WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least steps_per_epoch * epochs batches (in this case, 4 batches). You may need to use the repeat() function when building your dataset.
There are 724 images in train_generator and while doing
model.fit_generator , set steps_per_epoch=7 then this warning is coming and also val_loss and val_accuracy not print in output window.
hey @lgoyal50_be19 ,
This error means that you are running more number of steps then your actual data needs.
Means , assume that your 630 images
and batch size of 64 , means around 10 batches to be correct.
But you are running more than 10 times , and the model is not able to generate or get that data required .
Hence it raising this error.
like in your case, ]
the validation data is having 84 images with batch size 32
means 32*3 = 96, validation steps were need to at max 3.
but as you have specified it as 4 , hence it doesn’t gets data at the 4 step and hence raises that error.
just change it to 3.