test_models_keras.py 文件源码

def test_keras_model_gradients():
    num_classes = 1000
    bounds = (0, 255)
    channels = num_classes

    with warnings.catch_warnings():
        warnings.filterwarnings("ignore", category=DeprecationWarning)
        inputs = Input(shape=(5, 5, channels))
        logits = GlobalAveragePooling2D(
            data_format='channels_last')(inputs)

        preprocessing = (np.arange(num_classes)[None, None],
                         np.random.uniform(size=(5, 5, channels)) + 1)

        model = KerasModel(
            Model(inputs=inputs, outputs=logits),
            bounds=bounds,
            predicts='logits',
            preprocessing=preprocessing)

    eps = 1e-3

    np.random.seed(22)
    test_image = np.random.rand(5, 5, channels).astype(np.float32)
    test_label = 7

    _, g1 = model.predictions_and_gradient(test_image, test_label)

    test_label_array = np.array([test_label])
    l1 = model._loss_fn([test_image[None] - eps / 2 * g1, test_label_array])[0]
    l2 = model._loss_fn([test_image[None] + eps / 2 * g1, test_label_array])[0]

    assert 1e5 * (l2 - l1) > 1

    # make sure that gradient is numerically correct
    np.testing.assert_array_almost_equal(
        1e5 * (l2 - l1),
        1e5 * eps * np.linalg.norm(g1)**2,
        decimal=1)