The following results showcase the performance of our breed classification model. This model has been fine-tuned to recognize different dog breeds.
On the test dataset, the model achieved an accuracy of 83.53% across all breeds, demonstrating high precision and recall in most cases. The table below provides detailed metrics for each breed, including precision, recall, and F1-score, which indicate the model's effectiveness in identifying each breed correctly.
To view detailed images of each breed, click on the breed name in the table. Each breed's detail page provides a selection of images used during training and testing, illustrating the model's predictions versus the actual labels.
| Breed | PrecisionThe proportion of positive identifications that were actually correct. | RecallThe proportion of actual positives that were correctly identified. | F1-ScoreThe harmonic mean of precision and recall. |
|---|