I have been using tensorflow for a 3 years now, learning to use with keras and without keras by using tf core for all my work. I have been seeing many posts regarding how tensorflow is dying and will be replaced soon. So my question is, is tf dying? Should I write my work in other libraries like flax or torch instead of tf ?
1 Like
Hi @Nithish_M ,
It’s understandable to have concerns about the future of TensorFlow given the evolving landscape of deep learning libraries. While there may be discussions about its future, TensorFlow remains a robust framework with strong industry support and a vast community. It continues to evolve, addressing user feedback and incorporating new features.
Exploring other libraries like Flax or PyTorch can broaden your skill set and offer different perspectives on deep learning implementations. Each library has its strengths and may be better suited for certain tasks or preferences.
Thank You !
1 Like
Cool. Thx for the reply.
I have to say, that the drop of GPU support for windows, the lack of documentation and support for cpp, the lack of support and documentation for TensorFlow lite, the lack of TFrecord multi-platform standalone libraries… and so on is simply a strategy that will kill the library long term. Except for very niche projects in large companies.
Other platforms like PyTorch are investing in easy to use multi-platform solutions. If (or when) someone actually puts a solution powerful, stable, easy to access and easy to import and export to other platforms and languages. Private enthusiasts, researchers and academics will drop TensorFlow. And don’t forget that industries rely on specialists who learned in academia and come from research.
In a time of AI revolution, where the technology is more popular than ever, and is being added to literally everything. In my opinion, TensorFlow is neglecting everything outside Python-Linux, dropping an already lacking support for interoperability, and not investing in accessibility.
I’m saying this as a researcher and professor working in a computer science lab in an university. I write this just after investing almost 100 hours trying to simply build TensorFlow-cc to add some basic capabilities to a research project for the European Union, I failed. Also the absolute lack of recent information anywhere about TensorFlow-cc, and the responses I have seen to old threads lets me know most people gave up the same way I’m ready to tell my whole team to abandon TensorFlow and try other solutions.
I have seen others in my lab commenting similar concerns and frustrations. Many of our researchers are already moving away from TensorFlow and soon the whole department will follow.
For context. The Computer Science department is the largest department in my university, and serves the most important IT faculty in the Northwest of Spain.
For us ML is thriving. In addition to the Bachelor degree in Computer Science, where ML is more than present, being the most requested in the entire university. We opened a new one in Data Science, and are opening a new one in Artificial Intelligence. Next year we will be adding new classes and teachers to be able to serve the increasing number of students in two of the three Machine Learning subjects I teach… As far as I know, none of them will learn TensorFlow, none of them are using it in their personal projects and none of them will use it their degrees. They instead will be using Julia, Matlab, OpenCv , PyTorch, Scikit-Learn and other solutions.
Which leaves me to the industry sector. I worked also as a researcher in a public hospital in a project about diabetes, and in a private research center dedicated to laser and manufacturing. They all used TensorFlow, the same my laboratory did. I have been told they are all moving away from it, currently opting for a Scikit-Learn+OpenCv and PyTorch based approach. The reason is in one case the drop of GPU support for windows, and in the other a perceived drop of support combined with lack of interoperability.
The thing is, nobody moves away from a technology they spent years using and learning unless the technology fails them. And once you move away from something because of a problem, if you find a solution somewhere else, you will probably never return.
That is what is happening in TensorFlow. Google has intentionally dropped the ball with support, documentation, accessibility, ease of use, interoperability across languages and interoperability across platforms… so others will raise to the occasion.
Simply put, TensorFlow is becoming the Bing search engine with regards to AI.
1 Like
@Alvaro_Rodriguez Yeah I agree. “paperswithcode” shows that the percentage of paper implementation with tf is going down. I started learning flax and jax. It’s much faster than tf.
2 Likes
Thank you for the insightful post professor. I am just an ML enthusiast and the DL framework of choice was always Keras with TensorFlow as its backend. For that reason I obtained the TensorFlow Developer Certificate (which is not supported from May 2024 by the way). I am really very sorry to witness this trend you described.
Also note that until today the officially documented TensorFlow standard installation procedure for Linux users with GPUs does not include the additional steps required to perform deep learning experiments with TensorFlow version
2.16.1 and utilize GPU locally!! That’s why I submitted a respective pull request in good faith and for the shake of all users as TensorFlow is “An Open Source Machine Learning Framework for Everyone”. However, it is still pending review (26 days have already passed)…
1 Like