Code for Methods in Ecology and Evolution paper: "A Convolutional Neural Network for Detecting Sea Turtles in Drone Imagery"
Using this code:
Running run.sh in bash will run the full turtle detection workflow.
- Python 2.7 is required and nonstandard python packages necessary are: numpy, scipy, keras, tables, and hdf5storage
- This setup runs on preprocessed imagery contained in the .mat file. Full turtle image data along with labels for independent machine learning development can be found at doi:10.5061/dryad.5h06vv2
- defines utility functions for model creation and matlab ingestion functions
- run prediction on processed images
- Trained model weights file
- Model definition file
- processed and tiled RGB image data that is fed into the model. Training / validation split is 85% train / 15% validation