search

geffy / tffm

TensorFlow implementation of an arbitrary order Factorization Machine
MIT License
780 stars 176 forks source link

show a mean squared average between epochs like pyFM? #19

Closed thestick613 closed 7 years ago

thestick613 commented 7 years ago

https://github.com/coreylynch/pyFM#getting-started

geffy commented 7 years ago

I don't think that it's a really useful feature, but you can can set verbose=2 and get avarage trainig loss printed, like this:

from tffm import TFFMClassifier
model = TFFMClassifier(order=2, rank=10,  n_epochs=5, verbose=2)
model.fit(X_tr, y_tr)
[epoch 0]: mean target value: 0.6933335065841675
[epoch 1]: mean target value: 0.599380612373352
[epoch 2]: mean target value: 0.4427681267261505
[epoch 3]: mean target value: 0.38958144187927246
[epoch 4]: mean target value: 0.3296085000038147