Prototype: Object Embeddings v0#1431
Conversation
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
| @@ -1,21 +1,42 @@ | |||
| import { readAnnotationsWithPayloadInfiniteOptions } from '$lib/api/lightly_studio_local/@tanstack/svelte-query.gen'; | |||
| import { client as apiClient } from '$lib/api/lightly_studio_local/client.gen'; | |||
There was a problem hiding this comment.
The changes in this file are only required to make the lasso select scale well to large amount of selected points.
|
|
||
|
|
||
| class AnnotationPayloadQueryBody(BaseModel): | ||
| """Request body for reading annotations with payload without URL-sized filters.""" |
There was a problem hiding this comment.
The changes in this file are only required to make the lasso select scale well to large amount of selected points.
|
/review |
JonasWurst
changed the base branch from
malte-lig-9521-object-embeddings-prototype-embedding-plot-and-text-search
to
main
2 participants
What has changed and why?
In this prototype, the embeddings for objects are extracted on indexing time. for each annotation, the bbox is used to crop the input image. That crop is passed though the normal image embedding model. The resulting object Embeddings are stored in the embedding table.
The frontend changes have been made in an earlier prototpye.
How has it been tested?
Locally run with example_coco.py
and exmaple_evaluation.py
Did you update CHANGELOG.md?