[DOCS] Zero-Shot Image Classification Tutorial

[jacobmarks]

Tutorial showing off zero-shot image classification workflows with FiftyOne, including loading CLIP, OpenCLIP, and Hugging Face Transformers models for zero-shot image classification, applying to a dataset, and robustly evaluating these predictions.

It highlights:

• OpenCLIP integration
• Hugging Face Transformers integration
• Ultralytics Integration (at the end)
• The power of the plugin system
• The flexibility of the filtering/querying in FiftyOne

PDF version attached:

Zero-Shot Image Classification with Multimodal Models and FiftyOne — FiftyOne 0.24.0 documentation.pdf

• App: FiftyOne application changes
• Build: Build and test infrastructure changes
• Core: Core fiftyone Python library changes
• Documentation: FiftyOne documentation changes
• Other

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 15.98%. Comparing base (a4d5e31) to head (c189e2d).
Report is 12 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #4133   +/-   ##
========================================
  Coverage    15.98%   15.98%           
========================================
  Files          732      732           
  Lines        82054    82054           
  Branches      1110     1110           
========================================
  Hits         13115    13115           
  Misses       68939    68939           

Flag	Coverage Δ
app	15.98% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[danielgural]

LGTM

[brimoor]

LGTM