Tensorflow：tf.image.resize 仍然没有对齐角吗？

Question

我正在Hackernoon 上阅读这篇关于函数如何不是反射等变的博客文章Tensorflow's tf.image.resize_area()。因此，如果我要在某些数据增强步骤中调整图像大小，这可能会真正搞砸模型训练。

作者继续说，用户不应该使用任何tf.image.resize功能，因为潜在的不可预测的行为。这篇文章来自 2018 年 1 月，所以不久前。其实我看了文章的评论区，没有人提到问题已经解决。

我只是想知道这些问题是否仍然存在，解决方法是什么？后续版本中的任何更改tensorflow。比如我可以使用tf.keras增强函数来避免这些问题吗？

Answer 1

在我最初阅读您引用的 Hackernoon 文章后，我也看到了这篇文章，它很好地总结了 OpenCV、TF 1.X 和其他一些 DL 框架中双线性插值的不同实现。

我在 TF 2.0 文档中找不到任何关于此的内容，因此我复制了该文章中给出的示例以测试 2.0 中的双线性插值。当我使用 TensorFlow 2.0 运行以下代码时，测试通过，因此看起来迁移到 TF2.0 将为您提供与 OpenCV 实现匹配的双线性插值实现（因此解决了 Hackernoon 文章中提出的问题）：

def test_tf2_resample_upsample_matches_opencv_methodology():
    """
    According to the article below, the Tensorflow 1.x implementation of bilinear interpolation for resizing images did
    not reproduce the pixel-area-based approach adopted by OpenCV. The `align_corners` option was set to False by
    default due to some questionable legacy reasons but users were advised to set it to True in order to get a
    'reasonable' output: https://jricheimer.github.io/tensorflow/2019/02/11/resize-confusion/
    This appears to have been fixed in TF 2.0 and this test confirms that we get the results one would expect from a
    pixel-area-based technique.

    We start with an input array whose values are equivalent to their column indices:
    input_arr = np.array([
        [[0], [1], [2], [3], [4], [5]],
        [[0], [1], [2], [3], [4], [5]],
    ])

    And then resize this (holding the rows dimension constant in size, but increasing the column dimnesion to 12) to
    reproduce the OpenCV example from the article. We expect this to produce the following output:
    expected_output = np.array([
        [[0], [0.25], [0.75], [1.25], [1.75], [2.25], [2.75], [3.25], [3.75], [4.25], [4.75], [5]],
        [[0], [0.25], [0.75], [1.25], [1.75], [2.25], [2.75], [3.25], [3.75], [4.25], [4.75], [5]],
    ])

    """
    input_tensor = tf.convert_to_tensor(
        np.array([
            [[0], [1], [2], [3], [4], [5]],
            [[0], [1], [2], [3], [4], [5]],
        ]),
        dtype=tf.float32,
    )
    output_arr = tf.image.resize(
        images=input_tensor,
        size=(2,12),
        method=tf.image.ResizeMethod.BILINEAR).numpy()
    expected_output = np.array([
        [[0], [0.25], [0.75], [1.25], [1.75], [2.25], [2.75], [3.25], [3.75], [4.25], [4.75], [5]],
        [[0], [0.25], [0.75], [1.25], [1.75], [2.25], [2.75], [3.25], [3.75], [4.25], [4.75], [5]],
    ])
    np.testing.assert_almost_equal(output_arr, expected_output, decimal=2)