henghuiding/Vision-Language-Transformer

What's the gpu device that can support this model?

Closed this issue · 4 comments

Is the batch size 128? I can't deploy the model on single 11 GB NVIDIA 2080 Ti when setting batch size is 16.

Hi,

The model is trained with V100. You can use smaller batch size when training with 11GB 2080Ti.

Thank you. I get it. The batch size will be assigned to each gpu. So the samples of one gpu is batch_size / num_gpus

Hi,

The model is trained with V100. You can use smaller batch size when training with 11GB 2080Ti.

Dear author, how many V100 do you use to train the models?

1080Ti * 4 is also ok. But 3090Ti isn't.