Question

我想让我的模型的输入图像（张量）向上/向下或向右/向左移动，然后再填充。

例如，如果原始图像是3x3，如下所示，

1 2 3
4 5 6
7 8 9

然后，如果我转向左边，

2 3 0
5 6 0
8 9 0

我发现Tensorflow中有一个图像旋转功能，但我找不到翻译或移位。如果有内置功能，请告诉我，或建议实施的方式。

Answer 1

我根据tf.contrib.image.transform编写了一个函数来执行此操作： https://gist.github.com/astromme/8116a154be8dae5528f33669e490c19a

## Tensorflow image translation op
# images:        A tensor of shape (num_images, num_rows, num_columns, num_channels) (NHWC),
#                (num_rows, num_columns, num_channels) (HWC), or (num_rows, num_columns) (HW).
# tx:            The translation in the x direction.
# ty:            The translation in the y direction.
# interpolation: If x or y are not integers, interpolation comes into play. Options are 'NEAREST' or 'BILINEAR'
def tf_image_translate(images, tx, ty, interpolation='NEAREST'):
    # got these parameters from solving the equations for pixel translations
    # on https://www.tensorflow.org/api_docs/python/tf/contrib/image/transform
    transforms = [1, 0, -tx, 0, 1, -ty, 0, 0]
    return tf.contrib.image.transform(images, transforms, interpolation)

像这样使用：

translation_op = tf_image_translate(images, tx=-5, ty=10)

with tf.Session() as sess:
    translated_images = sess.run(translation_op)

Answer 2

我认为您可以将tf.image.crop_to_bounding_box和tf.image.pad_to_bounding_box结合起来实现这一目标。这是API：https://www.tensorflow.org/api_guides/python/image#Cropping

Answer 3

现在有一个功能（至少从TF v1.6开始）： tf.contrib.image.translate

如何在tensorflow中翻译（或移位）图像

3 个答案: