Setting up steps_per_epoch and val_gen

[chiragwxN (Chirag Jain)]

Hi Vasu Bhaiya,

steps_per_epoch=(number_of training examples)/(batch_size)

This formula ensures that we cover all the training data in 1 epoch.

In tiny-imagenet 200 dataset
I came across training_data=100,000
Sir kept batch_size=128
Then steps_per_epoch = 781 ??

Kindly confirm…

Also if we use ImageDataGenerator to load the data as well as augment the data.
Why do we call it to have infinite training data?

[S18CRX0120 (Vasu Gupta)]

Hey @chiragwxN, Go through this thread link, i have already discussed this in brief with one student,

Applying image augmentation on training data

Suppose I have 800 images in my training data. Now I apply image augmentation. Image augmentation results in infinite images. How many images should I now be training? The number of images I train will depend upon steps per epoch?

Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section.

[S18CRX0120 (Vasu Gupta)]

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.