deepLearn.c

Gamestudio Links

Zorro Links

Data from CSV not parsed correctly
by EternallyCurious. 04/20/24 21:39

M1 Oversampling
by 11honza11. 04/20/24 20:57

Scripts not found
by juergen_wue. 04/20/24 18:51

zorro 64bit command line support
by 7th_zorro. 04/20/24 10:06

folder management functions
by VoroneTZ. 04/17/24 06:52

AUM Magazine

Latest Screens

2 registered members (AndrewAMD, rki), 390 guests, and 0 spiders.

Key: Admin, Global Mod, Mod

Newest Members

Print Thread

Rate Thread

deepLearn.c #477575 07/09/19 19:50 07/09/19 19:50
Joined: May 2015 Posts: 390 Czech Republic G Grat OP Senior Member
Grat OP Senior Member G Joined: May 2015 Posts: 390 Czech Republic	Hi, I trying demo script DeepLearn.c and I have a few question: a) at first train with this option? Code #define DO_SIGNALS // generate sample set in Train mode //#define DEEPNET //#define H2O //#define MXNET //#define KERAS this create file: Train EURUSD_L -Jul 2019- => DeepLearn_EURUSD_L.csv sec train with this? Code //#define DO_SIGNALS // generate sample set in Train mode #define KERAS this use script: Code #ifdef KERAS Script = "DeepLearnKeras"; #endif in script DeepLearnKeras.r is the function Code neural.test = function() { neural.init() XY <<- read.csv('MyZorroPath/Data/DeepLearnKeras.csv',header = F) my basic question is - csv in this funstion have a different name with generated CSV. This is correct? DeepLearn_EURUSD_L.csv versus DeepLearnKeras.csv is any rules for this names? I cannot find anwser into manual... Last edited by Grat; 07/09/19 19:52.

Re: deepLearn.c [Re: Grat] #477578 07/10/19 08:31 07/10/19 08:31
Joined: Jul 2000 Posts: 27,982 Frankfurt jcl Chief Engineer
jcl Chief Engineer Joined: Jul 2000 Posts: 27,982 Frankfurt	There is no rule. You can change the csv file name for testing and calibrating the neural net. This is a manual process, not automated.

Moderated by Petra