From c1cc94a33aca9304a5351b3da7c9ebd923eea396 Mon Sep 17 00:00:00 2001 From: Paul O'Leary McCann Date: Wed, 3 Nov 2021 14:16:55 +0000 Subject: [PATCH] Fix typo about receptive field size (#9564) --- spacy/ml/models/tok2vec.py | 2 +- website/docs/api/architectures.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/spacy/ml/models/tok2vec.py b/spacy/ml/models/tok2vec.py index 8d78e418f..44ab50e85 100644 --- a/spacy/ml/models/tok2vec.py +++ b/spacy/ml/models/tok2vec.py @@ -53,7 +53,7 @@ def build_hash_embed_cnn_tok2vec( window_size (int): 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 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 be surprisingly small, due to the use of the hash embeddings. Recommended values are between 2000 and 10000. diff --git a/website/docs/api/architectures.md b/website/docs/api/architectures.md index 7044a7d02..01ca4540b 100644 --- a/website/docs/api/architectures.md +++ b/website/docs/api/architectures.md @@ -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~~ | | `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~~ | -| `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~~ | | `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~~ |