Python tensorflow.IndexedSlices.op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。

op用於查找用於產生值作為輸出的操作。它僅在禁用急切執行時有效。

用法：tensorflow.IndexedSlices.op

範例1：在此示例中，急切執行被禁用。

# Importing the library 
import tensorflow as tf 
  
# Disable Eager execution 
tf.compat.v1.disable_eager_execution() 
  
# Initializing the input 
data = tf.constant([[1, 2, 3], [4, 5, 6]]) 
  
# Printing the input 
print('data:', data) 
  
# Calculating result 
res = tf.IndexedSlices(data, [0], 1) 
  
# Finding operation 
op = res.op 
  
# Printing the result 
print('Operation:', op)

輸出：

data: Tensor("Const:0", shape=(2, 3), dtype=int32)
Operation: name:"Const"
op:"Const"
attr {
  key:"dtype"
  value {
    type:DT_INT32
  }
}
attr {
  key:"value"
  value {
    tensor {
      dtype:DT_INT32
      tensor_shape {
        dim {
          size:2
        }
        dim {
          size:3
        }
      }
      tensor_content:"\001\000\000\000\002\000\000\000\003\000\000\000\004\000\000\000\005\000\000\000\006\000\000\000"
    }
  }
}

範例2：在此示例中，啟用了急切執行，因此將引發AttributeError。

# Importing the library 
import tensorflow as tf 
  
# Initializing the input 
data = tf.constant([[1, 2, 3], [4, 5, 6]]) 
  
# Printing the input 
print('data:', data) 
  
# Calculating result 
res = tf.IndexedSlices(data, [0], 1) 
  
# Finding operation 
op = res.op 
  
# Printing the result 
print('Operation:', op)

輸出：

data: tf.Tensor(
[[1 2 3]
 [4 5 6]], shape=(2, 3), dtype=int32)

---------------------------------------------------------------------------

AttributeError                            Traceback (most recent call last)

<ipython-input-1-8dd32836815c> in <module>()
     12 
     13 # Finding operation
---> 14 op = res.op
     15 
     16 # Printing the result

1 frames

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py in op(self)
   1111   def op(self):
   1112     raise AttributeError(
-> 1113         "Tensor.op is meaningless when eager execution is enabled.")
   1114 
   1115   @property

AttributeError:Tensor.op is meaningless when eager execution is enabled.