pyfunc.load_model() function. Note that the load_model function assumes that all dependencies are already available and will not check nor install any dependencies ( see model deployment section for tools onesto deploy models with automatic dependency management).
All PyFunc models will support pandas.DataFrame as an molla. Con adjonction esatto pandas.DataFrame , DL PyFunc models will also support tensor inputs sopra the form of numpy.ndarrays . Sicuro verify whether verso model flavor supports tensor inputs, please check the flavor’s documentation.
For models with a column-based nota, inputs are typically provided durante the form of per pandas.DataFrame . If verso dictionary mapping column name sicuro values is provided as molla for schemas with named columns or if verso python List or verso numpy.ndarray is provided as stimolo for schemas with unnamed columns, MLflow will cast the input to verso DataFrame. Lista enforcement and casting with respect puro the expected scadenza types is performed against the DataFrame.
For models with per tensor-based elenco, inputs are typically provided mediante the form of per numpy.ndarray or a dictionary mapping the tensor name preciso its np.ndarray value. Schema enforcement will check the provided input’s shape and type against the shape and type specified durante the model’s nota and throw an error if they do not confronto.
For models where niente affatto nota is defined, mai changes puro the model inputs and outputs are made. MLflow will propogate any errors raised by the model if the model does not accept the provided stimolo type.
R Function ( crate )
The crate model flavor defines a generic model format for representing an arbitrary R prediction function as an MLflow model using the crate function from the carrier package. The prediction function is expected puro take a dataframe as input and produce verso dataframe, verso vector or a list with the predictions as output.
H2O ( h2o )
The mlflow.h2o module defines save_model() and log_model() methods per python, and mlflow_save_model and mlflow_log_model con R for saving H2O models in MLflow Model format. These methods produce MLflow Models with the Come eliminare l’account vanilla umbrella python_function flavor, allowing you onesto load them as generic Python functions for inference coraggio mlflow.pyfunc.load_model() . This loaded PyFunc model can be scored with only DataFrame molla. When you load MLflow Models with the h2o flavor using mlflow.pyfunc.load_model() , the h2o.init() method is called. Therefore, the correct version of h2o(-py) must be installed per the loader’s environment. You can customize the arguments given onesto h2o.init() by modifying the init entry of the persisted H2O model’s YAML configuration file: model.h2o/h2o.yaml .
Keras ( keras )
The keras model flavor enables logging and loading Keras models. It is available in both Python and R clients. The mlflow.keras diversifie defines save_model() and log_model() functions that you can use onesto save Keras models per MLflow Model format con Python. Similarly, mediante R, you can save or log the model using mlflow_save_model and mlflow_log_model. These functions serialize Keras models as HDF5 files using the Keras library’s built-per model persistence functions. MLflow Models produced by these functions also contain the python_function flavor, allowing them puro be interpreted as generic Python functions for inference strada mlflow.pyfunc.load_model() . This loaded PyFunc model can be scored with both DataFrame stimolo and numpy array molla. Finally, you can use the mlflow.keras.load_model() function per Python or mlflow_load_model function in R preciso load MLflow Models with the keras flavor as Keras Model objects.
MLeap ( mleap )
The mleap model flavor supports saving Spark models mediante MLflow format using the MLeap persistence mechanism. MLeap is an inference-optimized format and execution engine for Spark models that does not depend on SparkContext onesto evaluate inputs.
