Add clip resources to the transformers documentation #20190
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
stevhliu
reviewed
Nov 14, 2022
Co-authored-by: Steven Liu <[email protected]>
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
sgugger
approved these changes
Nov 15, 2022
NielsRogge
reviewed
Nov 15, 2022
Comment on lines
+89
to
+94
| <PipelineTag pipeline="image-to-text"/> | ||
| - A notebook showing [Video to text matching with CLIP for videos](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/X-CLIP/Video_text_matching_with_X_CLIP.ipynb). | ||
|
|
||
|
|
||
| <PipelineTag pipeline="zero-shot-classification"/> | ||
| - A notebook showing [Zero shot video classification using CLIP for video](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/X-CLIP/Zero_shot_classify_a_YouTube_video_with_X_CLIP.ipynb). |
There was a problem hiding this comment.
These are resources for X-CLIP, not CLIP.
NielsRogge
reviewed
Nov 15, 2022
Comment on lines
+85
to
+86
| - A blog post on [How to use CLIP to retrieve images from text](https://huggingface.co/blog/fine-tune-clip-rsicd). | ||
| - A blog bost on [How to use CLIP for Japanese text to image generation](https://huggingface.co/blog/japanese-stable-diffusion). |
There was a problem hiding this comment.
The first sentence should be something along the lines of "How to fine-tune CLIP on image-text pairs" rather than "How to retrieve...", the second one is not relevant for CLIP, as it's a blog about Stable Diffusion.
|
Folks, please make sure resources which are added are talking about the particular model. |
mpierrau
pushed a commit
to mpierrau/transformers
that referenced
this pull request
Dec 15, 2022
* WIP: Added CLIP resources from HuggingFace blog * ADD: Notebooks documentation to clip * Add link straight to notebook Co-authored-by: Steven Liu <[email protected]> * Change notebook links to colab Co-authored-by: Ambuj Pawar <[email protected]> Co-authored-by: Steven Liu <[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.
What does this PR do?
Fixes #20055 (partially)
Before submitting
Pull Request section?
to it if that's the case. Model resources contribution #20055
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@stevhliu Please can you have a look?