How to extract Weights, bias from trained model, and how to choose a error function ?

[automataIA]

1. How to extract Weights and bias from trained model?
2. How to set, or choose a error function for model?

im using the same code in the example:

 IMPORT DATASET -----------------------------------
X = pd.read_feather('Input.file') ; 
Y = pd.read_feather('Target.file') ;

TRASFORMATION DATASET IN ARRAY -------------------
X = X.values.T
Y = Y.values.T
print(X.shape,Y.shape)
 NETWORK ------------------------------
net = prn.CreateNN([3,6,8])

net = prn.train_LM(X,Y,net,verbose=True,k_max=1000,E_stop=1e-5)

ADD : why with command :

W0 = net['w0']; print(W0.shape) ;
W1 = net['w']; print(W1.shape) ; 

3. give me a shape for W0 and W1 of [80,] and not : [6x3] and [8x6] ?
4. and normP and normY are bias, i think?

[yabata]

HI Zawarud,

you can save weights as descibed here:

https://pyrenn.readthedocs.io/en/latest/save.html

Pyrenn only supports tanh as transfer function.

Best regards

Dennis

Von: Zawarud [mailto:notifications@github.com] Gesendet: Mittwoch, 29. Januar 2020 15:26 An: yabata/pyrenn pyrenn@noreply.github.com Cc: Subscribed subscribed@noreply.github.com Betreff: [yabata/pyrenn] How to extract Weights, bias from trained model, and how to choose a error function ? (#10)

1. How to extract Weights and bias from trained model?
2. How to set, or choose a error function for model?

im using the same code in the example: `# IMPORT DATASET ----------------------------------- X = pd.read_feather('Input.file') ; Y = pd.read_feather('Target.file') ;

TRASFORMATION DATASET IN ARRAY -------------------

X = X.values.T Y = Y.values.T print(X.shape,Y.shape)

NETWORK ------------------------------

net = prn.CreateNN([3,6,8])

net = prn.train_LM(X,Y,net,verbose=True,k_max=1000,E_stop=1e-5)`

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/yabata/pyrenn/issues/10?email_source=notifications&email_token=ACGZMJX4VNLNOPLLTGJ7D6TRAGGYNA5CNFSM4KNFQ34KYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4IJRSORQ , or unsubscribe https://github.com/notifications/unsubscribe-auth/ACGZMJT5RNV3MUABAUNJNK3RAGGYNANCNFSM4KNFQ34A . https://github.com/notifications/beacon/ACGZMJRRG5XIX7DSSLPG44LRAGGYNA5CNFSM4KNFQ34KYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4IJRSORQ.gif