User Portlet
Featured Contributor
| Discussions |
|---|
| Very neat! It seems like the feathering and multi-scale Laplacian image blending could be trivially modified to produce tileable texture images for graphics. I am curious how combining the two approaches works as well. Perhaps a good function... |
| Edit (in 2022, WL v13.1), it appears that several of these issues have been fixed. The NetTrain progress reporting graph no longer makes the Documentation UI completely unusable, re-running NetTrain in the same WL kernel no longer causes GPU memory... |
| This is absolutely amazing! I never thought to use finite difference methods inside the loss function to compute derivatives. I tried to build PINNs in WL [in the past](https://community.wolfram.com/groups/-/m/t/2298967), but I gave up after... |
| I created a chart to help express my point: &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/c9ac831a-cc54-444e-b8eb-5a04425990aa |
| Using NeuralNetworks`ClearCache[] appears to free some CPU memory, but it does nothing to the GB of data sitting in my valuable GPU memory. This becomes a major problem when you are doing training and quickly trying to test architectures and... |
| ![enter image description here][1]![enter image description here][2] &[Wolfram Notebook][3] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Screenshot2022-02-22222503.jpg&userId=20103 [2]:... |
| What OS are you using? I have noticed that the Windows desktop GUI tends to be much less responsive than the MacOS one. It would be good to report it; I hope Wolfram keeps track of GUI responsiveness problems and prioritizes performance fixes over... |
| &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/cc535bd8-c504-4d33-8147-41e164c8c6ae |
| 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... |
| Direct transfer of data to a Python environment is absolutely possible using [ExternalEvaluate](https://reference.wolfram.com/language/ref/ExternalEvaluate.html). See this simple example of using the numpy library with your test data (note that... |