When setting higher batch size during training, increases time taken per epoch?

[WeiKin007]

I am using this package to train a model on a custom dataset of images. I have been training my models using settings of batch size = 1, but when I increase the batch size to let's say 2, the time per epoch increases, which goes against what I understand of how batch processing works. Or is the way how the batches work differently in this package?

[hhk7734]

batch_size is the number of datasets per step. The number of datasets used for training is batch_size x steps_per_epoch x epochs.

[WeiKin007]

Sorry that is kind of confusing. So if I have 1000 images for training, and my batch size is set to 1, lets say it takes 60 seconds per epcoh to process the whole dataset, when I set my batch size to 10, shouldn't the time taken per epoch reduce as I am processing more samples per batch?

[hhk7734]

Ref: https://www.tensorflow.org/api_docs/python/tf/keras/Model#fit

[hhk7734]

I accidentally closed it.

If you increase the batch_size, the time spent per epoch will increase.