allennlp.commands.predictΒΆ

The predict subcommand allows you to make bulk JSON-to-JSON predictions using a trained model and its Predictor wrapper.

$ allennlp predict --help
usage: allennlp [command] predict [-h]
                                  [--output-file OUTPUT_FILE]
                                  [--batch-size BATCH_SIZE]
                                  [--silent]
                                  [--cuda-device CUDA_DEVICE]
                                  [-o OVERRIDES]
                                  [--include-package INCLUDE_PACKAGE]
                                  [--predictor PREDICTOR]
                                  archive_file input_file

Run the specified model against a JSON-lines input file.

positional arguments:
archive_file          the archived model to make predictions with
input_file            path to input file

optional arguments:
-h, --help            show this help message and exit
--output-file OUTPUT_FILE
                        path to output file
--batch-size BATCH_SIZE
                        The batch size to use for processing
--silent              do not print output to stdout
--cuda-device CUDA_DEVICE
                        id of GPU to use (if any)
-o OVERRIDES, --overrides OVERRIDES
                        a HOCON structure used to override the experiment
                        configuration
--include-package INCLUDE_PACKAGE
                        additional packages to include
--predictor PREDICTOR
                        optionally specify a specific predictor to use