tf.keras.preprocessing.image.smart_resize

Изменение размера изображений до целевого размера без искажения соотношения сторон.

tf.keras.preprocessing.image.smart_resize(
    x, size, interpolation='bilinear'
)

Наборы данных изображений TensorFlow обычно содержат изображения разного размера. Однако перед обработкой слоями Keras эти изображения необходимо объединить в пакет. Для объединения изображения должны иметь одинаковую высоту и ширину.

Вы могли бы просто сделать:

size = (200, 200)
ds = ds.map(lambda img: tf.image.resize(img, size))
```

However, if you do this, you distort the aspect ratio of your images, since
in general they do not all have the same aspect ratio as `size`. This is
fine in many cases, but not always (e.g. for GANs this can be a problem).

Note that passing the argument `preserve_aspect_ratio=True` to `resize`
will preserve the aspect ratio, but at the cost of no longer respecting the
provided target size. Because <a href="../../../../tf/image/resize"><code>tf.image.resize</code></a> doesn't crop images,
your output images will still have different sizes.

#### This calls for:



```python
size = (200, 200)
ds = ds.map(lambda img: smart_resize(img, size))
```

Your output images will actually be `(200, 200)`, and will not be distorted.
Instead, the parts of the image that do not fit within the target size
get cropped out.

The resizing process is:

1. Take the largest centered crop of the image that has the same aspect ratio
as the target size. For instance, if `size=(200, 200)` and the input image has
size `(340, 500)`, we take a crop of `(340, 340)` centered along the width.
2. Resize the cropped image to the target size. In the example above,
we resize the `(340, 340)` crop to `(200, 200)`.

<!-- Tabular view -->
 <table class="responsive fixed orange">
<colgroup><col width="214px"><col></colgroup>
<tr><th colspan="2"><h2 class="add-link">Arguments</h2></th></tr>

<tr>
<td>
`x`
</td>
<td>
Input image (as a tensor or NumPy array). Must be in format
`(height, width, channels)`.
</td>
</tr><tr>
<td>
`size`
</td>
<td>
Tuple of `(height, width)` integer. Target size.
</td>
</tr><tr>
<td>
`interpolation`
</td>
<td>
String, interpolation to use for resizing.
Defaults to `'bilinear'`. Supports `bilinear`, `nearest`, `bicubic`,
`area`, `lanczos3`, `lanczos5`, `gaussian`, `mitchellcubic`.
</td>
</tr>
</table>



<!-- Tabular view -->
 <table class="responsive fixed orange">
<colgroup><col width="214px"><col></colgroup>
<tr><th colspan="2"><h2 class="add-link">Returns</h2></th></tr>
<tr class="alt">
<td colspan="2">
Array with shape `(size[0], size[1], channels)`. If the input image was a
NumPy array, the output is a NumPy array, and if it was a TF tensor,
the output is a TF tensor.
</td>
</tr>

</table>