比较与tf.keras.preprocessing.image.random_shear的功能差异

tf.keras.preprocessing.image.random_shear

tf.keras.preprocessing.image.random_shear(
    x,
    intensity,
    row_axis=1,
    col_axis=2,
    channel_axis=0,
    fill_mode='nearest',
    cval=0.0,
    interpolation_order=1
)

更多内容详见tf.keras.preprocessing.image.random_shear。

mindspore.dataset.vision.RandomAffine

class mindspore.dataset.vision.RandomAffine(
    degrees,
    translate=None,
    scale=None,
    shear=None,
    resample=Inter.NEAREST,
    fill_value=0
)

更多内容详见mindspore.dataset.vision.RandomAffine。

使用方式

TensorFlow：对图像进行随机剪切，图像的行、列及通道轴索引可通过入参指定。

MindSpore：对图像进行随机仿射变换，其中包括随机剪切，图像需按照行、列、通道的轴顺序排列。

代码示例

# The following implements RandomAffine with MindSpore.
import numpy as np
import mindspore.dataset as ds
from mindspore.dataset.vision import Inter

image = np.random.random((28, 28, 3))
result = ds.vision.RandomAffine(0, shear=30, resample=Inter.NEAREST)(image)
print(result.shape)
# (28, 28, 3)

# The following implements random_shear with TensorFlow.
import tensorflow as tf

image = np.random.random((28, 28, 3))
result = tf.keras.preprocessing.image.random_shear(
    image, intensity=30, row_axis=0, col_axis=1, channel_axis=2, fill_mode='nearest')
print(result.shape)
# (28, 28, 3)