Mercurial > ift6266
view baseline/conv_mlp/convolutional_mlp.conf @ 173:954185d6002a
Take the validation set at the end of the training set files rather than at the beginning.
| author | Arnaud Bergeron <abergeron@gmail.com> |
|---|---|
| date | Sat, 27 Feb 2010 12:01:08 -0500 |
| parents | d37c944133c3 |
| children |
line wrap: on
line source
learning_rate=0.01 n_iter=1 batch_size=20 n_kern0=20 n_kern1=50 filter_shape=5 n_layer=3