User Portlet
Featured Contributor
| Discussions |
|---|
| I do not think anything is specifically built in, but there is support for spinning up (or connecting to existing) AWS instances. It would probably largely be a manual process of sharding your own data into whatever servers you want to use then... |
| As an update for anyone else who finds this thread, I found a list of currently supported CUDA Compute Capabilities in [the NetTrain TargetDevice documentation](https://reference.wolfram.com/language/ref/TargetDevice.html) section (kinda an obvious... |
| Yea, I am doing WL training on my desktop, which has a GTX 1060 6gb and an RTX 2060. I might use one GPU and leave the other open for experimentation while my main model trains, then use both GPUs when I am not experimenting anymore. My biggest... |
| You can extract this information from the trained net results object, but typically, I have observed "Automatic" settings mean ADAM optimizer. |
| +1 It would be great to have documentation about these things. These super-powerful functions (Classify and Predict) are really difficult to use in production environments as long as the documentation of procedures employed is so sparse and the... |
| Unfortunately, training transformers is slightly more complicated. You would need to add code for the loss function. You could instead train a simple (non-transformer) text classifier in Mathematica using the... |
| My bad! I forgot to link the repository! (edited main post) |
| I have discovered some more possible solutions: There are other functions like "FindFit" and "TimeSeriesForcast" that could be applicable since you already have TimeSeries data. I saw a list of Wolfram Language functions at the bottom of this... |
| Hello! I have really been enjoying the ```"MicrocontrollerKit`"``` and the ability to simply generate and deploy code for arbitrary discrete state space models. I have seen a few videos from Mr. Suba Thomas who seems to be working hard on this... |
| Hello, I am trying to learn ```"MicrocontrollerKit`"```, and I came across a strange issue with some example code. It appears that when using a specific target, "ArduinoMicro", compilation always fails with an error, regardless of what model I am... |