It said that I need to have more RAM？tks about paperrobot HOT 12 CLOSED

Thank you very much for your interest in our research. Perhaps you can try a smaller batch size by typing python train.py --batch_size 50. If that doesn't work you can decrease it again.

from paperrobot.

@EagleW Could you please tell us what GPU do you use? Thanks.

from paperrobot.

I use P100

from paperrobot.

I use P100

Thanks.

from paperrobot.

I am trying to replicate your work and am getting OOM errors on a P100 GPU with 16 GB when using the default batch size of 200. How much memory did your P100 GPU have?

from paperrobot.

@davidrpugh Which part of the code are you running?

from paperrobot.

I think you can decrease the batch size to 50

from paperrobot.

Specifically I ran the ./Existing paper reading/train.py script with default parameters using one 16 GB P100 GPU and got an OOM error from the GPU. I can decrease the batch size but I wanted to start with the default params used in your paper. Was 200 the batch size used in the paper? Or something smaller?

from paperrobot.

I think I use a much smaller batch size for it. Actually, the batch size didn't influence the model performance much

from paperrobot.

I have tried batch sizes of 128, 64, 32, and 16. With --batch_size=16 I was able to train for one full epoch before getting GPU OOM error. I am going to try again with 8 but I feel that there must be something else I am missing.

from paperrobot.

@davidrpugh I think you can add torch.cuda.empty_cache() after the line 263 in main.py

from paperrobot.

The problem is that the get_subgraph will return a very large adj_ingraph matrix. If the batch size is too large, the adjacent matrix will be too large to fit in the memory

from paperrobot.