RuntimeError: CUDA out of memory.

[KiAlexander]

even set batch_size = 3 as default with 3 GPU , I still get the following error, I wanna know how can I solve the problem now?

RuntimeError: CUDA out of memory. Tried to allocate 18.75 MiB (GPU 0; 11.90 GiB total capacity; 9.54 GiB already allocated; 9.00 MiB free; 159.98 MiB cached)

+-------------------------------+----------------------+----------------------+
| 1 TITAN X (Pascal) Off | 00000000:02:00.0 Off | N/A |
| 25% 44C P8 11W / 250W | 2MiB / 12189MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 2 TITAN X (Pascal) Off | 00000000:03:00.0 Off | N/A |
| 23% 39C P8 9W / 250W | 2MiB / 12189MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 3 TITAN X (Pascal) Off | 00000000:04:00.0 Off | N/A |
| 23% 36C P8 9W / 250W | 2MiB / 12189MiB | 0% Default |
+-------------------------------+----------------------+----------------------+

[KiAlexander]

btw， the sample rate =16000 instead 8000 , is it the reason for the error？

[mpariente]

Did you set id=0,1,2 in the run.sh ?

[KiAlexander]

yes, i idid

+-------------------------------+----------------------+----------------------+
| 1 TITAN X (Pascal) Off | 00000000:02:00.0 Off | N/A |
| 25% 44C P8 11W / 250W | 2MiB / 12189MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 2 TITAN X (Pascal) Off | 00000000:03:00.0 Off | N/A |
| 23% 39C P8 9W / 250W | 2MiB / 12189MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 3 TITAN X (Pascal) Off | 00000000:04:00.0 Off | N/A |
| 23% 36C P8 9W / 250W | 2MiB / 12189MiB | 0% Default |
+-------------------------------+----------------------+----------------------+

the above infomation is to show the condition of the GPU I used , insted of the usage of GPU

[mpariente]

Did you experience the same problem with a sample rate of 8k?
With 16k you'll need twice as much memory.