Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,6 +1,31 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
Please build a conda environment using the attached wildobs_QLD_WetTropics_env.yml file before running the evaluation script present in the Python notebook Evaluate_WetTropics_hf.ipynb.
|
| 6 |
|
|
|
|
| 1 |
+
The official location of the model files is this Hugging Face repo.
|
| 2 |
+
|
| 3 |
+
Developers
|
| 4 |
+
|
| 5 |
+
Prakash Palanivelu Rajmohan and Renuka Sharma
|
| 6 |
+
|
| 7 |
+
Description
|
| 8 |
+
|
| 9 |
+
The wildobs_QLD_WetTropics model for Australian Wet Tropics has been trained on ~30k labelled images from 15 classes. We used the Wildlife Observatory of Australia’s tagged image repository for the ‘Wet Tropics’ rainforests (n = 454 camera deployments, 2,184,664 images, 121 species), and refined this to a balanced dataset of the 15 most common species for CV training and testing. We found that fine-tuning SpeciesNet (https://github.com/google/cameratrapai) delivered the highest performance, often exceeding 95% F1-score. We are in the process of publishing our findings as part of this work.
|
| 10 |
+
|
| 11 |
+
Classes
|
| 12 |
+
|
| 13 |
+
Alectura lathami or Australian brush-turkey
|
| 14 |
+
Bos taurus or domestic cattle
|
| 15 |
+
Canis familiaris or domestic dog
|
| 16 |
+
Casuarius casuarius or southern cassowary
|
| 17 |
+
Felis catus or domestic cat
|
| 18 |
+
Heteromyias cinereifrons or grey-headed robin
|
| 19 |
+
Homo sapiens or human
|
| 20 |
+
Hypsiprymnodon moschatus or musky rat kangaroo
|
| 21 |
+
Megapodius reinwardt or orange-footed scrubfowl
|
| 22 |
+
Orthonyx spaldingii or northern chowchilla
|
| 23 |
+
Perameles nasuta or long-nosed bandicoot
|
| 24 |
+
Sus scrofa or wild boar
|
| 25 |
+
Thylogale stigmatica or red-legged pademelon
|
| 26 |
+
Uromys caudimaculatus or giant uromys
|
| 27 |
+
Wallabia bicolor or swamp wallaby
|
| 28 |
+
|
| 29 |
|
| 30 |
Please build a conda environment using the attached wildobs_QLD_WetTropics_env.yml file before running the evaluation script present in the Python notebook Evaluate_WetTropics_hf.ipynb.
|
| 31 |
|