diff --git a/spacy/about.py b/spacy/about.py
index a441508f6..f95d391a6 100644
--- a/spacy/about.py
+++ b/spacy/about.py
@@ -1,6 +1,6 @@
# fmt: off
-__title__ = "spacy"
-__version__ = "3.0.0.dev13"
+__title__ = "spacy_nightly"
+__version__ = "3.0.0a0"
__release__ = True
__download_url__ = "https://github.com/explosion/spacy-models/releases/download"
__compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
diff --git a/spacy/cli/train.py b/spacy/cli/train.py
index 6fbb44d65..0853bfb56 100644
--- a/spacy/cli/train.py
+++ b/spacy/cli/train.py
@@ -332,13 +332,14 @@ def create_evaluation_callback(nlp, optimizer, corpus, cfg):
)
n_words = sum(len(ex.predicted) for ex in dev_examples)
+ batch_size = cfg.get("evaluation_batch_size", 128)
start_time = timer()
if optimizer.averages:
with nlp.use_params(optimizer.averages):
- scorer = nlp.evaluate(dev_examples, batch_size=32)
+ scorer = nlp.evaluate(dev_examples, batch_size=batch_size)
else:
- scorer = nlp.evaluate(dev_examples, batch_size=32)
+ scorer = nlp.evaluate(dev_examples, batch_size=batch_size)
end_time = timer()
wps = n_words / (end_time - start_time)
scores = scorer.scores
diff --git a/spacy/gold/corpus.py b/spacy/gold/corpus.py
index 42637ce5c..9a688987c 100644
--- a/spacy/gold/corpus.py
+++ b/spacy/gold/corpus.py
@@ -45,18 +45,22 @@ class Corpus:
def make_examples(self, nlp, reference_docs, max_length=0):
for reference in reference_docs:
- if len(reference) >= max_length >= 1:
- if reference.is_sentenced:
- for ref_sent in reference.sents:
- yield Example(
- nlp.make_doc(ref_sent.text),
- ref_sent.as_doc()
- )
- else:
+ if len(reference) == 0:
+ continue
+ elif max_length == 0 or len(reference) < max_length:
yield Example(
nlp.make_doc(reference.text),
reference
)
+ elif reference.is_sentenced:
+ for ref_sent in reference.sents:
+ if len(ref_sent) == 0:
+ continue
+ elif max_length == 0 or len(ref_sent) < max_length:
+ yield Example(
+ nlp.make_doc(ref_sent.text),
+ ref_sent.as_doc()
+ )
def make_examples_gold_preproc(self, nlp, reference_docs):
for reference in reference_docs:
@@ -65,7 +69,7 @@ class Corpus:
else:
ref_sents = [reference]
for ref_sent in ref_sents:
- yield Example(
+ eg = Example(
Doc(
nlp.vocab,
words=[w.text for w in ref_sent],
@@ -73,6 +77,8 @@ class Corpus:
),
ref_sent
)
+ if len(eg.x):
+ yield eg
def read_docbin(self, vocab, locs):
""" Yield training examples as example dicts """
diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx
index ceaea3c9c..743b4ca1d 100644
--- a/spacy/syntax/nn_parser.pyx
+++ b/spacy/syntax/nn_parser.pyx
@@ -449,7 +449,7 @@ cdef class Parser:
if component is self:
break
if hasattr(component, "pipe"):
- doc_sample = list(component.pipe(doc_sample))
+ doc_sample = list(component.pipe(doc_sample, batch_size=8))
else:
doc_sample = [component(doc) for doc in doc_sample]
if doc_sample:
diff --git a/website/src/components/button.js b/website/src/components/button.js
index 5e03ca312..410193a7e 100644
--- a/website/src/components/button.js
+++ b/website/src/components/button.js
@@ -27,7 +27,7 @@ Button.defaultProps = {
}
Button.propTypes = {
- to: PropTypes.string.isRequired,
+ to: PropTypes.string,
variant: PropTypes.oneOf(['primary', 'secondary', 'tertiary']),
large: PropTypes.bool,
icon: PropTypes.string,
diff --git a/website/src/images/icon_nightly.png b/website/src/images/icon_nightly.png
index 069c1b803..20326e46d 100644
Binary files a/website/src/images/icon_nightly.png and b/website/src/images/icon_nightly.png differ
diff --git a/website/src/images/pattern_landing_nightly.jpg b/website/src/images/pattern_landing_nightly.jpg
index 74f4cf7b6..6ff0d574d 100644
Binary files a/website/src/images/pattern_landing_nightly.jpg and b/website/src/images/pattern_landing_nightly.jpg differ
diff --git a/website/src/images/pattern_nightly.jpg b/website/src/images/pattern_nightly.jpg
index 685dffc02..a3fadd87b 100644
Binary files a/website/src/images/pattern_nightly.jpg and b/website/src/images/pattern_nightly.jpg differ
diff --git a/website/src/images/social_nightly.jpg b/website/src/images/social_nightly.jpg
index f7087fb54..29889df12 100644
Binary files a/website/src/images/social_nightly.jpg and b/website/src/images/social_nightly.jpg differ
diff --git a/website/src/pages/404.js b/website/src/pages/404.js
new file mode 100644
index 000000000..a25e8f553
--- /dev/null
+++ b/website/src/pages/404.js
@@ -0,0 +1,47 @@
+import React from 'react'
+import { window } from 'browser-monads'
+import { graphql } from 'gatsby'
+
+import Template from '../templates/index'
+import { LandingHeader, LandingTitle } from '../components/landing'
+import Button from '../components/button'
+
+export default ({ data, location }) => {
+ const { nightly } = data.site.siteMetadata
+ const pageContext = { title: '404 Error', searchExclude: true, isIndex: false }
+ return (
+
+
+
+ Ooops, this page
+
+ does not exist!
+
+
+
+
+
+ )
+}
+
+export const pageQuery = graphql`
+ query {
+ site {
+ siteMetadata {
+ nightly
+ title
+ description
+ navigation {
+ text
+ url
+ }
+ docSearch {
+ apiKey
+ indexName
+ }
+ }
+ }
+ }
+`
diff --git a/website/src/pages/404.md b/website/src/pages/404.md
deleted file mode 100644
index 910b552b3..000000000
--- a/website/src/pages/404.md
+++ /dev/null
@@ -1,7 +0,0 @@
----
-title: 404 Error
----
-
-import Error from 'widgets/404.js'
-
-
diff --git a/website/src/widgets/404.js b/website/src/widgets/404.js
deleted file mode 100644
index bc65e9f0d..000000000
--- a/website/src/widgets/404.js
+++ /dev/null
@@ -1,19 +0,0 @@
-import React from 'react'
-import { window } from 'browser-monads'
-
-import { LandingHeader, LandingTitle } from '../components/landing'
-import Button from '../components/button'
-
-export default () => (
-
-
- Ooops, this page
-
- does not exist!
-
-
-
-
-)