R Deep Learning Cookbook

How to do it...

Here is how you train a deep learning model on a GPU:

1. The Inception-BN-transferred learning recipe discussed in the previous section can be made to run on the GPU installed and the configured machine by changing the device settings as shown in the following script:

 # Mode re-train model <- mx.model.FeedForward.create( symbol = new_soft, X = train, eval.data = val, ctx = mx.gpu(0), eval.metric = mx.metric.accuracy, num.round = 5, learning.rate = 0.05, momentum = 0.85, wd = 0.00001, kvstore = "local", array.batch.size = 128, epoch.end.callback = mx.callback.save.checkpoint("inception_bn"), batch.end.callback = mx.callback.log.train.metric(150), initializer = mx.init.Xavier(factor_type = "in", magnitude = 2.34), optimizer ...