Comments (12)
I seen only main(), and understand that you need scalable input and output
parameters for range [-1, 1]. For example:
inp = inp / 10
tar = tar / 40
error=net.train(inp, tar, show=50, goal=0.0001)
Default output activation function may generate output range [-1, 1].
I also chenge goal of training for get better result
Original comment by [email protected]
on 11 Mar 2013 at 3:31
from neurolab.
please do check the train function..
my input data are accelerometer data and target is 4 nodes with 3 zeros and
one 1 indicating the pattern
Original comment by sarath.sp06
on 11 Mar 2013 at 4:26
from neurolab.
I need train samples for check it
Original comment by [email protected]
on 12 Mar 2013 at 8:11
from neurolab.
sure here is the input and output[target]
Original comment by sarath.sp06
on 13 Mar 2013 at 10:24
Attachments:
from neurolab.
1) You file in difficult format
2) Arrays have a different lenght (input 395, target 87). I cut input array
3) Output SSE error of train range in [15; 5]. My best result 1.0, I think it
is norm (see train_result.png)
Original comment by [email protected]
on 13 Mar 2013 at 5:51
Attachments:
from neurolab.
Thank you let me is itwould work for me...Can you please let me know what
should be the net , training fn etc to be used for this..
Original comment by sarath.sp06
on 14 Mar 2013 at 3:10
from neurolab.
Epoch: 10; Error: 40.4550766464;
Epoch: 20; Error: 37.7631905921;
Epoch: 30; Error: 35.7498408171;
Epoch: 40; Error: 34.8640337229;
Epoch: 50; Error: 34.3089574896;
Epoch: 60; Error: 33.3786583596;
Epoch: 70; Error: 33.3756710823;
Epoch: 80; Error: 33.3753713557;
Epoch: 90; Error: 33.3730166875;
this is the output i got as i run your code in my fedora with the same
files as you uploaded
Original comment by sarath.sp06
on 14 Mar 2013 at 4:31
from neurolab.
And? Train algorithm find local minimum, it is normally. Run script again
Original comment by [email protected]
on 15 Mar 2013 at 7:04
from neurolab.
got it but am now facing another problem that is i can not load my net
using nl.net error is
File "./pro.py", line 45, in <module>
main_()
File "./pro.py", line 35, in main_
gesture=simulate(data14);
File "/home/sarath/gesture/my_part/ann.py", line 40, in simulate
net=get_net()
File "/home/sarath/gesture/my_part/t_sim.py", line 13, in main
net=nl.load('net.net')
File
"/usr/lib/python2.7/site-packages/neurolab-0.2.0-py2.7.egg/neurolab/tool.py",
line 54, in load
with open(fname, 'r') as file:
IOError: [Errno 2] No such file or directory: 'net.net'
but when i run script in an another folder with same function its working
fine am here by uploading the code ,
the problem is in file ann.py function simulate0
Original comment by sarath.sp06
on 17 Mar 2013 at 4:46
from neurolab.
>>>nl.load('net.net')
set absolute path to 'net.net' file
Original comment by [email protected]
on 19 Mar 2013 at 8:19
from neurolab.
Original comment by [email protected]
on 15 Apr 2013 at 6:24
- Changed state: Done
from neurolab.
yeah did it got it working thanks,i just completed my project work
Original comment by sarath.sp06
on 15 Apr 2013 at 1:52
from neurolab.
Related Issues (20)
- Failing to add Levenberg-Marquardt-training HOT 5
- Problem when using a modified network property HOT 1
- PureLin in outputl layer does not work HOT 2
- Setup issue HOT 3
- strange result HOT 13
- Cannot install successfully for Python 3.2 HOT 5
- Learning Rate is not present HOT 2
- Multiprocessing can not pickle unbound function HOT 6
- cannot save nn HOT 2
- output norm and different resutls HOT 1
- Citing neurolab HOT 3
- Parameters Ignored in Training Function Construction HOT 2
- Training Fails for Non-Default Activation Functions HOT 1
- Linear Activation Leads to NaN minmax HOT 2
- Support for weight decay (regularization parameter) HOT 2
- Missing newelm example in doc HOT 3
- fmin_bfgs() got an unexpected keyword argument 'lr', train func does not take lr as parameter HOT 2
- Added regularization and cross-entropy error to Neurolab HOT 5
- 0.3.5 version not available in pypi HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from neurolab.