explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix typo about receptive field size (#9564)

Browse Source
This commit is contained in:
Paul O'Leary McCann 2021-11-03 14:16:55 +00:00 committed by GitHub
parent e06bbf72a4
commit c1cc94a33a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/ml/models/tok2vec.py
View File

@ -53,7 +53,7 @@ def build_hash_embed_cnn_tok2vec(
window_size (int): The number of tokens on either side to concatenate during window_size (int): The number of tokens on either side to concatenate during
the convolutions. The receptive field of the CNN will be the convolutions. The receptive field of the CNN will be
depth * (window_size * 2 + 1), so a 4-layer network with window_size of depth * (window_size * 2 + 1), so a 4-layer network with window_size of
2 will be sensitive to 17 words at a time. Recommended value is 1. 2 will be sensitive to 20 words at a time. Recommended value is 1.
embed_size (int): The number of rows in the hash embedding tables. This can embed_size (int): The number of rows in the hash embedding tables. This can
be surprisingly small, due to the use of the hash embeddings. Recommended be surprisingly small, due to the use of the hash embeddings. Recommended
values are between 2000 and 10000. values are between 2000 and 10000.

2
website/docs/api/architectures.md
View File

@ -82,7 +82,7 @@ consisting of a CNN and a layer-normalized maxout activation function.
| `width` | The width of the input and output. These are required to be the same, so that residual connections can be used. Recommended values are `96`, `128` or `300`. ~~int~~ | | `width` | The width of the input and output. These are required to be the same, so that residual connections can be used. Recommended values are `96`, `128` or `300`. ~~int~~ |
| `depth` | The number of convolutional layers to use. Recommended values are between `2` and `8`. ~~int~~ | | `depth` | The number of convolutional layers to use. Recommended values are between `2` and `8`. ~~int~~ |
| `embed_size` | The number of rows in the hash embedding tables. This can be surprisingly small, due to the use of the hash embeddings. Recommended values are between `2000` and `10000`. ~~int~~ | | `embed_size` | The number of rows in the hash embedding tables. This can be surprisingly small, due to the use of the hash embeddings. Recommended values are between `2000` and `10000`. ~~int~~ |
| `window_size` | The number of tokens on either side to concatenate during the convolutions. The receptive field of the CNN will be `depth * (window_size * 2 + 1)`, so a 4-layer network with a window size of `2` will be sensitive to 17 words at a time. Recommended value is `1`. ~~int~~ | | `window_size` | The number of tokens on either side to concatenate during the convolutions. The receptive field of the CNN will be `depth * (window_size * 2 + 1)`, so a 4-layer network with a window size of `2` will be sensitive to 20 words at a time. Recommended value is `1`. ~~int~~ |
| `maxout_pieces` | The number of pieces to use in the maxout non-linearity. If `1`, the [`Mish`](https://thinc.ai/docs/api-layers#mish) non-linearity is used instead. Recommended values are `1`-`3`. ~~int~~ | | `maxout_pieces` | The number of pieces to use in the maxout non-linearity. If `1`, the [`Mish`](https://thinc.ai/docs/api-layers#mish) non-linearity is used instead. Recommended values are `1`-`3`. ~~int~~ |
| `subword_features` | Whether to also embed subword features, specifically the prefix, suffix and word shape. This is recommended for alphabetic languages like English, but not if single-character tokens are used for a language such as Chinese. ~~bool~~ | | `subword_features` | Whether to also embed subword features, specifically the prefix, suffix and word shape. This is recommended for alphabetic languages like English, but not if single-character tokens are used for a language such as Chinese. ~~bool~~ |
| `pretrained_vectors` | Whether to also use static vectors. ~~bool~~ | | `pretrained_vectors` | Whether to also use static vectors. ~~bool~~ |