Tiny Cats Model — Classifier Demo
Binary cat vs dog classifier (ResNet-18, 1478 images per
split eval, Oxford IIIT Pet), trained with class-balanced loss on the full
dataset. Evaluation report in evaluation_report.json at the
repo or the
model hub repo.
Headline metrics
| Metric | Value |
|---|
| Accuracy | 99.93% (1477/1478) |
| Macro F1 | 99.92% |
| Weighted F1 | 99.93% |
| Misclassifications | 1 |
Per-class precision / recall / F1
| Class | Precision | Recall | F1 |
|---|
| cat | 99.79% | 100.00% | 99.90% |
| not_cat | 100.00% | 99.90% | 99.95% |
Confusion matrix (rows=true, cols=predicted)
| cat | not_cat |
|---|
| cat | 480 | 0 |
|---|
| not_cat | 1 | 997 |
|---|
Report timestamp: 2026-08-12T10:51:31.480493+00:00