zhipeng93 commented on code in PR #237:
URL: https://github.com/apache/flink-ml/pull/237#discussion_r1209262254
##########
flink-ml-servable-lib/src/main/java/org/apache/flink/ml/classification/logisticregression/LogisticRegressionModelServable.java:
##########
@@ -81,11 +82,49 @@ public DataFrame transform(DataFrame input) {
public LogisticRegressionModelServable setModelData(InputStream...
modelDataInputs)
throws IOException {
Preconditions.checkArgument(modelDataInputs.length == 1);
+ List<LogisticRegressionModelData> modelPieces = new ArrayList<>();
+ while (true) {
+ try {
+ LogisticRegressionModelData piece =
+ LogisticRegressionModelData.decode(modelDataInputs[0]);
Review Comment:
Storing all segments in a list would probably leads to OOM here. When
dealing with large models, we probably need to partition them into segments and
store it one by one.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@flink.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
