Deploy issue with flask app. tensorflow/cuda package related.

2023-11-11 11:13:15.347377: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. 2023-11-11 11:13:16.154513: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /nix/store/xpxln7rqi3pq4m0xpnawhxb2gs0mn1s0-gcc-12.3.0-lib/lib:/nix/store/4rx3vkkd91wkbhpflsplfga603cp1l1c-zlib-1.3/lib:/usr/lib 2023-11-11 11:13:16.154608: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /nix/store/xpxln7rqi3pq4m0xpnawhxb2gs0mn1s0-gcc-12.3.0-lib/lib:/nix/store/4rx3vkkd91wkbhpflsplfga603cp1l1c-zlib-1.3/lib:/usr/lib 2023-11-11 11:13:16.154623: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. 2023-11-11 11:13:17.293814: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /nix/store/xpxln7rqi3pq4m0xpnawhxb2gs0mn1s0-gcc-12.3.0-lib/lib:/nix/store/4rx3vkkd91wkbhpflsplfga603cp1l1c-zlib-1.3/lib:/usr/lib 2023-11-11 11:13:17.293869: W tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: UNKNOWN ERROR (303)

Solution:

you're trying to run an ML related app on the trial plan, it's highly likely you are running out of memory, please upgrade to the hobby plan for access to 8gb of memory instead of 512mb on the trial plan

Jump to solution