search

google-research / tapas

End-to-end neural table-text understanding models.
Apache License 2.0
1.15k stars 217 forks source link

WTQ prediction #43

Closed lairikeqiA closed 4 years ago

lairikeqiA commented 4 years ago

I plan to predict WTQ. How can I set parameters when I run convert_prediction.py?

lairikeqiA commented 4 years ago

flags.DEFINE_list('interaction_files', None, 'A list of files contain interactions protos.') flags.DEFINE_list('prediction_files', None, 'A list of files that contain model prediction.') flags.DEFINE_string('output_directory', None, 'Output directory where converted files will be stored.') flags.DEFINE_enum_class('dataset_format', None, convert_predictions_utils.DatasetFormat, 'Dataset format.')

ghost commented 4 years ago

interactions are the interaction you create from the original WTQ data. run_task_main can do that for you. The Dataset format should be tfrecords. The predictions are the once created by run_task_main.