tf.compat.v1.losses.Reduction
    
    
      
    
    
      
      Stay organized with collections
    
    
      
      Save and categorize content based on your preferences.
    
  
  
      
    
  
  
  
  
  
    
  
  
    
    
Types of loss reduction.
Contains the following values:
- NONE: Un-reduced weighted losses with the same shape as input.
- SUM: Scalar sum of weighted losses.
- MEAN: Scalar- SUMdivided by sum of weights. DEPRECATED.
- SUM_OVER_BATCH_SIZE: Scalar- SUMdivided by number of elements in losses.
- SUM_OVER_NONZERO_WEIGHTS: Scalar- SUMdivided by number of non-zero
weights. DEPRECATED.
- SUM_BY_NONZERO_WEIGHTS: Same as- SUM_OVER_NONZERO_WEIGHTS. DEPRECATED.
Methods
all
View source
@classmethod
all()
validate
View source
@classmethod
validate(
    key
)
| Class Variables | 
|---|
| MEAN | 'weighted_mean' | 
| NONE | 'none' | 
| SUM | 'weighted_sum' | 
| SUM_BY_NONZERO_WEIGHTS | 'weighted_sum_by_nonzero_weights' | 
| SUM_OVER_BATCH_SIZE | 'weighted_sum_over_batch_size' | 
| SUM_OVER_NONZERO_WEIGHTS | 'weighted_sum_by_nonzero_weights' | 
  
  
 
  
    
    
      
       
    
    
  
  
  Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
  Last updated 2024-04-26 UTC.
  
  
  
    
      [null,null,["Last updated 2024-04-26 UTC."],[],[]]