Forward-Forward

Forward-Forward copied to clipboard

Question regarding logits = sum_of_squares - z.shape[1]

1

On file src.ff_model.py line 76: logits = sum_of_squares - z.shape[1] ff_loss = self.ff_loss(logits, labels.float()) I wondered for a long time and did not figure out why you wrote (sum_of_squares -...

YangLiangwei

The code changes facilitate multi-pass inference: passing an image with the one hot labels encoded into the image in a different pixel each time and choosing the predicted label as...

saum7800