Git Product home page Git Product logo

fanntool's Introduction

fanntool

fanntool's People

Contributors

googlecodeexporter avatar

Watchers

 avatar

fanntool's Issues

Some tweaks: Continue training, graph Y axis ticks

I have made some useful (for me) changes to the code, which might be useful to 
others.

The changes are:
- Add ticks and labels to Y axis
- Add Training normal continued menu option, to continue with training a network
- Make normal train log messages have 8 decimal places
- Add menu option to show info of neural net currently in memory. 

The main two issues are: 1) being able to stop training, tweak training values, 
and continue from where you left off.
And 2), the graph shows a scale so its clear how fast the error is really 
changing.

I would be happy to provide the changes for consideration on inclusion in the 
main code.

Original issue reported on code.google.com by [email protected] on 5 Aug 2014 at 8:06

Hidden Layer 1 size spin box has maximum size limit of 100

What steps will reproduce the problem?
1. Use training data with input vector size of 500 
2. Adjust the Hid. Layer 1 spin box

What is the expected output? What do you see instead?

It should be possible to set the hidden layer size to any integer number > 0, 
instead it seems to have a maximum value of 100.

What version of the product are you using? On what operating system?

Fanntool 1.1, Linux 64-bit

Please provide any additional information below.


Original issue reported on code.google.com by [email protected] on 7 Mar 2012 at 2:50

How to reuse the saved neural network in python?

What steps will reproduce the problem?
1. Trained a neural network using FANN Tool 1.2
2. Saved it.
3. Tried to use it in Python using Neurolab

What is the expected output? What do you see instead?

Expected to see the output. However it is not recognized by neurolab in Python.

What version of the product are you using? On what operating system?

Using FANN Tool 1.2 in Windows 7 64 bit machine

Please provide any additional information below.

Want to know which platform the saved neural network can be reused. Preferably 
in Python or Matlab. Also want to know how the data is processed in FANN Tool 
1.2. Is it similar to mapminmax function in Matlab? or some other normalization 
method 

Original issue reported on code.google.com by [email protected] on 10 Feb 2015 at 12:19

OS Compatibility issue

What steps will reproduce the problem?
1. create network in FANNtool on linux
2. use network in FANNtool on windows
3.


What version of the product are you using? On what operating system?
FANNtool 1.1, ubuntu 11.10 x64, windows 7 x64

Please provide any additional information below.
when i try to use trained file .net in windows wersion, FANNtool falls down

Original issue reported on code.google.com by [email protected] on 9 Jan 2012 at 2:52

Output not descaled to real values

What steps will reproduce the problem?
1. Run the saved Neural network file in FANN Tool 1.2
2. Choose the neural network file. 
3. Enter the scaled inputs
4. Click on Run

What is the expected output? What do you see instead?

Expected a descaled output to real value. But getting scaled output instead.

What version of the product are you using? On what operating system?

FANN Tool 1.2 in Windows 7 64 bit machine

Please provide any additional information below.

would like to know how the descaled output can be obtained.

Original issue reported on code.google.com by [email protected] on 10 Feb 2015 at 12:31

Makefile for Ubuntu 14.04

In case you would like to include it in the distribution:

ODIR = obj
FLAGS = -Wno-write-strings -fpermissive -Wno-format-security -Wno-format 
-I/usr/local/include
OBJ = $(ODIR)/DataProcess.o $(ODIR)/fl_ext_file_chooser.o $(ODIR)/Fl_PlotXY.o 
$(ODIR)/main.o $(ODIR)/Rotated.o
LIBRARIES = -lfltk -lXext -lXpm -lfann -lm -lstdc++ -Wl,-Bsymbolic-functions 
-lfltk -lX11 -lfltk_images

$(ODIR)/%.o: %.cpp
        g++ -c -o $@ $(FLAGS) $< -I.
$(ODIR)/%.o: %.cxx
        g++ -c -o $@ $(FLAGS) $< -I.
$(ODIR)/%.o: %.C
        g++ -c -o $@ $(FLAGS) $< -I.
$(ODIR)/%.o: %.c
        gcc -c -o $@ $(FLAGS) $< -I.
FannTool: $(OBJ)
        gcc -o $@ $^ -I. $(LIBRARIES)
clean:
        rm $(ODIR)/*.o

Original issue reported on code.google.com by [email protected] on 5 Aug 2014 at 8:02

Enter one-line summary

Fanntool v.0.60 ANN Training (clicking on the lightning bolt) not
implemented yet?
Timeframe?

Original issue reported on code.google.com by [email protected] on 2 Jul 2007 at 8:03

GUI keeps openning browser window

When selecting dat files via GUI, program keeps openning browser window, even 
after choosing appropriate dat file, so program is unusable.
Sometimes I can avoid openning the window fastly clicking ESC button and then 
choosing Return to program button. But it don't work in all cases.

Original issue reported on code.google.com by [email protected] on 10 Dec 2011 at 8:50

source typo

What steps will reproduce the problem?
1. open file main.cpp in editor
2. goto line 2040
3. read carefully

What is the expected output? 
line 2042:      Hid3->value(0);

What do you see instead?
line 2042:      Hid2->value(0);

What version of the product are you using? On what operating system?
0.93

Please provide any additional information below.
easy mistake to make ;)

Original issue reported on code.google.com by [email protected] on 5 Aug 2008 at 3:13

core dump in FannTool

What steps will reproduce the problem?
1. load a file with completely wrong format into FannTool
2. a core dump will show up. some error checkbox with some hint would be
nice :)

What is the expected output? What do you see instead?
core dump => message box with some lovely hint


What version of the product are you using? On what operating system?
it happened on linux

Original issue reported on code.google.com by [email protected] on 18 Jun 2009 at 8:12

UI problem

Nothing related to functionality but I'm using a 17" widescreen LCD. I
can't see the bottom lines of the UI. It's better if you can make it
resizable. :)


Original issue reported on code.google.com by [email protected] on 5 Jul 2009 at 7:19

Attachments:

Using doublefann for greater precision

What steps will reproduce the problem?
1. Replace the #include <fann.h> line with #include <doublefann.h>
2. Compile & run
3. Train on test data

What is the expected output? What do you see instead?
I expected to see the MSE gradually decreasing
Instead, the MSE stays constant

What version of the product are you using? On what operating system?
Fanntool 2.2, FANN 2.2, Ubuntu 14.04

Please provide any additional information below.


Original issue reported on code.google.com by [email protected] on 9 Aug 2014 at 7:46

open file window can not be closed

What steps will reproduce the problem?
1. in the "Training Data file" open file line or "test data file" line
2. click "..." tab on the right side of blue square, the open file window will 
not closed until you click many times 
3. or will not be responded. sometimes crashed.

What is the expected output? What do you see instead?

should be able to close the windows.
What version of the product are you using? On what operating system?
1.2

Please provide any additional information below.


Original issue reported on code.google.com by [email protected] on 21 Mar 2013 at 6:31

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.