Dataiku is a French startup and its product, DSS, is a challenger to market incumbents and features some visual tools to assist in building workflows.
N/A
TensorFlow
Score 8.4 out of 10
N/A
TensorFlow is an open-source machine learning software library for numerical computation using data flow graphs. It was originally developed by Google.
Dataiku DSS is very well suited to handle large datasets and projects which requires a huge team to deliver results. This allows users to collaborate with each other while working on individual tasks. The workflow is easily streamlined and every action is backed up, allowing users to revert to specific tasks whenever required. While Dataiku DSS works seamlessly with all types of projects dealing with structured datasets, I haven't come across projects using Dataiku dealing with images/audio signals. But a workaround would be to store the images as vectors and perform the necessary tasks.
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).
Theano is perhaps a bit faster and eats up less memory than TensorFlow on a given GPU, perhaps due to element-wise ops. Tensorflow wins for multi-GPU and “compilation” time.
As I have described earlier, the intuitiveness of this tool makes it great as well as the variety of users that can use this tool. Also, the plugins available in their repository provide solutions to various data science problems.
The support team is very helpful, and even when we discover the missing features, after providing enough rational reasons and requirements, they put into it their development pipeline for the future release.
Community support for TensorFlow is great. There's a huge community that truly loves the platform and there are many examples of development in TensorFlow. Often, when a new good technique is published, there will be a TensorFlow implementation not long after. This makes it quick to ally the latest techniques from academia straight to production-grade systems. Tooling around TensorFlow is also good. TensorBoard has been such a useful tool, I can't imagine how hard it would be to debug a deep neural network gone wrong without TensorBoard.
Strictly for Data Science operations, Anaconda can be considered as a subset of Dataiku DSS. While Anaconda supports Python and R programming languages, Dataiku also provides this facility, but also provides GUI to creates models with just a click of a button. This provides the flexibility to users who do not wish to alter the model hyperparameters in greater depths. Writing codes to extract meaningful data is time consuming compared to Dataiku's ability to perform feature engineering and data transformation through click of a button.
Keras is built on top of TensorFlow, but it is much simpler to use and more Python style friendly, so if you don't want to focus on too many details or control and not focus on some advanced features, Keras is one of the best options, but as far as if you want to dig into more, for sure TensorFlow is the right choice
