Cuda error while running inference


I have a problem with CUDA, because I use DeepSpeech for speech recognition. I use my own Ubuntu 20.04.2 LTS (GNU/Linux 4.9.140-tegra aarch64) image on my Jetson nano 2GB

When I launch the inference engine I get these messages:

2021-02-11 15:35:18.963581: I tensorflow/stream_executor/platform/default/] Successfully opened dynamic library
2021-02-11 15:35:18.998228: E tensorflow/stream_executor/cuda/] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
2021-02-11 15:35:18.998338: I tensorflow/stream_executor/cuda/] kernel driver does not appear to be running on this host (localhost): /proc/driver/nvidia/version does not exist

I would like to be able to use the GPU of the card but I don’t understand the error, any help on this error is welcome!

I think your custom image is missing CUDA drivers and/or some other essentials…