Loading two different Tensorflow versions with different classloaders

Hello, I am creating a program that makes inference with already trained models and I want to allow changing the tensorflow versions on runtime. For that I am loading dynamically the JARS needed to run Inference with TF Java in a separate classloader. These JARs are not in the classpath of the main program. I expected that when the ClassLoader is garbage collected, the native libraries loaded by that classloader were going to be unloaded too. However that is not the case and I am not able to load two different versions of Tensorflow in the same run time one after the other. The error I get when I try to execute a command with the JARs corresponding to the second TF version loaded is :
2021-12-21 14:47:11.121313: F external/org_tensorflow/tensorflow/core/framework/variant_op_registry.cc:46] Check failed: existing == nullptr (0x7ff35a2acc38 vs. nullptr)Unary VariantDecodeFn for type_name: tensorflow::data::WrappedDatasetVariant already registered

Is this behaviour expected? Is there any way I can do what I want?
regards,
Carlos

L’issue ne nomme aucun fichier du dépôt, test ni point d’entrée. Commencez par suivre le chargement des bibliothèques natives et la gestion du classloader de TensorFlow Java, puis reproduisez le chargement séquentiel de deux versions de TensorFlow à l’aide de l’échec de l’enregistrement de variant-op signalé. Le travail est considéré comme terminé lorsqu’il est documenté si le déchargement est pris en charge et qu’une manière validée de charger les versions séparément est identifiée, s’il en existe une.