As per tensorflow documentation , model.fit_generator method is now DEPRECATED and model.fit now supports generators, so there is no longer any need to use this endpoint.
But it is giving me this error :
logits and labels must be broadcastable: logits_size=[32,3] labels_size=[32,4]
so as you can see your model has output share to be 3 , but your generator has data in 4 classes.
hence , it is the error.
just change it to 4
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.
