batchflow.models

• dataset.models.metrics
  • Metrics
    • Metrics
      • Metrics.evaluate()
  • ClassificationMetrics
    • ClassificationMetrics
      • ClassificationMetrics.accuracy()
      • ClassificationMetrics.append()
      • ClassificationMetrics.condition_negative()
      • ClassificationMetrics.condition_positive()
      • ClassificationMetrics.confusion_matrix
      • ClassificationMetrics.copy()
      • ClassificationMetrics.diagnostics_odds_ratio()
      • ClassificationMetrics.f1_score()
      • ClassificationMetrics.false_discovery_rate()
      • ClassificationMetrics.false_negative()
      • ClassificationMetrics.false_negative_rate()
      • ClassificationMetrics.false_omission_rate()
      • ClassificationMetrics.false_positive()
      • ClassificationMetrics.false_positive_rate()
      • ClassificationMetrics.free()
      • ClassificationMetrics.jaccard()
      • ClassificationMetrics.negative_likelihood_ratio()
      • ClassificationMetrics.negative_predictive_value()
      • ClassificationMetrics.one_hot()
      • ClassificationMetrics.plot_confusion_matrix()
      • ClassificationMetrics.positive_likelihood_ratio()
      • ClassificationMetrics.positive_predictive_value()
      • ClassificationMetrics.prediction_negative()
      • ClassificationMetrics.prediction_positive()
      • ClassificationMetrics.prevalence()
      • ClassificationMetrics.total_population()
      • ClassificationMetrics.true_negative()
      • ClassificationMetrics.true_negative_rate()
      • ClassificationMetrics.true_positive()
      • ClassificationMetrics.true_positive_rate()
      • ClassificationMetrics.update()
  • SegmentationMetricsByPixels
    • SegmentationMetricsByPixels
  • SegmentationMetricsByInstances
    • SegmentationMetricsByInstances
      • SegmentationMetricsByInstances.condition_positive()
      • SegmentationMetricsByInstances.free()
      • SegmentationMetricsByInstances.prediction_positive()
      • SegmentationMetricsByInstances.total_population()
      • SegmentationMetricsByInstances.true_negative()
      • SegmentationMetricsByInstances.true_positive()
• batchflow.models.torch
  • Models
    • TorchModel
    • VGG
    • ResNet
    • UNet
  • Custom layers and blocks

Contains models

class BaseModel

Base interface for models.

property default_name

Placeholder for model name.

classmethod is_model_like(obj)

Check if the obj provides the same interface, as required by this specification.

abstractmethod load()

Load the model from the disc.

abstractmethod predict()

Make a prediction using the model.

abstractmethod reset()

Reset the trained model to allow a new training from scratch.

abstractmethod save()

Save the model to the disc.

abstractmethod train()

Train the model.

class SklearnModel(*args, **kwargs)

Base class for scikit-learn models

estimator

an instance of scikit-learn estimator

Notes

Configuration

estimator - an instance of scikit-learn estimator

load / path - a path to a pickled estimator

Examples

pipeline
    .init_model('static', SklearnModel, 'my_model',
                config={'estimator': sklearn.linear_model.SGDClassifier(loss='huber')})

pipeline
    .init_model('static', SklearnModel, 'my_model',
                config={'load/path': '/path/to/estimator.pickle'})

build(*args, **kwargs)

Define the model

load(path)

Load the model.

Parameters:

path (str) – a full path to a file from which a model will be loaded

predict(x, *args, **kwargs)

Predict with the data provided

Parameters:

X (array-like) – Subset of the training data, shape (n_samples, n_features)

Notes

For more details and other parameters look at the documentation for the estimator used.

Returns:

Predicted value per sample, shape (n_samples,)

Return type:

array

reset()

Reset the trained model to allow a new training from scratch

save(path)

Save the model.

Parameters:

path (str) – a full path to a file where a model will be saved to

train(x, y, *args, **kwargs)

Train the model with the data provided

Parameters:

• X (array-like) – Subset of the training data, shape (n_samples, n_features)

• y (numpy array) – Subset of the target values, shape (n_samples,)

Notes

For more details and other parameters look at the documentation for the estimator used.