在tensorflow 2.0中添加无维度

Question

我有一个xx形状为的张量：

>>> xx.shape
TensorShape([32, 32, 256])

如何添加前导None尺寸以获得：

>>> xx.shape
TensorShape([None, 32, 32, 256])

我在这里看到了很多答案，但都与 TF 1.x 有关

TF 2.0 的直接方式是什么？

Answer 1

您可以使用“None”或 numpy 的“newaxis”来创建新维度。

一般提示：您还可以使用 None 代替 np.newaxis；这些实际上是相同的对象。

下面是解释这两个选项的代码。

try:
  %tensorflow_version 2.x
except Exception:
  pass
import tensorflow as tf

print(tf.__version__)

# TensorFlow and tf.keras
from tensorflow import keras

# Helper libraries
import numpy as np

#### Import the Fashion MNIST dataset
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

#Original Dimension
print(train_images.shape)

train_images1 = train_images[None,:,:,:]
#Add Dimension using None
print(train_images1.shape)

train_images2 = train_images[np.newaxis is None,:,:,:]
#Add dimension using np.newaxis
print(train_images2.shape)

#np.newaxis and none are same
np.newaxis is None

上述代码的输出是

2.1.0
(60000, 28, 28)
(1, 60000, 28, 28)
(1, 60000, 28, 28)
True