Open Bug 1912596 Opened 2 years ago Updated 2 years ago

Image-to-Text Model Duplicates Inputs, Causing Inefficiency

Categories

(Core :: Machine Learning: General, defect)

Product:
Core
Component:
Machine Learning: General
Version:
Firefox 131
Type:
defect

Tracking

()

Tracking Flags:
Tracking Status
firefox131 --- affected

People

(Reporter: atossou, Unassigned, NeedInfo)

Details

Upon examining the intermediate output of the image-to-text model, it is evident that at each step, we receive a batch of two identical texts. This indicates that the model is processing duplicate batch inputs. To enhance efficiency, this issue must be resolved.

The severity field is not set for this bug.
:tarek, could you have a look please?

For more information, please visit BugBot documentation.

Flags: needinfo?(tziade)
You need to log in before you can comment on or make changes to this bug.