Skip to content

Conversation

@DimaBir
Copy link
Owner

@DimaBir DimaBir commented Oct 9, 2023

Extensive Refactoring and Bug Fixes

Description

In this PR, we have undertaken a comprehensive refactoring of the codebase and fixed a few bugs that were identified during the process.

Main Changes

  • Refactoring: Broke down the main function into multiple sub-functions and moved them into separate modules (e.g., initialization, prediction, benchmark).
  • Bug Fixes: Addressed several issues related to model initialization, prediction, and benchmarking.
  • Code Cleanup: Improved code readability and added comments for better maintainability.
  • Performance: Addressed performance warnings and ensured correct computation of average times in benchmarks.
  • Logging: Enhanced logging capabilities to include device information during model prediction.

Testing

Ensure that all the functionalities are working as expected and benchmarks are accurately reported.

Files Changed

  • Modified: main.py
  • Added: initialization/
  • Added: prediction/
  • Added: benchmark/

DimaBir added 30 commits October 6, 2023 21:03
- Refactored the main function for improved readability and maintainability.
- Extracted benchmarking, prediction, and utility functions into separate modules.
- Created dedicated modules for ONNX, OpenVINO, and CUDA operations to enhance code organization.
- Simplified CUDA configurations and added detailed comments for clarity.
@DimaBir DimaBir merged commit fa10fde into master Oct 9, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants