Created
July 5, 2017 17:28
-
-
Save dpressel/2aea46cc0d211b530d6afb1fed7bd0d2 to your computer and use it in GitHub Desktop.
Run baseline classifier model in a REPL
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from baseline import classifier_repl | |
| # You can use any of the implementations interchangeably! | |
| from baseline.keras.classify import ConvModel | |
| import argparse | |
| """ | |
| Example of loading a previously trained classifier (in Keras) and interacting | |
| with it using a shell. Your shell inputs (for the time being) should be | |
| in the form the model tokenizes its training data. | |
| """ | |
| parser = argparse.ArgumentParser(description='Type some tokenized text') | |
| parser.add_argument('--model', help='Model file', default='classifier-model-keras') | |
| args = parser.parse_args() | |
| model = ConvModel.load(args.model) | |
| classifier_repl(model) | |
| # E.g. | |
| # class> this is garbage | |
| # Guess [0]: 0.995 | |
| # class> this is totally amazing ! | |
| # Guess [1]: 1.000 | |
| # class> quit |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment