mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-27 22:21:08 +03:00
ef0820827a
These experiments were completed a few weeks ago, but I didn't make the PR, pending model release.
Token vector width: 128->96
Hidden width: 128->64
Embed size: 5000->2000
Dropout: 0.2->0.1
Updated optimizer defaults (unclear how important?)
This should improve speed, model size and load time, while keeping
similar or slightly better accuracy.
The tl;dr is we prefer to prevent over-fitting by reducing model size,
rather than using more dropout.
|
||
|---|---|---|
| .. | ||
| converters | ||
| __init__.py | ||
| _messages.py | ||
| conll17_ud_eval.py | ||
| convert.py | ||
| download.py | ||
| evaluate.py | ||
| info.py | ||
| init_model.py | ||
| link.py | ||
| package.py | ||
| pretrain.py | ||
| profile.py | ||
| train.py | ||
| ud_run_test.py | ||
| ud_train.py | ||
| validate.py | ||
| vocab.py | ||