Computer vision initial services#389
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. 🚀 New features to boost your workflow:
|
| } | ||
|
|
||
| message ImageInput { | ||
| bytes image = 1; |
There was a problem hiding this comment.
nit: having 3 different ImageInput feels like a code smell. How would you feel about either/any combination of:
- just throwing the images directly in
ImageClassificationRequestand doing something likerepeated bytes inputs = 1;. This would give us parity withrepeated string inputs = 1;in text services - Putting it in a separate proto or reusing it
- Condensing all of the protos into one file (would this be so horrible... this may make it easier if anyone is working with Kafka)
There was a problem hiding this comment.
I'm now taking image classification as "gold standard" while I work at the impl, and I'll probably retrofit the other two categories from there. So I'll take these comments into consideration when I revisit the proto defs for them 👍
There was a problem hiding this comment.
(It just felt easier to transcribe the hf pipelines in separate files at the start)
There was a problem hiding this comment.
(separate proto + imports ftw, imho)
| } | ||
|
|
||
| message ObjectDetectionResponse { | ||
| repeated ImageBoundingBoxes boxes_batch = 1; |
There was a problem hiding this comment.
nit: would prefer this just be named boxes, but not a hill I need to die on
There was a problem hiding this comment.
The thing is that for each image, we have boxes, but then for a bunch of input images we have groups of boxes.... so I ran out of imagination :-/ Any suggestions here?
There was a problem hiding this comment.
renamed to "box" and "boxes", although the grammatical number agreement gets a bit weird :-/
3 participants
Preliminary implementation for computer vision tasks (object detection, image segmentation and image classification).