當前位置: 首頁>>編程示例 >>用法及示例精選 >>正文


Python tensorflow.IndexedSlices.graph屬性用法及代碼示例

TensorFlow是Google設計的開源Python庫,用於開發機器學習模型和深度學習神經網絡。

graph用於查找包含值,索引和形狀張量的Graph。

用法:tensorflow.IndexedSlices.graph

返回:它返回一個Graph實例。

範例1:



Python3

# Importing the library 
import tensorflow as tf 
  
# Initializing the input 
data = tf.constant([[1, 2, 3], [4, 5, 6]], dtype = tf.float32) 
  
# Printing the input 
print('data:', data) 
  
# Calculating result 
res = tf.IndexedSlices(data, [0]) 
  
# Finding Graph 
@tf.function 
def gfg():  
  tf.compat.v1.disable_eager_execution() 
  
  graph = res.graph 
  
  # Printing the result 
  print('graph:', graph) 
  
  
gfg()

輸出:


data: Tensor("Const_1:0", shape=(2, 3), dtype=float32)
graph: <tensorflow.python.framework.ops.Graph object at 0x7f2eeda9e630>

<tf.Operation 'PartitionedCall_1' type=PartitionedCall>

範例2:

Python3

# Importing the library 
import tensorflow as tf 
  
# Initializing the input 
data = tf.constant([1, 2, 3]) 
  
# Printing the input 
print('data:', data) 
  
# Calculating result 
res = tf.IndexedSlices(data, [0]) 
  
# Finding Graph  
graph = res.graph 
  
# Printing the result 
print('graph:', graph)

輸出:


data: Tensor("Const_6:0", shape=(3, ), dtype=int32)
graph: <tensorflow.python.framework.ops.Graph object at 0x7f2eeda9e630>




相關用法


注:本文由純淨天空篩選整理自aman neekhara大神的英文原創作品 Python – tensorflow.IndexedSlices.graph Attribute。非經特殊聲明,原始代碼版權歸原作者所有,本譯文未經允許或授權,請勿轉載或複製。