search

jorgenkg / python-neural-network

This is an efficient implementation of a fully connected neural network in NumPy. The network can be trained by a variety of learning algorithms: backpropagation, resilient backpropagation and scaled conjugate gradient learning. The network has been developed with PYPY in mind.
BSD 2-Clause "Simplified" License
297 stars 98 forks source link

Support for python 3.+ #20

Closed NEGU93 closed 7 years ago

NEGU93 commented 7 years ago

I got the following:

Traceback (most recent call last):
  File "C:/Users/josea/Dropbox/ITBA/Redes Neuronales/ECG/src/main.py", line 5, in <module>
    from nimblenet.neuralnet import NeuralNet
  File "C:\Anaconda3\lib\site-packages\nimblenet\neuralnet.py", line 126
    print "[gradient check] Running gradient check..."
                                                     ^
SyntaxError: Missing parentheses in call to 'print'

This means of course that the program is for python 2.+ only.. will it be a version for python 3.+?

jorgenkg commented 7 years ago

Hi, I believe @fabikw has made a python 3 friendly fork of this project, but I've not tested it myself.

https://github.com/fabikw/python-neural-network

fabikw commented 7 years ago

I've made a fork, but haven't been able to put much work on it.

On Thu, Jun 22, 2017 at 3:33 PM, Jørgen Grimnes notifications@github.com wrote:

Hi, I believe @fabikw https://github.com/fabikw has made a python 3 friendly fork of this project, but I've not tested it myself.

https://github.com/fabikw/python-neural-network

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/jorgenkg/python-neural-network/issues/20#issuecomment-310479913, or mute the thread https://github.com/notifications/unsubscribe-auth/ATjVdvsoVLXQ8qUDNN1stj8XX1NIitc_ks5sGsF4gaJpZM4OCtU4 .

NEGU93 commented 7 years ago

Thank you for the quick answer!

I'll give it a try.

xuiqzy commented 4 years ago

The link to the fork is dead. Is there any similar library to use for python 3 to build a neural net yourself in a low level kind of way, but with access to the common functions needed for error, learning, etc?