# User Portlet

Sebastian Bodenstein
Discussions
> is important not to miss this issues before the data gets stored and starts to grow. Use MongoDB schema validation in this case to prevent invalid data from being inserted into the database:...
The issue is that the neural net framework of 11.3 was compiled against CUDA Toolkit 9.0, which is incompatible with the new Turing generation GPUs (ie the 2080). CUDA 10 was only released around 10 days ago, and it added support ("CUDA 10 is the...
> What I really need is a simple example invocation of NetTrain for the networks. That may be the way to go about this. Originally, we thought we would need to give a full training example and replicate the results of something trained in a...
Using a custom loss is documented in the 3rd example of the LossFunction documentation: http://reference.wolfram.com/language/ref/LossFunction.html. That whole page is useful for understanding how to control losses.
That is correct. Note also: we should have some reinforcement learning examples in the upcoming 12 release documentation. We are busy adding a simple feature to the neural net framework that will allow you train agents using using the recently...
You should add MXNet to the list: this is what the Wolfram Language is using underneath.
PNG is usually (always?) compressed. When its imported into the WL, the size increases (sometimes quite dramatically), as its stored as an uncompressed array in memory. This is one major advantage of out-of-core training: you can store all your...
> Sorry to say Sebastian, but you are really out of touch with what got delivered to your customers with 11.3 release.... > Your team member (and customers) had to tell you that the CUDA paclet was downgraded with 11.3 release I am one of the...
[@narendra ][at0]: out of curiosity, is there are particular activation you are trying to implement yourself? [at0]: http://community.wolfram.com/web/narendra
Your NetChain outputs a vector of length 30, and you are trying to feed this into a NetDecoder that expecting only 10 inputs. Hence the error. So something like this will work: NetChain[{LinearLayer[10]}, "Input" -> NetEncoder[{"Image",...