Python tensorflow.bitcast()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。

bitcast()是張量流庫中的方法，用於將張量從一種類型轉換為另一種類型。它不會複製數據。

用法：
tf.bitcast(
    input, type, name
)

Arguments: 
1. input: It is the Tensor and the allowed type for this tensor are
          bfloat16, half, float32, float64, int64, int32, uint8, uint16, uint32,
          uint64, int8, int16, complex64, complex128, qint8, quint8, qint16, quint16, qint32.
2. type:It defines the dtype in which input need to be bitcasted.
3. name: It is an optional argument. It is used to give a name to operation.
 
返回： It returns a tensor of type type.

注意：位廣播不能用於將實際dtype轉換為複雜dtype。它將引發InvalidArgumentError。

範例1：

# importing the library 
import tensorflow 
  
# initializing the constant tensor of dtype unit32 
a = tensorflow.constant(0xffffffff, dtype=tensorflow.uint32) 
  
# Checking the initialized tensor 
print('a:',a) 
  
# bitcasting to dtype unit8 
b = tensorflow.bitcast(a, tensorflow.uint8) 
  
# Checking the bitcasted tensor 
print('b:',b)

輸出：

a:tf.Tensor(4294967295, shape=(), dtype=uint32)
b:tf.Tensor([255 255 255 255], shape=(4,), dtype=uint8)

範例2：

本示例嘗試將實數dtype轉換為複雜dtype

# importing the library 
import tensorflow 
  
# initializing the constant tensor of dtype unit32 
a = tensorflow.constant(0xffffffff, dtype=tensorflow.uint32) 
  
# Checking the initialized tensor 
print('a:',a) 
  
# bitcasting to dtype complex128 
b = tensorflow.bitcast(a, tensorflow.complex128)

輸出：