evaluate

Evaluate a trained model to determine how accurate it is.

Additional Documentation

Usage

                                                                                                                                                                                                                                                                                               
 Usage: yzlite evaluate [OPTIONS] <model>                                                                                                                                                                                                                                                        
                                                                                                                                                                                                                                                                                               
 Evaluate a trained ML model                                                                                                                                                                                                                                                                   
 This passes validation samples through a trained YZLITE model and generates a model performance summary.                                                                                                                                                                                        
 For more details see:                                                                                                                                                                                                                                                                         
 https://github.com/ReRAM-Labs/yzlite/docs/guides/model_evaluation                                                                                                                                                                                                                               
                                                                                                                                                                                                                                                                                               
 ----------                                                                                                                                                                                                                                                                                    
  Examples                                                                                                                                                                                                                                                                                     
 ----------                                                                                                                                                                                                                                                                                    
                                                                                                                                                                                                                                                                                               
 # Evaluate the .h5 (i.e. float32) model                                                                                                                                                                                                                                                       
 yzlite evaluate audio_example1                                                                                                                                                                                                                                                                  
                                                                                                                                                                                                                                                                                               
 # Evaluate the .h5 (i.e. float32) using model archive                                                                                                                                                                                                                                         
 yzlite evaluate ~/workspace/my_model.yzlite.zip                                                                                                                                                                                                                                                   
                                                                                                                                                                                                                                                                                               
 # Evaluate the .tflite (i.e. quantized) model                                                                                                                                                                                                                                                 
 # and limit the max samples per class to 100                                                                                                                                                                                                                                                  
 yzlite evaluate audio_example1 --tflite --count 100                                                                                                                                                                                                                                             
                                                                                                                                                                                                                                                                                               
 # Evaluate the .tflite (i.e. quantized) auto encoder model                                                                                                                                                                                                                                    
 # and dump the input/output images                                                                                                                                                                                                                                                            
 yzlite evaluate fully_connected_autoencoder --tflite --dump                                                                                                                                                                                                                                     
                                                                                                                                                                                                                                                                                               
 Note: All log files are generated in the <model log dir>/eval directory.                                                                                                                                                                                                                      
 It a YZLITE model is provided, the model's archive is updated with the evaluation results.                                                                                                                                                                                                      
                                                                                                                                                                                                                                                                                               
 Arguments 
 *    model      <model>  Name of previously trained YZLITE model or path to trained model's archive (.yzlite.zip) [default: None] [required]                                                                                                                                                    

 Options 
 --tflite                                                   Evaluate the .tflite (i.e. quantized) model file.                                                                                                                                                                                
                                                            If omitted, evaluate the Keras .h5 model (i.e. float)                                                                                                                                                                            
 --weights         -w                         <weights>     Optional, load weights from previous training session.                             [default: None]                                                                                                                               
                                                            May be one of the following:                                                                                                                                                                                                     
                                                            - If option omitted then evaluate using output .h5 or .tflite from training                                                                                                                                                      
                                                            - Absolute path to a generated weights .h5 file generated by Keras during training                                                                                                                                               
                                                            - The keyword `best`; find the best weights in <model log dir>/train/weights                                                                                                                                                     
                                                            - Filename of .h5 in <model log dir>/train/weights                                                                                                                                                                               
                                                            Note: This option may only be used if the "--tflite" option is *not* used                                                                                                                                                        
 --classes                                    <class-list>  If evaluating a model with the EvaluateAutoEncoderMixin mixin,        [default: None]                                                                                                                                            
                                                            then this should be a comma-seperated list of classes in the dataset.                                                                                                                                                            
                                                            The first element should be considered the "normal" class,                                                                                                                                                                       
                                                            every other class is considered abnormal and compared independently.                                                                                                                                                             
                                                            If not provided, then the classes default to: [normal, abnormal]                                                                                                                                                                 
 --count           -c                         <value>       By default, all validation samples are used.                                                      [default: -1]                                                                                                                  
                                                            This option places an upper limit on the number of samples per class that are used for evaluation                                                                                                                                
 --dump                --no-dump                            If evaluating a model with the EvaluateAutoEncoderMixin mixin, then, for each sample, an image will be generated comparing the sample to the decoded sample [default: no-dump]                                                   
 --show                --no-show                            Display the generated performance diagrams [default: no-show]                                                                                                                                                                    
 --verbose         -v                                       Enable verbose console logs                                                                                                                                                                                                      
 --update-archive      --no-update-archive                  Update the model archive with the evaluation results [default: update-archive]                                                                                                                                                   
 --test                --no-test                            Use the model created by the test training. This does the same thing as: yzlite evaluate my_model-test [default: no-test]                                                                                                          
 --post                                                     This allows for post-processing the evaluation results (e.g. uploading to a cloud) if supported by the given YZLiteModel                                                                                                           
 --help                                                     Show this message and exit.