Calling Tensorfow sess.run() and TensorRT context.execute_async() in a loop.

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

The psedo Python code is as follows.

while True:
sess.run()
context.execute_async()

Getting the following error, and of course TensorRT result is not correct.

[TensorRT] ERROR: cuda/cudaScaleLayer.cpp (99) - Cuda Error in execute: 400 (invalid resource handle)

Is there a work around ?