chore: polish benchmark doc #839
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report
@@ Coverage Diff @@
## clip-benchmark #839 +/- ##
===============================================
Coverage 81.58% 81.58%
===============================================
Files 21 21
Lines 1575 1575
===============================================
Hits 1285 1285
Misses 290 290
Flags with carried forward coverage won't be shown. Click here to find out more. Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
ZiniuYu
requested changes
Oct 10, 2022
docs/user-guides/benchmark.rst
Outdated
|
|
||
| Zero-shot retrieval | ||
| Zero-shot Retrieval | ||
| +++++++++++++++++++ | ||
|
|
||
| In zero-shot retrieval benchmark, each model is evaluated on the following datasets: `COCO Caption <https://github.com/tylin/coco-caption>`_, `Flickr8k <http://hockenmaier.cs.illinois.edu/8k-pictures.html>`_ and `Flickr30k <https://shannon.cs.illinois.edu/DenotationGraph/>`_. |
There was a problem hiding this comment.
Suggested change
| In zero-shot retrieval benchmark, each model is evaluated on the following datasets: `COCO Caption <https://github.com/tylin/coco-caption>`_, `Flickr8k <http://hockenmaier.cs.illinois.edu/8k-pictures.html>`_ and `Flickr30k <https://shannon.cs.illinois.edu/DenotationGraph/>`_. | |
| In the zero-shot retrieval benchmark, each model is evaluated on the following datasets: `COCO Caption <https://github.com/tylin/coco-caption>`_, `Flickr8k <http://hockenmaier.cs.illinois.edu/8k-pictures.html>`_ and `Flickr30k <https://shannon.cs.illinois.edu/DenotationGraph/>`_. | |
| The best results are highlighted in bold (higher is better). |
docs/user-guides/benchmark.rst
Outdated
| @@ -151,7 +154,7 @@ From the table, we observe that the ViT models outperform the RN models in gener | |||
| More specifically, the ``ViT-H-14::laion2b_s32b_b79k`` model and ``ViT-g-14::laion2b_s12b_b42k`` model achieve the best and second-best results on all zero-shot retrieval tasks. | |||
| For ViT models, the results of the same base model are better on those pre-trained with larger datasets (e.g., ``ViT-B-32::openai`` vs ``ViT-B-32::laion400m_e31`` vs ``ViT-B-32::laion2b-s34b-b79k``). | |||
|
|
|||
| Zero-shot classification | |||
| Zero-shot Classification | |||
| ++++++++++++++++++++++++ | |||
|
|
|||
| In zero-shot classification benchmark, each model is evaluated on the following datasets: `ImageNetV2 <https://github.com/modestyachts/ImageNetV2>`_, `VOC2007 <http://host.robots.ox.ac.uk/pascal/VOC/voc2007/>`_ and 19 `VTAB datasets <https://github.com/google-research/task_adaptation>`_. | |||
There was a problem hiding this comment.
Suggested change
| In zero-shot classification benchmark, each model is evaluated on the following datasets: `ImageNetV2 <https://github.com/modestyachts/ImageNetV2>`_, `VOC2007 <http://host.robots.ox.ac.uk/pascal/VOC/voc2007/>`_ and 19 `VTAB datasets <https://github.com/google-research/task_adaptation>`_. | |
| In the zero-shot classification benchmark, each model is evaluated on the following datasets: `ImageNetV2 <https://github.com/modestyachts/ImageNetV2>`_, `VOC2007 <http://host.robots.ox.ac.uk/pascal/VOC/voc2007/>`_ and 19 `VTAB datasets <https://github.com/google-research/task_adaptation>`_. | |
| The best results are highlighted in bold (higher is better). |
ZiniuYu
approved these changes
Oct 10, 2022
|
📝 Docs are deployed on https://ft-polish-clip-benchmark--jina-docs.netlify.app 🎉 |
numb3r3
added a commit
that referenced
this pull request
Oct 10, 2022
…832) * docs: clip benchmark on zeroshot classification and retrieval tasks * docs: add label * docs: introduction * docs: open clip naming convention * fix: typo * docs: retrieval table * docs: update classification * chore: test html table * chore: update css * chore: test rst * chore: test rst * chore: test * fix: use rst in benchmark * fix: typo * fix: rst * fix: rst * fix: subtitle * docs: classification benchmark * docs: highlight retrieval * docs: highlight retireval * docs: highlight classification * docs: remove redundancy * docs: add links * fix: link * docs: update section * docs: datasets description * docs: add datasets description * docs: format * docs: footnote * docs: add QPS * docs: improve conclusion * docs: update machine config * docs: update software version * chore: polish benchmark doc (#839) * chore: update benchmark intro * chore: minor revision * chore: minor revision * chore: minor revision * chore: minor revision * chore: minor revision * chore: minor revision Co-authored-by: felix-wang <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.