fann_set_bit_fail_limit() fails to actually set the bit fail limit, forcing me to manually edit the ANN file
struct fann *ann;
ann = fann_create_standard(3, 600, 1200, 30);
fann_set_activation_function_hidden(ann, FANN_SIGMOID);
fann_set_activation_function_output(ann, FANN_SIGMOID);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Whenever I load this neural network from the file and read fann_get_bit_fail_limit()
, the returned value is the default 0.35 instead of the 0.002 I tried to set. I have to edit the ANN file manually for it to take effect.
I am using doublefann.h
. Am I doing something wrong?
c++ fann
add a comment |
struct fann *ann;
ann = fann_create_standard(3, 600, 1200, 30);
fann_set_activation_function_hidden(ann, FANN_SIGMOID);
fann_set_activation_function_output(ann, FANN_SIGMOID);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Whenever I load this neural network from the file and read fann_get_bit_fail_limit()
, the returned value is the default 0.35 instead of the 0.002 I tried to set. I have to edit the ANN file manually for it to take effect.
I am using doublefann.h
. Am I doing something wrong?
c++ fann
add a comment |
struct fann *ann;
ann = fann_create_standard(3, 600, 1200, 30);
fann_set_activation_function_hidden(ann, FANN_SIGMOID);
fann_set_activation_function_output(ann, FANN_SIGMOID);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Whenever I load this neural network from the file and read fann_get_bit_fail_limit()
, the returned value is the default 0.35 instead of the 0.002 I tried to set. I have to edit the ANN file manually for it to take effect.
I am using doublefann.h
. Am I doing something wrong?
c++ fann
struct fann *ann;
ann = fann_create_standard(3, 600, 1200, 30);
fann_set_activation_function_hidden(ann, FANN_SIGMOID);
fann_set_activation_function_output(ann, FANN_SIGMOID);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Whenever I load this neural network from the file and read fann_get_bit_fail_limit()
, the returned value is the default 0.35 instead of the 0.002 I tried to set. I have to edit the ANN file manually for it to take effect.
I am using doublefann.h
. Am I doing something wrong?
c++ fann
c++ fann
asked Nov 24 '18 at 23:18
daedsidogdaedsidog
1,3362828
1,3362828
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
"Am I doing something wrong?"
As per Documentation - FANN Training > Parameters > fann_get_bit_fail_limit
(emphasis added) :
The bit fail limit is used during training where the fann_stopfunc_enum is set to
FANN_STOPFUNC_BIT
.
Example :
fann_set_train_stop_function(ann, FANN_STOPFUNC_BIT);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Just in case:
I am using
doublefann.h
.
Link -ldoublefann
instead of -lfann
.
I figured as such by myself by messing around with it. I did use the bit stop function, but it didn't occur to me to use it as a training function, because unlike the other training functions, this one does not begin withfann_set_train_
.
– daedsidog
Nov 25 '18 at 17:37
@daedsidog Training algorithm, -stop function and -error function are distinct parameters to the process;fann_set_train_error_function
hasFANN_ERRORFUNC_TANH
"... not recommended for cascade training and incremental training.".
– user4157124
Nov 26 '18 at 1:23
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53463226%2ffann-set-bit-fail-limit-fails-to-actually-set-the-bit-fail-limit-forcing-me-t%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
"Am I doing something wrong?"
As per Documentation - FANN Training > Parameters > fann_get_bit_fail_limit
(emphasis added) :
The bit fail limit is used during training where the fann_stopfunc_enum is set to
FANN_STOPFUNC_BIT
.
Example :
fann_set_train_stop_function(ann, FANN_STOPFUNC_BIT);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Just in case:
I am using
doublefann.h
.
Link -ldoublefann
instead of -lfann
.
I figured as such by myself by messing around with it. I did use the bit stop function, but it didn't occur to me to use it as a training function, because unlike the other training functions, this one does not begin withfann_set_train_
.
– daedsidog
Nov 25 '18 at 17:37
@daedsidog Training algorithm, -stop function and -error function are distinct parameters to the process;fann_set_train_error_function
hasFANN_ERRORFUNC_TANH
"... not recommended for cascade training and incremental training.".
