transformers.js
Add support for computing CLIP image and text embeddings separately (Closes #148)
#227
Merged
Merged
Add support for computing CLIP image and text embeddings separately (Closes #148) #227
xenova
merged
17 commits into
main
from
clip-split
Define custom CLIP ONNX configs
a528d1ba
Update conversion script
c1332f98
Support specifying custom model file name
aba4c95d
Use int64 for CLIP input ids
1b101876
Add support for CLIP text and vision models
82281c16
Fix JSDoc
b15b8023
Add docs for `CLIPTextModelWithProjection`
48c9e4bd
Add docs for `CLIPVisionModelWithProjection`
b2b9980a
Add unit test for CLIP text models
093acfa4
Add unit test for CLIP vision models
f42bf9c9
Set resize precision to 3 decimal places
421446c9
Fix `RawImage.save()` function
5ceebd6d
Throw error when reading image and status != 200
3db01c19
Create basic semantic image search application
7038e60c
Separate out components
4837c2c3
Add `update-database` script
954b7854
Update transformers.js version
c67e4cea
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub