search

JialianW / GRiT

GRiT: A Generative Region-to-text Transformer for Object Understanding (https://arxiv.org/abs/2212.00280)
MIT License
302 stars 30 forks source link

Batch size Configuration #4

Closed Wykay closed 1 year ago

Wykay commented 1 year ago

Hello, Jialian.

I am currently training the model on 4 3090 GPUs and I find that the batch size is small.

I have changed the SOLVER: IMS_PER_BATCH from 64 to 128 in config/base.yaml but the memomy consumption doesn't seem to become larger.

Could you please tell me how could I increase it.

Thanks a lot.

JialianW commented 1 year ago

Thanks for your interest in GRiT.

The batch size is defined here: https://github.com/JialianW/GRiT/blob/39b33dbc0900e4be0458af14597fcb1a82d933bb/configs/GRiT_B_ObjectDet.yaml#L19