Do I have to set same batch size for training, validation and testing?

Question

Do I have to set same batch size for training, validation and testing?

Pratichhya

2022年5月9日 22:06

I was performing segmentation task and have set my batchsize to 16 for all train, validation and inferencing. In my observation, I got better result in inferencing when setting batch size to 1. How should I decide the correct size for these three or they will have to be of same size?

Topic semantic-segmentation deep-learning

Category Data Science

Inuraghe · Accepted Answer · 2022年3月22日 16:27

1

Inuraghe answered at 2022年3月22日 16:27

It depends on what is your problem, what is your target and how are good your data. There isn't a correct number, but here you can find some helps.

Do I have to set same batch size for training, validation and testing?

About