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 esatto deploy models with automatic dependency management).
All PyFunc models will support pandas.DataFrame as an input. Mediante addition esatto pandas.DataFrame , DL PyFunc models will also support tensor inputs mediante the form of numpy.ndarrays . Esatto verify whether verso model flavor supports tensor inputs, please check the flavor’s documentation.
For models with per column-based schema, inputs are typically provided sopra the form of per pandas.DataFrame . If a dictionary mapping column name puro values is provided as spinta for schemas with named columns or if a python List or verso numpy.ndarray is provided as stimolo for schemas with unnamed columns, MLflow will cast the spinta esatto per DataFrame. Elenco enforcement and casting with respect sicuro the expected datazione types is performed against the DataFrame.
For models with per tensor-based specifica, inputs are typically provided mediante the form of verso numpy.ndarray or verso dictionary mapping the tensor name esatto its np.ndarray value. Precisazione enforcement will check the provided input’s shape and type against the shape and type specified sopra the model’s nota and throw an error if they do not competizione.
For models where no elenco is defined, mai changes to the model inputs and outputs are made. MLflow will propogate any errors raised by the model if the model does not accept the provided molla type.
R Function ( crate )
The crate model flavor defines per 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 esatto take a dataframe as molla and produce verso dataframe, per vector or per 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 in R for saving H2O models sopra MLflow Model format. These methods produce MLflow Models with the python_function flavor, allowing you onesto load them as generic Python functions for inference cammino mlflow.pyfunc.load_model() . This loaded PyFunc model can be scored with only DataFrame incentivo. 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 con the loader’s environment. You can customize the arguments given preciso 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 sopra both Python and R clients. The mlflow.keras varie defines save_model() and log_model() functions that you can use onesto save Keras models in MLflow Model format per Python. Similarly, durante 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-con model persistence functions. MLflow Models produced by these functions also contain the python_function flavor, allowing them sicuro be interpreted as generic Python functions for inference coraggio mlflow.pyfunc.load_model() . This loaded PyFunc model can be scored with both DataFrame incentivo and numpy array molla. Finally, you can use the mlflow.keras.load_model() function in Python or mlflow_load_model function durante R onesto load MLflow Models with the keras flavor as Keras Model objects.
MLeap ( mleap )
The mleap model flavor supports saving Spark models durante MLflow format using the MLeap persistence mechanism. MLeap is an Codice sconto telegraph dating inference-optimized format and execution engine for Spark models that does not depend on SparkContext to evaluate inputs.