thirdwing commented on issue #7364: MxnetR chunk-wise neural nets URL: https://github.com/apache/incubator-mxnet/issues/7364#issuecomment-321406878 @train-test-laura If you are using the same model over different chunks of data, you can do something similar to below: ```r data(BostonHousing, package = "mlbench") train.ind <- seq(1, 506, 3) train.x <- data.matrix(BostonHousing[train.ind,-14]) train.y <- BostonHousing[train.ind, 14] test.x <- data.matrix(BostonHousing[-train.ind,-14]) test.y <- BostonHousing[-train.ind, 14] train.x2 <- train.x train.y2 <- train.y library(mxnet) data <- mx.symbol.Variable("data") fc1 <- mx.symbol.FullyConnected(data, num_hidden = 1) lro <- mx.symbol.LinearRegressionOutput(fc1) mx.set.seed(0) model <- mx.model.FeedForward.create(lro, X = train.x, y = train.y, ctx = mx.cpu(), num.round = 50, array.batch.size = 20, learning.rate = 2e-6, momentum = 0.9, eval.metric = mx.metric.rmse) model2 <- mx.model.FeedForward.create(lro, X = train.x2, y = train.y2, ctx = mx.cpu(), num.round = 50, array.batch.size = 20, learning.rate = 2e-6, momentum = 0.9, eval.metric = mx.metric.rmse, arg.params = model$arg.params, aux.params = model$aux.params) ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
With regards, Apache Git Services