fmin_bfgs() got an unexpected keyword argument 'lr', train func does not take lr as parameter
GoogleCodeExporter opened this issue · comments
What steps will reproduce the problem?
1.net = nl.net.newff([[-1.2499051235,7.7401906134]], [2, 15, 1],
[nl.trans.TanSig(), nl.trans.TanSig(), nl.trans.PureLin()])
2.error = net.train(inputs, targets, epochs = 1000, show = 50, goal = 0.02, lr
= 0.001)
3.
What is the expected output? What do you see instead?
What version of the product are you using? On what operating system?
Neurolab 0.3.4, Linux Mint
Please provide any additional information below.
I can't adjust learning rate with adding additional parameter lr = "some float".
Original issue reported on code.google.com by vincent....@gmail.com
on 19 Sep 2014 at 10:27
TrainBFGS use scipy.optimize.fmin_bfgs for optimization. This implementation
have not learing rate paremeter
see:
http://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.optimize.fmin_b
fgs.html
Original comment by zue...@gmail.com
on 21 Sep 2014 at 7:07
Original comment by zue...@gmail.com
on 23 Sep 2014 at 4:20
- Changed state: Done