How to use multiple GPUs ?

[phanxlee]

When i running multiple jobs, it use only one GPU card.

python3 tools/infer_e2e.py --img_path=/home/cx/test.png

How to make it use multiple GPU cards？

[root@localhost OpenOCR]# nvidia-smi
Sat Dec 28 21:24:36 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.216.03 Driver Version: 535.216.03 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Tesla V100S-PCIE-32GB Off | 00000000:3B:00.0 Off | 0 |
| N/A 42C P0 59W / 250W | 4014MiB / 32768MiB | 15% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 1 Tesla V100S-PCIE-32GB Off | 00000000:AF:00.0 Off | 0 |
| N/A 29C P0 25W / 250W | 4MiB / 32768MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 213858 C python3 668MiB |
| 0 N/A N/A 213869 C python3 668MiB |
| 0 N/A N/A 213986 C python3 668MiB |
| 0 N/A N/A 214050 C python3 668MiB |
| 0 N/A N/A 214114 C python3 668MiB |
| 0 N/A N/A 214178 C python3 668MiB |
+---------------------------------------------------------------------------------------+

[Topdu]

The commands you're using currently only support single-card processing. If you have a large number of text images to recognize, you can manually divide them into several batches and assign each batch to a different card for inference, enabling multi-card processing.