TensorFlow – 如何广播参数以在 ND 网格上进行评估

TensorFlow 是由 Google 设计的开源Python库，用于开发机器学习模型和深度学习神经网络。

在使用 TensorFlow 时，一些操作会自动广播参数，有时我们必须显式地广播参数。使用网格网格方法显式广播参数。

Method Used:

meshgrid: This method is used to broadcasts parameters for evaluation on an N-D grid. It accepts rank-1 tensors and broadcast all of them to same shape and returns a list of N Tensors with rank N. Default indexing for this method is ‘xy’.

示例 1：在此方法中使用默认索引。

Python3

# importing the library
import tensorflow as tf
  
# Initializing Input
x = [1, 2, 3]
y = [4, 5, 6, 7]
  
# Printing the Input
print("x: ", x)
print("y: ", y)
  
# Broadcasting the Tensors
X, Y = tf.meshgrid(x, y)
  
# Printing the resulting Tensors
print("X: ", X)
print("Y: ", Y)

Python3

# importing the library
import tensorflow as tf
  
# Initializing Input
x = [1, 2, 3]
y = [4, 5, 6, 7]
  
# Printing the Input
print("x: ", x)
print("y: ", y)
  
# Broadcasting the Tensors
X, Y = tf.meshgrid(x, y, indexing = 'ij')
  
# Printing the resulting Tensors
print("X: ", X)
print("Y: ", Y)

输出：

x:  [1, 2, 3]
y:  [4, 5, 6, 7]
X:  tf.Tensor(
[[1 2 3]
 [1 2 3]
 [1 2 3]
 [1 2 3]], shape=(4, 3), dtype=int32)
Y:  tf.Tensor(
[[4 4 4]
 [5 5 5]
 [6 6 6]
 [7 7 7]], shape=(4, 3), dtype=int32)

示例 2：在此示例中，索引更改为“ij”。

Python3

# importing the library
import tensorflow as tf
  
# Initializing Input
x = [1, 2, 3]
y = [4, 5, 6, 7]
  
# Printing the Input
print("x: ", x)
print("y: ", y)
  
# Broadcasting the Tensors
X, Y = tf.meshgrid(x, y, indexing = 'ij')
  
# Printing the resulting Tensors
print("X: ", X)
print("Y: ", Y)

输出：

x:  [1, 2, 3]
y:  [4, 5, 6, 7]
X:  tf.Tensor(
[[1 1 1 1]
 [2 2 2 2]
 [3 3 3 3]], shape=(3, 4), dtype=int32)
Y:  tf.Tensor(
[[4 5 6 7]
 [4 5 6 7]
 [4 5 6 7]], shape=(3, 4), dtype=int32)