FANN 2.2.0 has been released, after almost 5 years since the last release.
Since the last release there has been more than 230,000 FANN downloads, so hoping that this new release will be just as popular.
Version 2.2.0 is backwards compatible and adds the following new features:
- Added Sarprop training
- Added fann_create_train for creating an empty training data struct
- Added fann_copy for copying an ANN
- Added cascade_min_out_epochs and cascade_min_cand_epochs to improve cascade training
- Added extra checks when training, to ensure that data and network input and output sizes matches
- Added Visual Studio 2010 solution
- Added support for 64bit architecture
- Cleanup in sources
- Moved source from CVS to GIT
For now there is only a source release (includes windows binaries), but have been playing around with CPACK, and a binary release should be coming soon.
very good, i will do now my projects with the fann new version
Great news!
It seems language bindings aren’t included in the package?
No, in order to make the release more clean, only C/C++ is included in the release.
Hi Steffen,
Where can I find the language bindings for Python? They are not included in the download package and the “Python FANN” link on the language bindings page does not lead anywhere.
Thanks.
Hi Steffen,
First of all: great work you share
Like other comments, I’m wondering if getting the Python binding will be possible later ?
As I clone the git repo and didn’t found out these neither.
Thanks
Python is part of the FANN 2.1.0, but since this binding is not developed by the same developer as the main FANN library, it has not been updated for version 2.2.0.
The Language Bindings page has been updated to reflect this.
Having recently discovered FANN, am very much looking forward to using it in my projects from now on. Keep up the good work.
Hi Steffen,
Any word about CUDA? Would make a world of difference!
Thanks,
Jason
Hi, Steffen,
Is the scaling issue fixed in this new release ?
Thanks,
Mei
Disculpa, donde podría encontrar documentación acerca de como puedo utilizar la aplicación ?
Gracias por la atención prestada
Hello I need a java example done for the library is that I need to do a project in java pattern recognition and can not find information about this language …
Anyone can help me