Changing the training data after end of each iteration

yajiemiao / pdnn

PDNN: A Python Toolkit for Deep Learning. http://www.cs.cmu.edu/~ymiao/pdnntk.html

Apache License 2.0

224 stars 105 forks source link

Changing the training data after end of each iteration #3

Closed tofigh- closed 9 years ago

tofigh- commented 9 years ago

Another question is, Is it possible to change the training data after each epoch?

ghost commented 9 years ago

No implementation in PDNN is specifically for this. A workaround is to terminate network training after one epoch finishes. Then load the new data and restart training. Each epoch needs to write out the resulting model so that the next epoch can load it.

muhammadriz commented 8 years ago

How i can terminate network training after each epoch ?