The first frame processed by prediction, new_image = yolo.detect_image(img) results in the following warning:
xecutor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2020-04-27 04:31:41.873854: W tensorflow/stream_executor/cuda/redzone_allocator.cc:312] Internal: Invoking ptxas not supported on Windows
Relying on driver to perform ptx compilation. This message will be only logged once.
2020-04-27 04:31:41.952813: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2020-04-27 04:31:42.704845: W tensorflow/core/common_runtime/bfc_allocator.cc:305] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature.
All other frames process perfectly with great results, for awhile... then the system gives a stackoverflow error.
The first frame processed by prediction, new_image = yolo.detect_image(img) results in the following warning:
xecutor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll 2020-04-27 04:31:41.873854: W tensorflow/stream_executor/cuda/redzone_allocator.cc:312] Internal: Invoking ptxas not supported on Windows Relying on driver to perform ptx compilation. This message will be only logged once. 2020-04-27 04:31:41.952813: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2020-04-27 04:31:42.704845: W tensorflow/core/common_runtime/bfc_allocator.cc:305] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature.
All other frames process perfectly with great results, for awhile... then the system gives a stackoverflow error.
Memory does NOT grow during the process.
Any ideas?
Thanks