![]() Since I am at it, any chance to do something like deep learning too? I know there's tons of possibilities already but since it seems to be a very important subject, now and in the future, it would be very cool to have it (ready for Igor 9!). From the Crash Report I see that USEDPHYSMEM is 1/40 of PHYSMEM, and FREEMEM is much, much higher. Igor Pro 9 Changed and New Features How to update Previous versions. Besides my Igor has done more demanding things than that, without crashing. I'm thinking that if the PC can train on 21 curves, it shouldn't be a matter of resources to apply the model to 1 curve. I tried to kill the weights waves, re-run the training and re-run the run -> crash I have shortcuts to them placed in: C:UsersMYNAMEDocumentsWaveMetricsIgor Pro 6 User FilesIgor Extensions. The actual extension files are in C:Program Files (x86)WaveMetricsIgor Pro FolderIgor Extensions. NeuralNetworkRun Input=test, WeightsWave1=M_weights1, WeightsWave2=M_weights2 Im trying to use a few basic extensions such as FindPeaks and AnnotationTools. I'm shocked, never seen Igor crashing :) I tried several times, on two computers (both Windows 10), with 2 Igor versions (I think 6.37 and 8.02), continuously crashing on me. Actually the first curve/row of the input wave just to see how it works), Igor crashes. Now the disappointing part: when I try to run the neural network on a test wave (1 row, ~5000 columns. The RMS error is kind of high, 0.05, but as said it is as good as it gets with old school directly programming. ![]() Very cool, I leave the PC running and the day after I find out that a simple network can apparently predict that one single parameter with the same accuracy as applying a physical model and tuning the fitting parameters (done separately). Since I am not familiar with learning rate, momentum etc., in particular for this small data set, I went brute force with 3 nested loops changing the nodes and these parameters, recording the best RMS error. My output wave has only 1 column and 21 rows. So my input wave has 21 rows and ~5000 columns. Support Information Customer Support: Technical Support: Mailing Address: WaveMetrics, P.O. I know 21 is not really a lot but this is what I have and I guess it is good enough to start learning. I have 21 experimental curves with ~5000 Points, and I am trying to predict one single parameter, coming from a different kind of test, from each curve. Wide-Angle Neutron Spin Echo SpectroscopyĬan you please help me on this one: I am using neural networks in Igor, I understand it would be better to go for something like Keras but I decided to give it a try given my experience in Igor and my love for it. It will work best at 100 scaling if you have set it to 120 (which is pretty common for people who want things to appear somewhat bigger) it will probably have troubles with font sizes in various places.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |