yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-09-25 16:15:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Show warning in reader.eval() about differences compared to pipeline.eval() (#2477)

Browse Source 
* deprecate reader.eval

* Update Documentation & Code Style

* update warning to describe differences between pipeline.eval()

* remove empty lines

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
This commit is contained in:
tstadel 2022-06-23 18:40:17 +02:00 committed by GitHub
parent e69492a28f
commit a084a982c4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
haystack/nodes/reader/farm.py
View File

@ -818,6 +818,14 @@ class FARMReader(BaseReader):
Choose from torch.device("cpu") and torch.device("cuda") (or simply "cpu" or "cuda")
or use the Reader's device by default.
"""
logger.warning(
"FARMReader.eval_on_file() uses a slightly different evaluation approach than `Pipeline.eval()`:\n"
"- instead of giving you full control over which labels to use, this method always returns three types of metrics: combined (no suffix), text_answer ('_text_answer' suffix) and no_answer ('_no_answer' suffix) metrics.\n"
"- instead of comparing predictions with labels on a string level, this method compares them on a token-ID level. This makes it unable to do any string normalization (e.g. normalize whitespaces) beforehand.\n"
"Hence, results might slightly differ from those of `Pipeline.eval()`\n."
"If you are just about starting to evaluate your model consider using `Pipeline.eval()` instead."
)
if device is None:
device = self.devices[0]
else:
@ -887,6 +895,14 @@ class FARMReader(BaseReader):
:param use_no_answer_legacy_confidence: Whether to use the legacy confidence definition for no_answer: difference between the best overall answer confidence and the no_answer gap confidence.
Otherwise we use the no_answer score normalized to a range of [0,1] by an expit function (default).
"""
logger.warning(
"FARMReader.eval() uses a slightly different evaluation approach than `Pipeline.eval()`:\n"
"- instead of giving you full control over which labels to use, this method always returns three types of metrics: combined (no suffix), text_answer ('_text_answer' suffix) and no_answer ('_no_answer' suffix) metrics.\n"
"- instead of comparing predictions with labels on a string level, this method compares them on a token-ID level. This makes it unable to do any string normalization (e.g. normalize whitespaces) beforehand.\n"
"Hence, results might slightly differ from those of `Pipeline.eval()`\n."
"If you are just about starting to evaluate your model consider using `Pipeline.eval()` instead."
)
if device is None:
device = self.devices[0]
else: