def test_softmax_calculate_gradient(self):
# Given
pre_activation = np.array([[1, 2, 3, 6], [2, 4, 5, 6], [3, 8, 7, 6]])
target = np.array([[1, 0, 0, 0], [0, 1, 0, 0], [0, 0, 1, 0]])
softmax = Softmax()
# When
activation = softmax.apply_activation(pre_activation)
grad = softmax.calculate_gradient(activation, target)
