Classification test result object. More...
Inherits TestResultBase.
Public Member Functions | |
| None | ClassificationTestResult (self, str file_name) |
| Load a saved classification test result from a file. | |
Public Member Functions inherited from PolimagoFactoryCreatedObject | |
| None | save (self, str file_name) |
| Save this object into a file. | |
Properties | |
| classes = property | |
| List[str]: Class labels available in this test result. | |
| error_rate = property | |
| float: Total number of errors divided by the total number of examples. | |
| example_confidence_distributions = property | |
| List[List[float]]: Confidence distributions for each example. | |
| example_confidences = property | |
| List[float]: Confidences in the classification decision for each sample. | |
| num_classes = property | |
| int: Number of classes in the sample database on which the test result was calculated. | |
| num_errors = property | |
| int: Total number of errors made during classification testing. | |
| output_dimension = property | |
| int: For tests with usage OneVersusAll the output dimension will equal the number of classes in the training database. | |
| predicted_class_indices = property | |
| List[int]: Prediction results for all indices. | |
| true_class_indices = property | |
| List[int]: The real class index for each example. | |
Properties inherited from TestResultBase | |
| example_mean_square_error = property | |
| List[float]: Mean square error for each individual example (the index runs over all the examples that contributed to this test result). | |
| feature_resolution = property | |
| int: Feature resolution value with which the classifier was trained. | |
| num_examples = property | |
| int: Number of examples that contributed to this test result. | |
| total_mean_square_error = property | |
| float: Total mean square error of the predictor over all examples and all coordinates. | |
Properties inherited from PolimagoFactoryCreatedObject | |
| correction = property | |
| cvb.Point2D: Correction factors in X and Y direction required to rescale the input images for projection onto the retina. | |
| feature_window_extent = property | |
| cvb.Rect: The feature window extent that has been used during classifier training. | |
| file_name = property | |
| str: Name of the file the object has been loaded from (or empty string if the object was not loaded). | |
| image_planes = property | |
| int: Intercept weight that has been used for generating this object. | |
| interpolation = property | |
| int: Interpolation setting used for generating this object (see cvb.polimago.InterpolationType). | |
| lambda_ = property | |
| float: Regularization value that has been used for generating this object. | |
| offset = property | |
| float: Intercept weight that has been used for generating this object. | |
| preprocessing = property | |
| str: Preprocessing code with which this object was generated. | |
| retina_size = property | |
| cvb.Size2D: Size of the 'Retina' in pixels. | |
Classification test result object.
| None ClassificationTestResult | ( | self, | |
| str | file_name ) |
Load a saved classification test result from a file.
file_name : str Name of the file to be loaded.
|
static |
int: For tests with usage OneVersusAll the output dimension will equal the number of classes in the training database.
For usage ClassifyOneVersusOne the output dimension is (NumClasses - 1) * (NumClasses) / 2.