Closed ewong18 closed 4 years ago
Hi,
If you have only one gpu, you should remove the distributed launching entirely:
python main.py --coco_path /path/to/coco
This will train with a total batch size of 2, which is currently untested/unsupported (we recommend at least bs=16, which is unlikely to fit on a single gpu)
Closing following @alcinos answer, but let us know if you have further issues / questions.
I'm trying to run the example as-is, and i'm running into this issue. I did have to adjust the number of gpus because the VM I'm working on only has 1. I'm also working on a Windows 10 machine with pytorch version 1.5.0, CUDA version 10.1, and CUDA compiler driver v10.0.130.