diff options
author | Alex Auvolat <alex@adnab.me> | 2016-04-26 16:33:02 +0200 |
---|---|---|
committer | Alex Auvolat <alex@adnab.me> | 2016-04-26 16:33:02 +0200 |
commit | b5584610a14578d0f3ebf9eea3067a0284f67288 (patch) | |
tree | cc23207cf82a6ee0d0bc121d1f0f6bd6e2a8e531 /config/lstm-xreg-relu.py | |
parent | 760587b5d9771257160fac216dfcfff852de3ccc (diff) | |
download | text-rnn-b5584610a14578d0f3ebf9eea3067a0284f67288.tar.gz text-rnn-b5584610a14578d0f3ebf9eea3067a0284f67288.zip |
Xreg hyperparameter change
Diffstat (limited to 'config/lstm-xreg-relu.py')
-rw-r--r-- | config/lstm-xreg-relu.py | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/config/lstm-xreg-relu.py b/config/lstm-xreg-relu.py new file mode 100644 index 0000000..7697558 --- /dev/null +++ b/config/lstm-xreg-relu.py @@ -0,0 +1,48 @@ +from blocks.algorithms import AdaDelta +from blocks.bricks import Tanh, Rectifier + +from model.lstm import Model + +dataset = 'data/logcompil.txt' +io_dim = 256 + +# An epoch will be composed of 'num_seqs' sequences of len 'seq_len' +# divided in chunks of lengh 'seq_div_size' +num_seqs = 50 +seq_len = 5000 +seq_div_size = 200 + +layers = [ + {'dim': 1024, + 'xreg': (768, 0.1, 50, 5, 5) + }, + {'dim': 1024, + 'xreg': (768, 0.1, 50, 5, 5) + }, + {'dim': 1024, + }, +] +activation_function = Rectifier() + +i2h_all = True # input to all hidden layers or only first layer +h2o_all = True # all hiden layers to output or only last layer + +w_noise_std = 0.02 +i_dropout = 0.5 + +l1_reg = 0 + +step_rule = AdaDelta() + +# parameter saving freq (number of batches) +monitor_freq = 100 +save_freq = 100 + +# used for sample generation and IRC mode +sample_temperature = 0.7 #0.5 + +# do we want to generate samples at times during training? +sample_len = 1000 +sample_freq = 100 +sample_init = '\nalex\ttu crois?\n' + |