Activity for deconf
-
deconf posted a comment on discussion Help
you should recompile entire library in amd64
-
i think this can be related to mysql performance shema is staled updating (or similar query thread stalls)
-
np
-
yes of course, but this is what u need
-
1) you can, just expand old dataset with additional parameters in/out 2) you can try, but possibly this will not work (or will work but on very very long train)
-
first of all, AI (fann/other) is just a NS name for neural networks. they can't learn game, they can ADOPT to games in repeated battles (if u construct some points system. be aware: agent way is error.yes), if u make million builds&runs (use met) and trying logic blocks mutating system, but u always should create logic rules, and this what comes me in mind can be mined like bitcoin s on gpu. what a idea.
-
sorry i need to kill u now
-
first of all, AI (fann/other) is just a NS name for neural networks. they can't learn game, they can ADOPT to games in repeated battles, if u make million builds&runs (use met) and trying logic blocks mutating system, but u always should create logic rules, and this what comes me in mind can be mined like bitcoin s on gpu. what a idea.
-
Moderation posting await.
-
Post awaiting moderation
-
Post awaiting moderation.
-
"that takes the type"
-
"that takes the type"
-
Post awaiting moderation.
-
Post awaiting moderation.
-
Post awaiting moderation.
-
Post awaiting moderation.
-
\rPost awaiting moderation.
-
Post awaiting moderation.
-
or what
-
google 'nvidia ai'/'google ai'
-
looks like fann is abandoned and new technologies from nvidia/google should be tryed
-
try version as stated in .fann file [at top]
-
paste your network file at pastebin
-
try to open this network using latest FANN version
-
http://leenissen.dk/fann/html/files/fann_error-h.html your error is "FANN_E_CANT_READ_TD"
-
change library version
-
Hi, i can't find documentation on how to scale input data before feed it to network using FANNCSharp lib. It has Scaleinput(DataAccessor dac), but how do i construct such object?
-
that is not my project =) really the forum is almost dead for last 3 years
-
http://joelself.github.io/FannCSharp/files/NeuralNetFloat-cs.html https://mac-blog.org.ua/c-fann-example-raspoznavanie-s-ispolzovaniem-neyronnoy-seti/
-
yes, np
-
yes
-
hi, you can't just use image as input, you will need to translate image into X,Y coordinates with color in each cell, so it would be widthXheight inputs.
-
you will need to make additional program logic to distinct washing phases in your scenario. i think such approach to predict phase only by NN is very hard. but if washing phases power consumption is depend on previous phases, it is possible.
-
you will need to make additional program logic to distinct washing phases in your scenario. i think such approach to predict phase only by NN is very hard
-
maybe u can use amount of unwashed material for that? (<unwashed>/<washed>)*100.0
-
maybe u can use amount of unwashed material for that?
-
yes, it is possible using fann. but using historical data of power (consuption you mean?) is not the best. you need to make deeper research.
-
as first, use fanntool before do any coding, to be sure you have correct train data
-
do you have correct output from trained in fanntool network?
-
try to use fanntool before writing code. Firstly make & train network in fanntool to ensure you have correct input and output train data
-
try using double library
-
wich library type you using - float or double? try change this
-
do you have success with fann samples?
-
you're using random values as input, what do you want to expect?
-
try to find file fanndouble.dll and check the directory is in your env PATH
-
did you add fann library with nuget?
-
it also should show the error detail of exception, check the logs
-
there is much big count of descriptions of what "Artificial intelligence" is, so...
-
yes, someone has train car to drive, so i think image recognition is supported
-
you can only try that, there is no pretty sure and all success is based on how good...
-
you can only try that, there is no pretty sure
-
with simple functions like y=5x
-
in fann (not FANTool) you can create sparse and other types of networks, if you sure...
-
good, so you finded working combination?
-
good, so you find working combination?
-
so, you have error in your train data and this should be resolved before you write...
-
so, you have error in your train data and this should be resolved before you write...
-
ok but do you got correct output (as you expected) in FANNTool ?
-
is this train data or just one input?
-
yes of course
-
all inputs and outputs should be scaled/descaled
-
is your network producing good results in FANNTool ?
-
you need http://libfann.github.io/fann/docs/files/fann_train-h.html#fann_descale...
-
you again skipped scaling on input params
-
if you have success with train output in FANNTool you can use this network.
-
fann is working, i have practices with it and it gives right results if designed...
-
in the previous code you load the network to test it, but you did not descaling the...
-
if you want to use fann you should download FANNTool and do in it design and train...
-
fann_save(ann, "sinus.net"); fann_destroy(ann); <--- you destroing the network printf("test...
-
http://libfann.github.io/fann/docs/files/fann_train-h.html fann_scale_train Scale...
-
strange input and output... you should scale your train input/output to be in range...
-
show part of your train data
-
dunno
-
yes
-
if you use 100 epochs it will iterate over all 500 data lines 100 times
-
epoch is a one train iteration over all train data
-
backprogranation function is used in training, when network adjusts their neurons...
-
how do you will know what network has calculated on this data? you should know neural...
-
you cant just start it, because you compiled the library, its output is fann*.dll,...
-
yes
-
FANN Tool has source code, you can compile and test is as you wish
-
you probaby opening the network which was made by higher version of FANN library
-
you probaby opening the network wich is designed for higher version of FANN
-
You training only one epoch in the loop, this is not enough, you should have hundreths...
-
interesting IDE, never see it i will try to use fann in it
-
interesting IDE, never see it
-
interesting IDE, never see it, but i am now learning c#. Does it have gui design...
-
i have minimal skills about c#, but yes it is strange that errors is same, try maybe...
-
you should try linking with fanndouble
-
you cant run program until you compiled it, show linker errors output here
-
the another quick answer is yes, you can use it but you need to extract some data...
-
there is plenty big count of docs about predicting using timeseries in the network,...
-
hi, i dont know c# very good but if it have double type for digits you might have...
-
hmm. i think you did overtrain of network. it is possible than simple fann example...
-
i did not used parallel training but try to use different train algorithms
-
:)
-
what type of fann library do you use, float or double? and you did not specify the...
-
what type of fann library do you use, float or double?
-
try to use FANNTool with your data
1 >