Skip to content

Releases: fkodom/clip-text-decoder

1.4.4

07 Nov 15:27
f2df8ed

Choose a tag to compare

What's Changed

  • Fix string error when loading clip models. by @Adenialzz in #12

New Contributors

Full Changelog: 1.4.3...1.4.4

1.4.3

07 Nov 03:23
4993f4c

Choose a tag to compare

What's Changed

Full Changelog: 1.4.2...1.4.3

1.4.2

26 Oct 13:44
e477dab

Choose a tag to compare

What's Changed

Full Changelog: 1.4.1...1.4.2

1.4.1

26 Oct 13:33
2de7981

Choose a tag to compare

What's Changed

Full Changelog: 1.4.0...1.4.1

1.4.0

23 Oct 03:31
a262bce

Choose a tag to compare

What's Changed

Full Changelog: 1.3.0...1.4.0

1.3.0

02 Oct 01:23
d530c05

Choose a tag to compare

What's Changed

Full Changelog: 1.2.0...1.3.0

1.2.0

29 Jan 15:03
16bbc75

Choose a tag to compare

What's Changed

  • Cache CLIP embeddings for the dataset, rather than recomputing them each time.

  • Reduce model file sizes by storing at lower precision

  • Add an ImageCaptionInferenceModel class for easier out-of-the-box use

  • Fix some broken unit tests

  • Better Data Caching by @fkodom in #3

  • Bug Fixes for Broken Tests by @fkodom in #4

Full Changelog: 1.1.0...1.2.0

1.1.0

22 Dec 15:26
63b8491

Choose a tag to compare

What's Changed

New Contributors

  • @fkodom made their first contribution in #2

Full Changelog: 1.0.0...1.1.0

1.0.0

15 Nov 03:17

Choose a tag to compare

Move example predictions up higher in README

0.1.1

14 Nov 19:32

Choose a tag to compare

0.1.1 Pre-release
Pre-release

Add installation docs to README, and automatically publish to PyPI using GitHub Actions workflow.