step method
Appends the SGD weight update operations to the provided tape.
This optimizer does not require to be updated and can be reused indefinitely via the same tape execution.
Implementation
@override
void step(CommandBuffer tape) {
for (int i = 0; i < parameters.length; i = i + 1) {
tape.putInt(OP_SGD_UPDATE);
tape.putString(parameters[i].id); // The weights
tape.putString('${parameters[i].id}_grad'); // The gradients
tape.putFloat(learningRate);
}
}