AI-generated Key Takeaways
- 
          
The CustomValidationConfig.Builder class is used to construct a custom validation configuration.
 - 
          
It provides methods to set properties like the accuracy validator, batch size, golden configuration, golden inputs, golden outputs, and inference timeout.
 - 
          
The build method returns the final CustomValidationConfig object after all desired properties have been set.
 - 
          
The setAccuracyValidator method allows specifying how to determine if a benchmark result passes accuracy checks.
 - 
          
The setGoldenInputs method is used to set the input data for the validation test.
 
Builder class.
Public Constructor Summary
| 
                 
                  
                  Builder()
                   
              
                    Creates the custom validation config builder.
                   
                 | 
            
Public Method Summary
| CustomValidationConfig | 
                 
                  
                  build()
                   
              
                    Returns the  
                
                    CustomValidationConfig result.
                   | 
            
| CustomValidationConfig.Builder | 
                 
                  
                  setAccuracyValidator(CustomValidationConfig.AccuracyValidator
                  value)
                   
              
                    Sets the  
                
                    CustomValidationConfig.AccuracyValidator to decide whether a
                    
                    BenchmarkResult passes accuracy check.
                   | 
            
| CustomValidationConfig.Builder | 
                 
                  
                  setBatchSize(int value)
                   
              
                    Sets the number of batches of the golden input.
                   
                 | 
            
| CustomValidationConfig.Builder | 
                 
                  
                  setGoldenConfig(AccelerationConfig
                  value)
                   
              
                    Sets the  
                
                    AccelerationConfig used to calculate golden output if the
                    
                    CustomValidationConfig.goldenOutputs() is not provided.
                   | 
            
| CustomValidationConfig.Builder | |
| CustomValidationConfig.Builder | |
| CustomValidationConfig.Builder | 
                 
                  
                  setInferenceTimeoutMillis(long value)
                   
              
                    Sets the time out setting for a validation test.
                   
                 | 
            
Inherited Method Summary
Public Constructors
public Builder ()
Creates the custom validation config builder.
Public Methods
public CustomValidationConfig build ()
Returns the 
            CustomValidationConfig result.
Throws
| IllegalArgumentException | if 
                CustomValidationConfig.goldenInputs() is not set, or 
                CustomValidationConfig.accuracyValidator() is not set, or both
                
                CustomValidationConfig.goldenOutputs() and 
                CustomValidationConfig.goldenConfig() are set | 
              
|---|
public CustomValidationConfig.Builder setAccuracyValidator (CustomValidationConfig.AccuracyValidator value)
Sets the 
            CustomValidationConfig.AccuracyValidator to decide whether a BenchmarkResult
            passes accuracy check. If accuracy validation is not needed, set this field to
            
            CustomValidationConfig.SKIP_VALIDATION. Default value is set to
            
            CustomValidationConfig.BYTE_MATCHING_VALIDATOR.
public CustomValidationConfig.Builder setBatchSize (int value)
Sets the number of batches of the golden input. Set to 1 by default.
public CustomValidationConfig.Builder setGoldenConfig (AccelerationConfig value)
Sets the 
            AccelerationConfig used to calculate golden output if the 
            CustomValidationConfig.goldenOutputs() is not provided. By default it is set
            to 
            CustomValidationConfig.DEFAULT_GOLDEN_CONFIG. If accuracy validation is not
            needed, set this field to null.
public CustomValidationConfig.Builder setGoldenInputs (Object... value)
Sets the golden input of validation test. The value should be in the
            same order as inputs of the model. When more than one batch input is provided, the same
            input from different batches needs to be concatenated as one of the allowed input type.
            Each value can be an array or multidimensional rectangular array, or a
            Buffer of primitive types including int, float, long, and byte, or null.
            When Buffer is used, its content should remain unchanged until the
            
            build() is done, and the caller must ensure that the Buffer is
            at the appropriate read position. Boolean and String tensor type is not supported.
public CustomValidationConfig.Builder setGoldenOutputs (ByteBuffer... value)
Sets the golden output used for accuracy validation. It will be passed to
            
            CustomValidationConfig.AccuracyValidator.validate(BenchmarkResult,
            ByteBuffer[]) when verifying actual and golden output. If this is not
            provided, we will use 
            CustomValidationConfig.goldenConfig() to calculate the golden output
            first.
public CustomValidationConfig.Builder setInferenceTimeoutMillis (long value)
Sets the time out setting for a validation test.