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 non indica alcun file del repository, test o punto di ingresso. Inizia tracciando il caricamento delle librerie native e la gestione del classloader di TensorFlow Java, quindi riproduci il caricamento sequenziale di due versioni di TensorFlow usando l’errore di registrazione di variant-op segnalato. Il lavoro è completo quando viene documentato se il caricamento è supportato e viene identificato un modo validato per caricare le versioni separatamente, se ne esiste uno.