mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 03:19:13 +03:00
375f0dc529
Currently the TextCategorizer defaults to a fairly complicated model, designed partly around the active learning requirements of Prodigy. The model's a bit slow, and not very GPU-friendly. This patch implements a straightforward CNN model that still performs pretty well. The replacement model also makes it easy to use the LMAO pretraining, since most of the parameters are in the CNN. The replacement model has a flag to specify whether labels are mutually exclusive, which defaults to True. This has been a common problem with the text classifier. We'll also now be able to support adding labels to pretrained models again. Resolves #2934, #2756, #1798, #1748. |
||
|---|---|---|
| .. | ||
| information_extraction | ||
| keras_parikh_entailment | ||
| notebooks | ||
| pipeline | ||
| training | ||
| deep_learning_keras.py | ||
| README.md | ||
| vectors_fast_text.py | ||
| vectors_tensorboard.py | ||
spaCy examples
The examples are Python scripts with well-behaved command line interfaces. For more detailed usage guides, see the documentation.
To see the available arguments, you can use the --help or -h flag:
$ python examples/training/train_ner.py --help
While we try to keep the examples up to date, they are not currently exercised by the test suite, as some of them require significant data downloads or take time to train. If you find that an example is no longer running, please tell us! We know there's nothing worse than trying to figure out what you're doing wrong, and it turns out your code was never the problem.