– user4157124
Nov 26 '18 at 1:23
add a comment |
"Am I doing something wrong?"
As per Documentation - FANN Training > Parameters > fann_get_bit_fail_limit
(emphasis added) :
The bit fail limit is used during training where the fann_stopfunc_enum is set to
FANN_STOPFUNC_BIT
.
Example :
fann_set_train_stop_function(ann, FANN_STOPFUNC_BIT);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Just in case:
I am using
doublefann.h
.
Link -ldoublefann
instead of -lfann
.
I figured as such by myself by messing around with it. I did use the bit stop function, but it didn't occur to me to use it as a training function, because unlike the other training functions, this one does not begin withfann_set_train_
.
– daedsidog
Nov 25 '18 at 17:37
@daedsidog Training algorithm, -stop function and -error function are distinct parameters to the process;fann_set_train_error_function
hasFANN_ERRORFUNC_TANH
"... not recommended for cascade training and incremental training.".
– user4157124
Nov 26 '18 at 1:23
add a comment |
"Am I doing something wrong?"
As per Documentation - FANN Training > Parameters > fann_get_bit_fail_limit
(emphasis added) :
The bit fail limit is used during training where the fann_stopfunc_enum is set to
FANN_STOPFUNC_BIT
.
Example :
fann_set_train_stop_function(ann, FANN_STOPFUNC_BIT);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Just in case:
I am using
doublefann.h
.
Link -ldoublefann
instead of -lfann
.
"Am I doing something wrong?"
As per Documentation - FANN Training > Parameters > fann_get_bit_fail_limit
(emphasis added) :
The bit fail limit is used during training where the fann_stopfunc_enum is set to
FANN_STOPFUNC_BIT
.
Example :
fann_set_train_stop_function(ann, FANN_STOPFUNC_BIT);
fann_set_bit_fail_limit(ann, 0.002);
fann_save(ann, "ann.net");
Just in case:
I am using
doublefann.h
.
Link -ldoublefann
instead of -lfann
.
answered Nov 25 '18 at 15:17
user4157124user4157124
2,21451333
2,21451333
I figured as such by myself by messing around with it. I did use the bit stop function, but it didn't occur to me to use it as a training function, because unlike the other training functions, this one does not begin withfann_set_train_
.
– daedsidog
Nov 25 '18 at 17:37
@daedsidog Training algorithm, -stop function and -error function are distinct parameters to the process;fann_set_train_error_function
hasFANN_ERRORFUNC_TANH
"... not recommended for cascade training and incremental training.".
– user4157124
Nov 26 '18 at 1:23
add a comment |
I figured as such by myself by messing around with it. I did use the bit stop function, but it didn't occur to me to use it as a training function, because unlike the other training functions, this one does not begin withfann_set_train_
.
– daedsidog
Nov 25 '18 at 17:37
@daedsidog Training algorithm, -stop function and -error function are distinct parameters to the process;fann_set_train_error_function
hasFANN_ERRORFUNC_TANH
"... not recommended for cascade training and incremental training.".
– user4157124
Nov 26 '18 at 1:23
I figured as such by myself by messing around with it. I did use the bit stop function, but it didn't occur to me to use it as a training function, because unlike the other training functions, this one does not begin with
fann_set_train_
.– daedsidog
Nov 25 '18 at 17:37
I figured as such by myself by messing around with it. I did use the bit stop function, but it didn't occur to me to use it as a training function, because unlike the other training functions, this one does not begin with
fann_set_train_
.– daedsidog
Nov 25 '18 at 17:37
@daedsidog Training algorithm, -stop function and -error function are distinct parameters to the process;
fann_set_train_error_function
has FANN_ERRORFUNC_TANH
"... not recommended for cascade training and incremental training.".– user4157124
Nov 26 '18 at 1:23
@daedsidog Training algorithm, -stop function and -error function are distinct parameters to the process;
fann_set_train_error_function
has FANN_ERRORFUNC_TANH
"... not recommended for cascade training and incremental training.".– user4157124
Nov 26 '18 at 1:23
add a comment |
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53463226%2ffann-set-bit-fail-limit-fails-to-actually-set-the-bit-fail-limit-forcing-me-t%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown