Function test_BatchNorm1D

numpy_ml/tests/test_nn.py:748–797

(N=15)

def test_BatchNorm1D(N=15):
    from numpy_ml.neural_nets.layers import BatchNorm1D

    np.random.seed(12345)

    N = np.inf if N is None else N

    np.random.seed(12345)

    i = 1
    while i < N + 1:
        n_ex = np.random.randint(2, 1000)
        n_in = np.random.randint(1, 1000)
        X = random_tensor((n_ex, n_in), standardize=True)

        # initialize BatchNorm1D layer
        L1 = BatchNorm1D()

        # forward prop
        y_pred = L1.forward(X)

        # backprop
        dLdy = np.ones_like(y_pred)
        dLdX = L1.backward(dLdy)

        # get gold standard gradients
        gold_mod = TorchBatchNormLayer(
            n_in, L1.parameters, "1D", epsilon=L1.epsilon, momentum=L1.momentum
        )
        golds = gold_mod.extract_grads(X)

        params = [
            (L1.X[0], "X"),
            (y_pred, "y"),
            (L1.parameters["scaler"].T, "scaler"),
            (L1.parameters["intercept"], "intercept"),
            (L1.parameters["running_mean"], "running_mean"),
            #  (L1.parameters["running_var"], "running_var"),
            (L1.gradients["scaler"], "dLdScaler"),
            (L1.gradients["intercept"], "dLdIntercept"),
            (dLdX, "dLdX"),
        ]

        print("Trial {}".format(i))
        for ix, (mine, label) in enumerate(params):
            assert_almost_equal(
                mine, golds[label], err_msg=err_fmt(params, golds, ix), decimal=1
            )
            print("\tPASSED {}".format(label))
        i += 1


def test_LayerNorm1D(N=15):