Skip to content

ETCE-LAB/mushr-mask-r-cnn

Repository files navigation

This repository hosts the MushR Mask R CNN model for maturity detection of Oyster mushrooms.

Dependencies

To run inference, please follow the official instructions to install detectron2.

Annotations

  1. Train: MushR_Dataset_V1.1_2023_04_04-COCO.json
  2. Test: MushR_Dataset_2023_06_29_TEST-COCO.json

Training

All training related configuration can be found in train_2023_04_04/.

We used the train.sh script to train the model.

To continue training from the last checkpoint, use: continue_training.sh

NOTE

The model weights of our trained model can be found in https://github.com/ETCE-LAB/mushr-mask-r-cnn/releases

Inference

The scripts, inference_images.sh and inference_images-single.sh can be used to run inference.

Please check inference_2023_04_20 for examples of expected results.

Evaluation

To evaluate the model, please use the eval.sh script.

Our evaluation results of the trained model are given in eval_2023_07_19.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Packages

No packages published