Group Abstract Group Abstract

Message Boards Message Boards

Wolfram Neural Net Repository (WNNR) and model discussions

Test Account
Posted 4 years ago
POSTED BY: Test Account
5 Replies
Sort By:
Test Account
Test Account
Posted 3 years ago
POSTED BY: Test Account
Updating Name
Updating Name
Posted 4 years ago

Question 3: Additional Sections

It is hard to think of anything super critical. More documentation of transfer learning in complicated architectures would be nice.

Standard benchmarks for runtime performance on CPU/GPU would be nice, and it would be a great intern project to set up an automated test suite using wolframscript on a Linux GPU docker container that downloads and runs the ‘example usage’ section of each network in WNNR and records average CPU/GPU runtime speed on standardized example data. Results could automatically be uploaded to the Data Repository and visualized on the WNNR website. This test could also measure performance between WL-NN releases and GPU driver updates and hardware versions. Such a detailed reference does not exist as far as I know, and it would be super helpful for fully understanding the speed and accuracy tradeoffs of different networks. It would also be insightful to track baseline performance on real-world hardware over time. The size of WNNR makes it well-suited to this kind of analysis and comparison of networks.
POSTED BY: Updating Name
Alec Graves
Alec Graves
Posted 4 years ago

Also, RE: adding sections explaining the architectures,

I do not think this would be very helpful to me. It seems like it would take a lot of technical work to make sure these explanations are very accurate and suitable for use as a professional reference. Furthermore, as someone wise once said, “Truth can only be found in one place: the code.” I can gather a lot of 100% accurate detail about the architecture very quickly simply by looking at the architecture graph (a very nice part of the WL NN library).

I would like to see slightly more elaboration in the brief description at the top of the page of some architectures, but having long Shingle-page explanations of the architecture would provide little value to me personally.

Thanks for asking :)
POSTED BY: Alec Graves
Updating Name
Updating Name
Posted 4 years ago
POSTED BY: Updating Name
Rohit Namjoshi
Rohit Namjoshi
Posted 4 years ago

Crossposted here.
POSTED BY: Rohit Namjoshi