I am doing simple CNN based binary image classification on classifying types of waste as organic and recyclable using image augmentation. How ever I have a doubt.

First part of the code

Second part of the code


In the third figure i have set the steps_per_epoch = 22564/32= 705 where 32 is batch size and validation_steps as 2513/32 = 79 as per documentation does that mean out of 22564 training and 2513 validation samples 705 and 79 are trained and validated ?

  • $\begingroup$ Hi and welcome to the site! Can you please paste and properly format your code? $\endgroup$ – Sammy Apr 6 '20 at 15:25
  • $\begingroup$ I am sorry i dont know how to do that $\endgroup$ – Abhinav Thapper Apr 6 '20 at 19:20

No, that is the steps per epoch. One step is taking 32 images(batch size) So, 709*32 images used in that epoch and validated with 79*32 images.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.