prediction_loop marked as finished

[T0T4R4]

Hi,

As soon as I want to run the samples a second time, the code finishes without error in less than 30 seconds, with the following message :

2021-11-27 13:33:33.341757: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2021-11-27 13:33:33.381717: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: 
name: NVIDIA GeForce RTX 2070 with Max-Q Design major: 7 minor: 5 memoryClockRate(GHz): 1.125
pciBusID: 0000:01:00.0
2021-11-27 13:33:33.382132: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
2021-11-27 13:33:33.385376: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2021-11-27 13:33:33.388222: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_10.dll
2021-11-27 13:33:33.389799: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_10.dll
2021-11-27 13:33:33.393559: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_10.dll
2021-11-27 13:33:33.395904: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_10.dll
2021-11-27 13:33:33.403845: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2021-11-27 13:33:33.404044: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2021-11-27 13:33:34.129347: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-11-27 13:33:34.129674: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]      0 
2021-11-27 13:33:34.130111: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0:   N
2021-11-27 13:33:34.130627: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6728 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2070 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 7.5)
INFO:tensorflow:Running local_init_op.
I1127 13:33:35.260242 20532 session_manager.py:500] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I1127 13:33:35.317266 20532 session_manager.py:502] Done running local_init_op.
2021-11-27 13:33:35.682760: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
INFO:tensorflow:prediction_loop marked as finished
I1127 13:33:36.315276 20532 error_handling.py:101] prediction_loop marked as finished
INFO:tensorflow:prediction_loop marked as finished
I1127 13:33:36.316240 20532 error_handling.py:101] prediction_loop marked as finished

Any idea how I can re-run it ?

Thanks