view baseline/conv_mlp/convolutional_mlp.conf @ 314:2937f2a421aa

Print the error sometimes in the pretrain loop.
author Arnaud Bergeron <abergeron@gmail.com>
date Thu, 01 Apr 2010 14:28:50 -0400
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