marieai / marie-ai

Integrate AI-powered Document Analysis Pipelines
MIT License
60 stars 5 forks source link

You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset #90

Open gregbugaj opened 11 months ago

gregbugaj commented 11 months ago

Describe the bug When running ClassificationPipeline we get the following warning.

You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset

Describe how you solve it

Classifications should be batched.