tf.image.random_saturation——tf2.1 Document

參考自tf2.1官方文檔:
https://www.tensorflow.org/api_docs/python/tf/image/random_saturation

---

Adjust the saturation of RGB images by a random factor.
該函數用於隨機調整RGB圖像的飽和度。

tf.image.random_saturation(
    image, lower, upper, seed=None
)

Equivalent to adjust_saturation() but uses a saturation_factor randomly picked in the interval [lower, upper].
在區間[lower, upper]上隨機選擇saturation_factor，更改圖片飽和度

Args:

• image: RGB image or images. Size of the last dimension must be 3.

• image: 單張RGB圖片或多張RGB圖片，最後一維必須爲3

• lower: float. Lower bound for the random saturation factor.

• lower: 浮點數，隨機saturation factor的下限。

• upper: float. Upper bound for the random saturation factor.

• upper: 浮點數，隨機saturation factor的上限。

• seed: An operation-specific seed.
  It will be used in conjunction with the graph-level seed to determine the real seeds that will be used in this operation.
  Please see the documentation of set_random_seed for its interaction with the graph-level random seed.

• seed: 特定操作的種子。(注：筆者不太明白這個種子和隨機數種子有什麼區別，只是感覺有點兒玄乎)

Returns:

• Adjusted image(s), same shape and DType as image.
• 飽和度調整過後的圖片，與輸入 image 有相同的shape和類型

Raises:

• ValueError: if upper <= lower or if lower < 0.
• 如果 upper <= lower 或者 lower < 0，將 raise ValueError