def _Accuracy(inputs, axis=-1, **unused_kwargs): """Returns a layer to score matches of predicted versus target categories.""" y_hat, target_category = inputs predicted_category = np.argmax(y_hat, axis=axis) # TODO(pkozakowski): This assertion breaks some tests. Fix and uncomment. # shapes.assert_same_shape(predicted_category, target_category) return np.equal(predicted_category, target_category).astype(np.float32)
def WeightMask(target, mask_id=0, **unused_kwargs): if mask_id is None: return np.ones_like(target) return 1.0 - np.equal(target, mask_id).astype(np.float32)
def Accuracy(inputs, axis=-1, **unused_kwargs): prediction, target = inputs predicted_class = np.argmax(prediction, axis=axis) return np.equal(predicted_class, target)
def _ElementMask(target, id_to_mask=0, **unused_kwargs): """Returns a mask with zeros marking elements to exclude from calculations.""" if id_to_mask is None: return np.ones_like(target) return 1.0 - np.equal(target, id_to_mask).astype(np.float32)
def _Accuracy(inputs, axis=-1, **unused_kwargs): """Returns a layer to score matches of predicted versus target categories.""" y_hat, target_category = inputs predicted_category = np.argmax(y_hat, axis=axis) return np.equal(predicted_category, target_category).astype(np.float32)
def f(y_hat, target_category): # pylint: disable=invalid-name predicted_category = np.argmax(y_hat, axis=axis) # TODO(pkozakowski): This assertion breaks some tests. Fix and uncomment. # shapes.assert_same_shape(predicted_category, target_category) return np.equal(predicted_category, target_category).astype(np.float32)
def WeightMask(target, mask_id=0, **kw): del kw if mask_id is None: return np.ones_like(target) return 1.0 - np.equal(target, mask_id).astype(np.float32)
def Accuracy(x, axis=-1, **kw): del kw prediction, target = x predicted_class = np.argmax(prediction, axis=axis) return np.equal(predicted_class, target)