used to develop NLP models. But if you are developing conventional machine learning, I don't think this is much required as that can be done using Python libraries like sciPy.

There are lots of use cases to use this tool and also lot of cases where you should look to this. Like when it comes to building or playing with a deep learning algorithm like neural networks you should choose this one. But if you are implementing some other machine learning algorithm then definitely you have to check whether TensorFlow is a good choice or not. And you can also use this for NLP as well.

I think TensorFlow is very good for people who want to dive deeper and have full control of the NN layer of details. It is a production-ready design and supports the distributed environment, so it is very good for mature and enterprise production. If the user is looking for reusing some standard models and wants to do some quick POC without too much in-depth understanding of the NN, then maybe something like Keras would be the better wrapper to begin with.