redis.exceptions.ResponseError: GPU requested but TF couldn't find CUDA about redis-camera-ai HOT 4 CLOSED

version: '3'
services:
  redisedge:
    build: ./redisedge
    ports:
      - 6379:6379
    runtime: nvidia
    environment:
      NVIDIA_VISIBLE_DEVICES: all
  init:
    build: ./app
    depends_on:
      - redisedge
    volumes:
      - ./app:/app
    command: ['init.py', '--url', 'redis://172.20.10.64:6379', '-d', 'GPU']

redisedge-redisedge-1  | 1:M 09 Mar 2022 16:58:05.407 # <ai> backend TF not loaded, will try loading default backend
redisedge-redisedge-1  | 2022-03-09 16:58:05.518613: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.518646: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
redisedge-redisedge-1  | 1:M 09 Mar 2022 16:58:05.562 * <ai> TF backend loaded from /usr/lib/redis/modules/backends/redisai_tensorflow/redisai_tensorflow.so
redisedge-redisedge-1  | 2022-03-09 16:58:05.672075: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F FMA
redisedge-redisedge-1  | To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
redisedge-redisedge-1  | 2022-03-09 16:58:05.878211: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878308: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublas.so.11'; dlerror: libcublas.so.11: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878372: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublasLt.so.11'; dlerror: libcublasLt.so.11: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878419: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcufft.so.10'; dlerror: libcufft.so.10: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878463: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcurand.so.10'; dlerror: libcurand.so.10: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878521: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusolver.so.11'; dlerror: libcusolver.so.11: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878585: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusparse.so.11'; dlerror: libcusparse.so.11: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878656: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/redis/modules
redisedge-redisedge-1  | 2022-03-09 16:58:05.878673: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1835] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
redisedge-redisedge-1  | Skipping registering GPU devices...
redisedge-redisedge-1  | 1:M 09 Mar 2022 16:58:05.881 # <ai> ERR GPU requested but TF couldn't find CUDA
redisedge-init-1       | Loading model - Traceback (most recent call last):
redisedge-init-1       |   File "init.py", line 35, in <module>
redisedge-init-1       |     res = conn.execute_command('AI.MODELSET', 'yolo:model', 'TF', args.device, 'INPUTS', 'input', 'OUTPUTS', 'output', 'BLOB', model)
redisedge-init-1       |   File "/usr/local/lib/python3.7/site-packages/redis/client.py", line 775, in execute_command
redisedge-init-1       |     return self.parse_response(connection, command_name, **options)
redisedge-init-1       |   File "/usr/local/lib/python3.7/site-packages/redis/client.py", line 789, in parse_response
redisedge-init-1       |     response = connection.read_response()
redisedge-init-1       |   File "/usr/local/lib/python3.7/site-packages/redis/connection.py", line 642, in read_response
redisedge-init-1       |     raise response
redisedge-init-1       | redis.exceptions.ResponseError: GPU requested but TF couldn't find CUDA

redisedge-redisedge-1  | 2022-03-09 16:58:05.878673: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1835] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
redisedge-redisedge-1  | Skipping registering GPU devices...