ria-com/nomeroff-net

Как заставить это работать на Jetson Nano?

Closed this issue · 2 comments

Ilyaprok commented

Работает на CPU. Хочу заставить работать на GPU. Попробовал переустановить PyTorch и Torchvsision из исходников, при запуске модели "number_plate_localization" падает в Segmenation fault.

Ilyaprok commented

PyTorch version: 1.8.1a0+37c1f4a
Is debug build: False
CUDA used to build PyTorch: 10.2
ROCM used to build PyTorch: N/A

OS: Ubuntu 18.04.6 LTS (aarch64)
GCC version: (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) 7.5.0
Clang version: 6.0.0-1ubuntu2 (tags/RELEASE_600/final)
CMake version: version 3.10.2

Python version: 3.8 (64-bit runtime)
Is CUDA available: True
CUDA runtime version: Could not collect
GPU models and configuration: Could not collect
Nvidia driver version: Could not collect
cuDNN version: Probably one of the following:
/usr/lib/aarch64-linux-gnu/libcudnn.so.8.2.1
/usr/lib/aarch64-linux-gnu/libcudnn_adv_infer.so.8.2.1
/usr/lib/aarch64-linux-gnu/libcudnn_adv_train.so.8.2.1
/usr/lib/aarch64-linux-gnu/libcudnn_cnn_infer.so.8.2.1
/usr/lib/aarch64-linux-gnu/libcudnn_cnn_train.so.8.2.1
/usr/lib/aarch64-linux-gnu/libcudnn_ops_infer.so.8.2.1
/usr/lib/aarch64-linux-gnu/libcudnn_ops_train.so.8.2.1
HIP runtime version: N/A
MIOpen runtime version: N/A

Versions of relevant libraries:
[pip3] numpy==1.13.3
[conda] Could not collect

Ilyaprok commented

проблема была не в библиотеке, а в Opencv, imshow приводил к Segmenation fault