jens/Rbm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

- Rbm: scale learningRate and weightDecay by minibtachsize

Browse Source 
- after create: new Layer is selected

git-svn-id: http://moon:8086/svn/software/trunk/projects/Rbm@653 b431acfa-c32f-4a4a-93f1-934dc6c82436
This commit is contained in:
jens
2019-11-11 07:07:23 +00:00
parent d99a28bbd1
commit 1a876bc8e5
2 changed files with 3 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
source/Rbm.cpp
+2 -2
View File
@@ -85,8 +85,8 @@ void Rbm::train(const arma::mat& batch, IListener* pListener)
arma::mat miniBatch = batch.rows(batchRowIndex, batchRowIndex+miniBatchSizeActual-1);
trainingSizeRemain -= miniBatchSizeActual;
batchRowIndex += miniBatchSizeActual;
double learning_rate = m_params.learningRate/miniBatchSizeActual;
double weight_decay = m_params.weightDecay/miniBatchSizeActual;
double learning_rate = m_params.learningRate/m_params.miniBatchSize;
double weight_decay = m_params.weightDecay/m_params.miniBatchSize;
arma::mat vis_state(miniBatchSizeActual, m_w.n_rows);
arma::mat vis_probs(miniBatchSizeActual, m_w.n_rows);