How do the outputs change?

[yarinbar]

According to the code (and assuming that STEPS = 1, i dont understand how the outputs change after the adaptation:

def forward(self, x):
    if self.episodic:
        self.reset()

    for _ in range(self.steps):
        outputs = forward_and_adapt(x, self.model, self.optimizer)
    return outputs

@torch.enable_grad()  # ensure grads in possible no grad context for testing
def forward_and_adapt(x, model, optimizer):
    """Forward and adapt model on batch of data.

    Measure entropy of the model prediction, take gradients, and update params.
    """
    # forward
    outputs = model(x)
    # adapt
    loss = softmax_entropy(outputs).mean(0)
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()
    return outputs

judging by the code, you return the original outputs however they do change somehow, how?

[NneurotransmitterR]

I think in Online TTA, a batch of samples won't be fed into the network again to do another forward pass, so the updated model is for the next batch. But in some other scenarios the current batch will get a new output.