I am training my model in loop using tensorflow and keras, iterating over data etc.

Simple example
Loop N times:
    "Collect samples"
    if x > 100:
       "1 Epoch will have 5 train groups."
       mod.fit(x, Y, batch_size=20)

Does Adam remember gradient momentum from previous fits, or this only works for batches?


Your Answer

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

Browse other questions tagged or ask your own question.