User Portlet User Portlet

Discussions
Also, 'RoundLength' turns out to be 'the number of samples that is expected to be seen during a Round (epoch)', so it should be equal to the number of training samples, 'ntrain' in this case: trained = NetTrain[net, {genTrain,...
Hi, Thank you for your reply. After reading the dataset into RAM my dataset exists as a linear array of multiples of 24 bytes in RAM. Suppose the batch size is 65536. For the next batch I have to take the next block of (65536, 24) bytes of my...
Hi, I have a dataset of 192 binary inputs (0/1) and corresponding outputs. I have compressed the inputs to 24 8-bit integers, so that the entire dataset can fit into RAM which greatly speeds up training of the neural network. Obviously, before a...
Please see [FunctionLayer error compilerr: Cannot interpret as a network][1] for a way to achieve this using NetEncoder. Regards, GW [1]: https://community.wolfram.com/groups/-/m/t/3096538
Thank you! I modified your function to support the 24 8-bit integers expanding to 192 integers as follows: NetEncoder[{"Function", Flatten[IntegerDigits[#, 2, 8]] &, {192}}] and the following commands indeed produce the same output: ...
Hi, After some lengthy troubleshooting I managed to narrow down the issue to the title. I am running Mathematica 13.1 on Zorin OS 16.2. Anyone else seeing this? Thanks, GW
Hi, I want to use a custom LossFunction (in particular, a loss function that calculates the q'th percentile of the absolute differences), but I cannot figure out how to do this from the documentation. Through some educated guessing I found out...
I am running Mathematica 13.1 on Zorin OS 16.1. I just upgraded CUDA to version 11.7 but CUDALink now raises the following error: Directory /usr/local/cuda-11.6/bin does not exist. Is CUDA 11.7 already supported? Thanks, GW
Hi, I now see that I have not updated this question with the answer. It turned out that my input vectors were 'too random'. The use case was to train a neural network on a number of international draughts positions. If you choose a collection of...
Hi, As MeanSquaredLossLayer did not seem a suitable LossFunction for my network, I wanted to try other LossFunctions. The documentation says that you can use 'any network with an "Input" and optional "Target" port' as a LossFunction, but it was not...