比较与tf.image.random_crop的功能差异

查看源文件

tf.image.random_crop

tf.image.random_crop(
    value,
    size,
    seed=None,
    name=None
)

更多内容详见tf.image.random_crop

mindspore.dataset.vision.c_transforms.RandomCrop

class mindspore.dataset.vision.c_transforms.RandomCrop(
    size,
    padding=None,
    pad_if_needed=False,
    fill_value=0,
    padding_mode=Border.CONSTANT
)

更多内容详见mindspore.dataset.vision.c_transforms.RandomCrop

使用方式

TensorFlow:对图像进行随机裁剪,随机种子可通过入参指定。

MindSpore:对图像进行随机裁剪,支持同时填充图像,随机种子需通过 mindspore.dataset.config.set_seed 全局设置。

代码示例

# The following implements RandomCrop with MindSpore.
import numpy as np
import mindspore.dataset as ds

ds.config.set_seed(57)
image = np.random.random((28, 28, 3))
result = ds.vision.c_transforms.RandomCrop((5, 5))(image)
print(result.shape)
# (5, 5, 3)

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

image = tf.random.normal((28, 28, 3))
result = tf.image.random_crop(image, (5, 5, 3), seed=57)
print(result.shape)
# (5, 5, 3)