Overflow error on Ubuntu

[mvorobyo]

Hey I tried running your code but then got an overflow warning.
...
Processed 69 of 75 batches
Processed 70 of 75 batches
Processed 71 of 75 batches
Processed 72 of 75 batches
Processed 73 of 75 batches
Processed 74 of 75 batches
Processed 75 of 75 batches
Time 2.70161509514
Pre Training
Visible units: 2000 Hidden units: 500
[loggingutils.py :38 ] - 2016-11-10 16:51:12,471 - WARNING - /home/michael/deep-belief-nets-for-topic-modeling/DBN/dbn.py:239: RuntimeWarning: overflow encountered in exp
return 1. / (1 + exp(-x))

File "./main.py", line 209, in
run_examples(options.exp_num)

File "./main.py", line 195, in run_examples
example1()

File "./main.py", line 63, in example1
deepbelief.run_pretraining(learning_rate=0.01, weight_cost=0.0002, momentum=0.9, gibbs_steps=1)

File "/home/michael/deep-belief-nets-for-topic-modeling/DBN/dbn.py", line 56, in run_pretraining
pretraining_process.start()

File "/usr/lib/python2.7/multiprocessing/process.py", line 130, in start
self._popen = Popen(self)

File "/usr/lib/python2.7/multiprocessing/forking.py", line 126, in init
code = process_obj._bootstrap()

File "/usr/lib/python2.7/multiprocessing/process.py", line 258, in _bootstrap
self.run()

File "/usr/lib/python2.7/multiprocessing/process.py", line 114, in run
self._target(*self._args, **self._kwargs)

File "/home/michael/deep-belief-nets-for-topic-modeling/DBN/dbn.py", line 67, in run_pretraining_as_process
r.rsm_learn(self.max_epochs)

File "/home/michael/deep-belief-nets-for-topic-modeling/DBN/pretraining.py", line 102, in rsm_learn
neg_vis, neg_hid_prob, D, p = self.contrastive_divergence_rsm(neg_vis, pos_hid_prob, D)

File "/home/michael/deep-belief-nets-for-topic-modeling/DBN/pretraining.py", line 142, in contrastive_divergence_rsm
neg_hid_prob = dbn.sigmoid(dot(neg_vis, self.weights) + outer(D, self.hidden_biases))

File "/home/michael/deep-belief-nets-for-topic-modeling/DBN/dbn.py", line 239, in sigmoid
return 1. / (1 + exp(-x))

File "/home/michael/code/python/util/loggingutils.py", line 38, in my_showwarning
logging.warning(warnings.formatwarning(message, category, filename, line) + '\n' + '\n'.join(traceback.format_stack()))

Epoch[ 1]: Perplexity = 584.66
Epoch[ 2]: Perplexity = 518.24
Epoch[ 3]: Perplexity = 475.66
Epoch[ 4]: Perplexity = 443.47
...