Rotate image(s) counter-clockwise by 90 degrees.
tf.image.rot90(
image, k=1, name=None
)
For example:
a=tf.constant([[[1],[2]],
[[3],[4]]])
# rotating `a` counter clockwise by 90 degrees
a_rot=tf.image.rot90(a)
print(a_rot[...,0].numpy())
[[2 4]
[1 3]]
# rotating `a` counter clockwise by 270 degrees
a_rot=tf.image.rot90(a, k=3)
print(a_rot[...,0].numpy())
[[3 1]
[4 2]]
Args |
|---|
image
|
4-D Tensor of shape [batch, height, width, channels] or 3-D Tensor
of shape [height, width, channels].
|
k
|
A scalar integer. The number of times the image is rotated by 90 degrees.
|
name
|
A name for this operation (optional).
|
Returns |
|---|
A rotated tensor of the same type and shape as image.
|
Raises |
|---|
ValueError
|
if the shape of image not supported.
|
TensorFlow 1 version
View source on GitHub