Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 1 year ago.
Improve this question
I am building tensorflow with bazel on my local PC, but as expected it takes quite a long time. The problem is that I want to make my own contributions in the source, so it's not feasible to compile all over again the whole code for every small change that I am making. I want to use tensorflow for a custom project of mine, thus I cannot rely/expect on/from the community to take any issues of mine into consideration.
Are there certain targets I may could use with bazel, just like if I was using make?
I have access to a pretty good GPU server but I cannot figure out whether tensorflow-bazel uses GPU resources for building. Are there any configurations I could use for building with GPU?
What's the fastest way to re-compile tensorflow in general all over again, for every small tweak that I am applying?
How do independent contributors work on tensorflow in general?
Bazel is smart about incremental changes. If you change a single file, then only bare minimum will be recompiled. Just change a file and run the same command as you do for a full build
I have access to a pretty good GPU server but I cannot figure out whether tensorflow-bazel uses GPU resources for building. Are there any configurations I could use for building with GPU?
No, compilers are complicated beasts, which use only CPU
If you want to contribute to Tensorflow go through Contribution guidelines.
Related
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 1 year ago.
Improve this question
We are trying to train an LSTM under anaconda (spyder) from a dataset of size 333113kb. (3628801 rows * 31columns) The data is stored in a .csv file and is imported using the pandas library. The execution is too slow and somtimes spyder crashes.
NB : we are using an Intel Core (TM) i5-8300H CPU 2.3 GHz with 8Go of RAM.
not directly an IDE but I like to use Visual Studio Code because it's an excellent way to go even for machine learning and data science.
it works on any OS
supports many Technologies besides Python, C#, JS etc.
open source and lightweight
VS Code is integrated with PyLint
You can perform unit testing on your machine learning models easily
for me VS Code makes working with SQL, .NET, Node.js and many other Tools a lot easier. It's a great code editor that supports you with operations like debugging, task running, version control and many other things that a full featured IDE can also do.
Is this like university-wise project or commercial? You could try Google Colab.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I've been a full stack web developer for 15 years now and would like to be involved in machine learning. There is already a specific scenario for this: We have a database with several million products and one product image each. There is also a database with about 5000 terms.
A product image is linked to several terms (usually 3 - 20), whereby the link still has a weighting (1-100%). The terms are always of a visual nature, that is, they describe a visually recognizable feature on the image.
The aim should now be to upload a new image (of course with thematic reference) and to get an answer with possible terms (including probability) based on the already classified images.
Do you have any advice on how best to start here? Is there a framework that comes close to this scenario? Is TensorFlow relevant for this task? What new language should I learn?
Thank you very much!
TensorFlow can be used, it's pretty "low-level" though. So if you're just starting out you might be better off using Keras with a TensorFlow backend as it's more userfriendly.
Regarding languages you will probably use Python. So if you don't know it already you should get started. In my opinion you can also learn it on-the-fly while practicing as you're already a developer.
As for tutorials you will have to probably pick out the relevant bits of many different tutorials. You could get started with something like this:
https://www.pyimagesearch.com/2018/05/07/multi-label-classification-with-keras/
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
Rakudo Star is a release targeted towards end users (if I'm not mistaken). As such, it includes a number of useful modules that can be used in a wide range of projects.
But how does the team behind it decide which modules to include? Do module developers talk to them and ask for inclusion, or do they look at usage statistics and include the most popular? Or is inclusion completely arbitrary?
What process should one go through to get their module included?
The collection of modules is in the star repository, includes as sub-modules of the repo. I haven't seen any kind of description of what modules are installed there and why, but I guess using the issues and/or pull requests is the way to go. In fact there's this closed issue which points in that direction, including a reference to ecosystem statistics, so I guess regarding your three questions.
There's no established procedure that I have been able to see.
Apparently, they look at statistics, after some developer asks for them.
I don't think that's the case. They at least have to pass all the tests in all platforms to be included. Also, I don't think my evolutionary algorithms module will be included any time soon.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 5 years ago.
Improve this question
Recently I decided to learn MXNet, as some code I need to use, is written using this API.
However, I would like to know which are the advantages and disadvantages of MXNet compared to the other Deep Learning Libraries out there.
Perhaps the biggest reason for considering MXNet is its high-performance imperative API. This is one of the most important advantages of MXNet to other platforms. Imperative API with autograd makes it much easier and more intuitive to compose and debug a network. PyTorch also supports imperative API, but MXNet is the only platform AFAIK that supports hybridization, which effectively allows your imperative model to be converted to a symbol for similar performance to symbolic API. Here is a link to tutorials on Gluon, MXNet's imperative API: http://gluon.mxnet.io/
Given that you're using an example code, it is possible that the example was written using symbolic API. You may notice MXNet's advantage in symbolic API when training on many GPUs. Otherwise you won't notice much of a difference (except perhaps in some memory usage).
Tensorflow does have a one year head-start to MXNet and as a result it has a larger user base, but it only supports symbolic API (imperative API is very new and is only meant for experimentation), which is significantly harder to debug a network when you run into issues. However MXNet has quickly caught up in features and with 1.0 release, I don't think there is anything in TF that MXNet doesn't support.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 6 years ago.
Improve this question
It seems TensorFlow only supports CUDA and not OpenCL.
I saw the tensorflow-cl project, which compiles the CUDA code into OpenCL, but it is still a development version which does not work in all cases.
My question is whether Google, TensorFlow's developer, will ever develop a multi-platform version of its tool (no, I do not mean the CPU only version). Are the features of proprietary CUDA so critical to focus on a single GPU vendor? Are there any plans to develop an OpenCL/Vulkan/SPIR-V version at anytime in the future?
The answer is obviously yes, and Tensorflow started supporting OpenCL SYCL in the last few weeks, still in the master github branch and with few basic kernels. Many other kernels need to be written in the new format and contributions are welcome.