pull/189/head
Piero Toffanin 2022-08-11 00:19:21 -04:00 zatwierdzone przez GitHub
rodzic 8355086b30
commit d9c5fb4b8c
Nie znaleziono w bazie danych klucza dla tego podpisu
ID klucza GPG: 4AEE18F83AFDEB23
1 zmienionych plików z 4 dodań i 4 usunięć

Wyświetl plik

@ -50,15 +50,15 @@ docker run -p 3000:3000 -v /mnt/external_hd:/var/www/data opendronemap/nodeodm
This can be also used to access the computation results directly from the file system. This can be also used to access the computation results directly from the file system.
## Using GPU Acceleration for SIFT processing inside NodeODM ## Using GPU Acceleration
Since the ODM has support [of GPU acceleration](https://github.com/OpenDroneMap/ODM#gpu-acceleration) you can use another base image for GPU processing.
Since ODM has support [for GPU acceleration](https://github.com/OpenDroneMap/ODM#gpu-acceleration) you can use another base image for GPU processing. You need to use the `opendronemap/nodeodm:gpu` docker image instead of `opendronemap/nodeodm` and you need to pass the `--gpus all` flag:
To use this feature, you need to use the `opendronemap/nodeodm:gpu` docker image instead of `opendronemap/nodeodm` and you need to pass the `--gpus all` flag:
```bash ```bash
docker run -p 3000:3000 --gpus all opendronemap/nodeodm:gpu docker run -p 3000:3000 --gpus all opendronemap/nodeodm:gpu
``` ```
The SIFT GPU implementation is OpenCL-based, so should work with most graphics card (not just NVIDIA). The GPU implementation is CUDA-based, so will only work on NVIDIA GPUs.
If you have an NVIDIA card, you can test that docker is recognizing the GPU by running: If you have an NVIDIA card, you can test that docker is recognizing the GPU by running: