Optimal Batch Size

[vinits5]

Hello,

Thank you for such a great job and for releasing your code.
I want to train your network using a custom dataset. When I looked at the options.py file, the batch_size parameter is set to 1 and has not changed anywhere in other training files.
Do you find empirically that batch_size 1 works best with your network? Please suggest this parameter as my dataset contains almost 15000 images and it will be very slow to train with batch_size 1.
Thanks.

[HighwayWu]

Hi, Vinits.

I set the batch_size=1 mainly because of the limitation of resources. I think you could try a larger batch size according to your resources.
Sorry for the late reply.

Best,
Haiwei

[vinits5]

Sure. I will try other batch sizes.