Code and guidance (written by Sicily Fiennes, with the assistance of Sam Watts) to identify traded animals in highly occluded contexts, based on images.

1. Using the merge function in Python to set up a match-mismatch survey
2. Testing for differences between match/mismatch questions and plotting phylogenies using ggfree

3. Glossary of machine learning terms
4. Hardware requirements: setting up Python and downloading TensorFlow
5. Running code on University High Performance Computers
6. Object Detection using the MegaDetector to localise and extract bird crops
7. Data pre-processing: image augmentation as a method of class balancing
8. Training convolutional networks: training the models for species identification
9. Ensembling models
10. Evaluating model performance using cross validation

11. Building a binary model
12. Superimposing uncaged images with caged masks in the foreground

Our work flow for the classification of 37 bird species

• Machine Learning Mastery - Dr. Jason Brownlee
• Deep Lizard

The website for this work can be found @ https://sicily-f.github.io/cagedbirdID/, which has more rationale for the project. For more information about our methods, processes of deduction and tool selection please contact [email protected]. If you have a question related to the material presented here, please create a New Issue under the ‘Issues’ tab above. If you can specify the name of the notebook which your question is related to, that would also be great.