We asked business professionals to review the solutions they use. Here are some excerpts of what they said:
"Its interface is the most valuable. The ability to have an interface to train machine learning models and construct them with the high-level interface, without excess busting and reconstructing the same technical elements, is very useful."
"I like that PyTorch actually follows the pythonic way, and I feel that it's quite easy. It's easy to find compared to others who require us to type a long paragraph of code."
"Our clients were not aware they were using TensorFlow, so that aspect was transparent. I think we personally chose TensorFlow because it provided us with more of the end-to-end package that you can use for all the steps regarding billing and our models. So basically data processing, training the model, evaluating the model, updating the model, deploying the model and all of these steps without having to change to a new environment."
"It is also totally Open-Source and free. Open-source applications are not good usually. but TensorFlow actually changed my view about it and I thought, "Look, Oh my God. This is an open-source application and it's as good as it could be." I learned that TensorFlow, by sharing their own knowledge and their own platform with other developers, it improved the lives of many people around the globe."
"TensorFlow is a framework that makes it really easy to use for deep learning."
"The most valuable features are the frameworks and the functionality to work with different data, even when we have a certain quantity of data flowing."
"TensorFlow improves my organization because our clients get a lot of investment from their investors and we are progressively improving the products. Every six months we release new features."
"Google is behind TensorFlow, and they provide excellent documentation. It's very thorough and very helpful."
"It's got quite a big community, which is useful."
"It is open-source, and it is being worked on all the time. You don't have to pay all the big bucks like Azure and Databricks. You can just use your local machine with the open-source TensorFlow and create pretty good models."
"There is not enough documentation about some methods and parameters. It is sometimes difficult to find information."
"I would like a model to be available. I think Google recently released a new version of EfficientNet. It's a really good classifier, and a PyTorch implementation would be nice."
"It doesn't allow for fast the proto-typing. So usually when we do proto-typing we will start with PyTorch and then once we have a good model that we trust, we convert it into TensorFlow. So definitely, TensorFlow is not very flexible."
"However, if I want to change just one thing in the implementation of TensorFlow functions I have to copy everything that they wrote and I change it manually if indeed it can be amended. This is really hard as it's written in C++ and has a lot of complications."
"There are connection issues that interrupt the download needed for the data sets. We need to prepare them ourselves."
"In terms of improvement, we always look for ways they can optimize the model, accelerate the speed and the accuracy, and how can we optimize with our different techniques. There are various techniques available in TensorFlow. Maintaining accuracy is an area they should work on."
"I know this is out of the scope of TensorFlow, however, every time I've sent a request, I had to renew the model into RAM and they didn't make that prediction or inference. This makes the point for the request that much longer. If they could provide anything to help in this part, it will be very great."
"Personally, I find it to be a bit too much AI-oriented."
"It would be nice to have more pre-trained models that we can utilize within layers. I utilize a Mac, and I am unable to utilize AMD GPUs. That's something that I would definitely be like to be able to access within TensorFlow since most of it is with CUDA ML. This only matters for local machines because, in Azure, you can just access any GPU you want from the cloud. It doesn't really matter, but the clients that I work with don't have cloud accounts, or they don't want to utilize that or spend the money. They all see it as too expensive and want to know what they can do on their local machines."
"It is free."
"PyTorch is an open-source solution."
"TensorFlow is free."
"I think for learners to deploy a project, you can actually use TensorFlow for free. It's just amazing to have an open-source platform like TensorFlow to deploy your own project. Here in Russia no one really cares about licenses, as it is totally open source and free. My clients in the United States were also pleased to learn when they enquired, that licensing is free."
"We are using the free version."
"It is open-source software. You don't have to pay all the big bucks like Azure and Databricks."
"I did not require a license for this solution. It a free open-source solution."
We've built this course as an introduction to deep learning. Deep learning is a field of machine learning utilizing massive neural networks, massive datasets, and accelerated computing on GPUs. Many of the advancements we've seen in AI recently are due to the power of deep learning. This revolution is impacting a wide range of industries already with applications such as personal voice assistants, medical imaging, automated vehicles, video game AI, and more.
In this course, we'll be covering the concepts behind deep learning and how to build deep learning models using PyTorch. We've included a lot of hands-on exercises so by the end of the course, you'll be defining and training your own state-of-the-art deep learning models.
TensorFlow is an open source software library for high performance numerical computation. Its flexible architecture allows easy deployment of computation across a variety of platforms (CPUs, GPUs, TPUs), and from desktops to clusters of servers to mobile and edge devices. Originally developed by researchers and engineers from the Google Brain team within Google’s AI organization, it comes with strong support for machine learning and deep learning and the flexible numerical computation core is used across many other scientific domains.
PyTorch is ranked 4th in AI Development Platforms with 2 reviews while TensorFlow is ranked 2nd in AI Development Platforms with 10 reviews. PyTorch is rated 9.0, while TensorFlow is rated 9.2. The top reviewer of PyTorch writes "A highly user-friendly open-source machine learning library". On the other hand, the top reviewer of TensorFlow writes "The generator saves us a lot of time and memory in terms of development and the learning process of models". PyTorch is most compared with OpenVINO, whereas TensorFlow is most compared with OpenVINO, Microsoft Azure Machine Learning Studio, Wit.ai, Infosys Nia and Caffe. See our PyTorch vs. TensorFlow report.
See our list of best AI Development Platforms vendors.
We monitor all AI Development Platforms reviews to prevent fraudulent reviews and keep review quality high. We do not post reviews by company employees or direct competitors. We validate each review for authenticity via cross-reference with LinkedIn, and personal follow-up with the reviewer when necessary.