Daniel comments

Results 7 comments of


                                            Daniel

use "session.runner.run " to predict with tensors，after many times, the memory grow higher and higher then oom

@hanfengatonline how did this issue ended up?, any update you can bring?, we are experiencing a very similar issue with 1.0.0 version.

java tensorflow and maven version is org.tensorflow:libtensorflow:1.15.0 after session.runner.run() for many times, the memory grow higher and higher then oom

I'm still experiencing this with TensorFlow 2.16.2. I'm using TensorFlow for Java 1.0.0

java tensorflow and maven version is org.tensorflow:libtensorflow:1.15.0 after session.runner.run() for many times, the memory grow higher and higher then oom

I'm performing inference on a number of Tensorflow-based models for different steps of NLP pipeline. Memory leak has been identified after migrating from Tf1 to Tf2 , most likely because...

java tensorflow and maven version is org.tensorflow:libtensorflow:1.15.0 after session.runner.run() for many times, the memory grow higher and higher then oom

Setting "org.bytedeco.javacpp.nopointergc" does not seem to solve it. GC is -XX:+UseG1GC. There's indeed physical memory growing for the process as we can see it both in our netadata reporting and...

java tensorflow and maven version is org.tensorflow:libtensorflow:1.15.0 after session.runner.run() for many times, the memory grow higher and higher then oom

Not that I know. ``` private Tensor getInputs(List values) { byte[][] input = new byte[values.size()][]; for (int i = 0; i < values.size(); i++) { String val = values.get(i); input[i]...

java tensorflow and maven version is org.tensorflow:libtensorflow:1.15.0 after session.runner.run() for many times, the memory grow higher and higher then oom

UPDATE. Initially we had a number of Tensorflow objects that were not properly handled within try-with-resources blocks, which have already been addressed. In the current version, however, we still see...

Sentencepiece version upgrade

Hi @rkoystart , trying to run sentencepiece in a java application from Mx apple series and finding issues with native libraries. I saw 0.2.0 include these. Any luck making sentencepiece-jni...