In this documentation of Keras.model, it describe the differences between using keras.model.predict(input) and keras.model(input), stating that the latter is a better suit for small numbers of inputs.
My question is, what is the max numbers of inputs for keras.model(input)?
Revision 12-20-2022
"For small numbers of inputs that fit in one batch, directly use __call__() for faster execution, e.g., model(x)"
The quote is as above. learner and Dr. snoopy said that I might misunderstand the meaning of "small numbers of inputs that fit in one batch".