hummingbird.ml.operator_converters.constants¶
Constants used in the Hummingbird converters are defined here.
- hummingbird.ml.operator_converters.constants.BASE_PREDICTION = 'base_prediction'¶
base prediction for ensemble models requiring it.
- hummingbird.ml.operator_converters.constants.FEATURE_NAMES = 'feature_names'¶
Names of the features used for training.
- hummingbird.ml.operator_converters.constants.GET_PARAMETERS_FOR_TREE_TRAVERSAL = 'get_parameters_for_tree_trav'¶
Which function to use to extract the parameters for the tree traversal strategy.
- hummingbird.ml.operator_converters.constants.IFOREST_THRESHOLD = 'iforest_threshold'¶
threshold of the sklearn isolation forest implementation, backward compatibility for sklearn <= 0.21.
- hummingbird.ml.operator_converters.constants.LEARNING_RATE = 'learning_rate'¶
Learning Rate.
- hummingbird.ml.operator_converters.constants.MAX_SAMPLES = 'max_samples'¶
max_samples of sklearn isolation forest implementation.
- hummingbird.ml.operator_converters.constants.NUM_TREES = 'n_trees'¶
Number of trees composing an ensemble.
- hummingbird.ml.operator_converters.constants.N_FEATURES = 'n_features'¶
Number of features expected in the input data.
- hummingbird.ml.operator_converters.constants.N_INPUTS = 'n_inputs'¶
Number of inputs expected by the model.
- hummingbird.ml.operator_converters.constants.OFFSET = 'offset'¶
offset of the sklearn anomaly detection implementation.
- hummingbird.ml.operator_converters.constants.ONNX_INITIALIZERS = 'onnx_initializers'¶
The initializers of the onnx model.
- hummingbird.ml.operator_converters.constants.POST_TRANSFORM = 'post_transform'¶
Post transform for tree inference.
- hummingbird.ml.operator_converters.constants.REORDER_TREES = 'reorder_trees'¶
Whether to reorder trees in multiclass tasks.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_CONTAINER_PATH = 'container.pkl'¶
Path where to find the container when saving or loading.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_MODEL_CONFIGURATION_PATH = 'model_configuration.txt'¶
Path where to find the modules versions used when saving or loading.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_MODEL_TYPE_PATH = 'model_type.txt'¶
Path where to find the model type when saving or loading.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_ONNX_PATH = 'deploy_model.onnx'¶
Path where to find the onnx model when saving or loading.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_TORCH_JIT_PATH = 'deploy_model.zip'¶
Path where to find the torchscript model when saving or loading.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_TVM_GRAPH_PATH = 'deploy_graph.json'¶
Path where to find the TVM graph when saving or loading.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_TVM_LIB_PATH = 'deploy_lib.tar'¶
Path where to find the TVM lib when saving or loading.
- hummingbird.ml.operator_converters.constants.SAVE_LOAD_TVM_PARAMS_PATH = 'deploy_param.params'¶
Path where to find the TVM params when saving or loading.
- hummingbird.ml.operator_converters.constants.SIGMOID = 'LOGISTIC'¶
Sigmoid post transform.
- hummingbird.ml.operator_converters.constants.SOFTMAX = 'SOFTMAX'¶
Softmax post transform.
- hummingbird.ml.operator_converters.constants.SUPPORTED_STRING_TYPES = {'S', 'U'}¶
Numpy string types suppoted by Humingbird.
- hummingbird.ml.operator_converters.constants.TEST_INPUT = 'test_input'¶
The test input data for models that need to be traced.
- hummingbird.ml.operator_converters.constants.TVM_CONTEXT = 'tvm_context'¶
The context for TVM containing information on the target.
- hummingbird.ml.operator_converters.constants.TVM_GRAPH = 'tvm_graph'¶
The graph defining the TVM model. This parameter is used for saving and loading a TVM model.
- hummingbird.ml.operator_converters.constants.TVM_INPUT_NAMES = 'tvm_input_names'¶
TVM expects named inputs. This is used to set the names for the inputs.
- hummingbird.ml.operator_converters.constants.TVM_LIB = 'tvm_lib'¶
The lib for the TVM model. This parameter is used for saving and loading a TVM model.
- hummingbird.ml.operator_converters.constants.TVM_PARAMS = 'tvm_params'¶
The params for the TVM model. This parameter is used for saving and loading a TVM model.
- hummingbird.ml.operator_converters.constants.TWEEDIE = 'TWEEDIE'¶
Tweedie post transform.