Skip to content

Faster R-CNN R-101-FPN model was implemented with TensorFlow2.0 eager execution.

License

Notifications You must be signed in to change notification settings

Viredery/tf-eager-fasterrcnn

Repository files navigation

tf-eager-fasterrcnn

Faster R-CNN R-101-FPN model was implemented with TensorFlow2.0 Eager Execution.

Requirements

  • Cuda 10.0
  • Python 3.5
  • TensorFlow 2.0.0
  • cv2

Usage

see train_model.ipynb, inspect_model.ipynb and eval_model.ipynb

Download trained Faster R-CNN

Updating

  • online hard examples mining
  • soft-nms
  • TTA (multi-scale testing, flip and box voting)
  • multi-scale training

Acknowledgement

This work builds on many excellent works, which include:

About

Faster R-CNN R-101-FPN model was implemented with TensorFlow2.0 eager execution.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published