User Portlet
| Discussions |
|---|
| No offense but I think that Wolfram should have released new NN backend with 14.0 already. Moving too slowly in this key field. And ExternalEvaluate support for Python and Julia etc. is about the same as crippling. |
| We haven't added any feature to `ImageAugmentationLayer`, but I don't see any reason why you shouldn't be able to achieve what you want by using the "generator" syntax of `NetTrain` as I mentioned in my old reply. Your generator function should grab... |
| > About numerical vs image data: There is absolutely no difference > between them from the neural net perspective. Images are immediately > turned into numerical data by NetEncoder["Image"] Thats what I figured, which is why I couldnt understand... |
| So, is there like a "complete code" or a "workbook" version we can play with? As opposed to attempting to assemble it ourselves from scratch? ^_^ I'd love to play with this, at some point. And can it only work with neural networks trained on a... |
| **UPDATE**: Even though the Weights show up in Red, if I use NetExtract on the nested NetChains, they seem to have legit values. So maybe I'm fine. Testing now... -- Seems to be fine, which is great. Sorry for the false alarm, although I still don't... |