why we randomly shuffle data before training what if we train all images of dogs then all images of cats and so on for training how will it effect our model
Why we randomly shuffle data before training what if we train all images of dogs then all images of cats and so on for training how will it effect our model
Hey @hssharma2212000, the practise you are telling its not good, if we do so, the model will become bias towards one class, this means, our model will guess that there is only one class, and model needs to predict only dogs. This is the problem we also face in imbalanced class classification as well. You can read about that as well.
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 
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.