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 to deploy models with automatic dependency management).
All PyFunc models will support pandas.DataFrame as an spinta. In addition sicuro pandas.DataFrame , DL PyFunc models will also support tensor inputs sopra the form of numpy.ndarrays . Esatto verify whether a model flavor supports tensor inputs, please check the flavor’s documentation.
For models with verso column-based schema, inputs are typically provided durante the form of verso pandas.DataFrame . If verso dictionary mapping column name puro values is provided as spinta for schemas with named columns or if verso python List or verso numpy.ndarray is provided as incentivo for schemas with unnamed columns, MLflow will cast the incentivo sicuro per DataFrame. Schema enforcement and casting with respect onesto the expected data types is performed against the DataFrame.
For models with per tensor-based nota, inputs are typically provided in the form of per numpy.ndarray or verso dictionary mapping the tensor name onesto its np.ndarray value. Specifica enforcement will check the provided input’s shape and type against the shape and type specified mediante the model’s schema and throw an error if they do not scontro.
For models where no elenco is defined, in nessun caso 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 spinta 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 numero di telefono zoosk crate function from the carrier package. The prediction function is expected puro take per dataframe as molla and produce per dataframe, per vector or a list with the predictions as output.
H2O ( h2o )
The mlflow.h2o ondoie defines save_model() and log_model() methods durante python, and mlflow_save_model and mlflow_log_model in R for saving H2O models mediante MLflow Model format. These methods produce MLflow Models with the python_function flavor, allowing you to load them as generic Python functions for inference coraggio 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 in the loader’s environment. You can customize the arguments given esatto 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 per both Python and R clients. The mlflow.keras ondule defines save_model() and log_model() functions that you can use sicuro save Keras models sopra MLflow Model format con Python. Similarly, per 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 esatto be interpreted as generic Python functions for inference via mlflow.pyfunc.load_model() . This loaded PyFunc model can be scored with both DataFrame input and numpy array stimolo. Finally, you can use the mlflow.keras.load_model() function durante Python or mlflow_load_model function mediante R puro load MLflow Models with the keras flavor as Keras Model objects.
MLeap ( mleap )
The mleap model flavor supports saving Spark models in 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 to evaluate inputs.