Skip to content

Latest commit

 

History

History
15 lines (11 loc) · 337 Bytes

Readme.md

File metadata and controls

15 lines (11 loc) · 337 Bytes

Onnxruntime based Inference Optimization of Roberta text classification model.

Analysed Inference optimization based on

  • Graph optimization
  • Quatnization
  • CPU archtecture AVX2,AVX512

Metrics : Conclusion based on

  • Classification Accuracy
  • Performance in milliseconds(ms)

Dataset : Huggingface model :