TTA now returns class probability for each n_aug so you need to:
log_preds,y = learn.TTA()
preds = np.mean(np.exp(log_preds),0)
This should work…
2 Likes
TTA now returns class probability for each n_aug so you need to:
log_preds,y = learn.TTA()
preds = np.mean(np.exp(log_preds),0)
This should work…