Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,9 @@ The classifier uses DenseNet161 as the encoder and some linear layers at classif
|
|
| 6 |
|
| 7 |
# Model accuracy:
|
| 8 |
Model achieves 91.3% accuracy on the validation set.
|
| 9 |
-
|
|
|
|
|
|
|
| 10 |
|
| 11 |
|
| 12 |
# Training dataset metadata:
|
|
|
|
| 6 |
|
| 7 |
# Model accuracy:
|
| 8 |
Model achieves 91.3% accuracy on the validation set.
|
| 9 |
+
F1-score per class: {'digital': 0.9873773235685747, 'hard': 0.9338602782753218, 'soft': 0.8444277483052108}
|
| 10 |
+
Mean F1-score: 0.9218884500497024
|
| 11 |
+
Accuracy: 0.913
|
| 12 |
|
| 13 |
|
| 14 |
# Training dataset metadata:
|