Update README.md
Browse files
README.md
CHANGED
|
@@ -10,3 +10,20 @@ CNN Model for binary classification trained on the cats_vs_dogs dataset from ten
|
|
| 10 |
The model was trained for 21h53m on a GCE VM instance (n1-standard-4, 1 x NVIDIA T4) and achieved an accuracy of 74.83% on the test split (10% of the dataset).
|
| 11 |
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
The model was trained for 21h53m on a GCE VM instance (n1-standard-4, 1 x NVIDIA T4) and achieved an accuracy of 74.83% on the test split (10% of the dataset).
|
| 11 |
|
| 12 |
|
| 13 |
+
The model trained for 90 epochs. Last few epochs' metrics:
|
| 14 |
+
|
| 15 |
+
```
|
| 16 |
+
After 28122 steps, test loss: 0.5549, test accuracy: 0.7418
|
| 17 |
+
After 28449 steps, test loss: 0.5515, test accuracy: 0.7491
|
| 18 |
+
After 28776 steps, test loss: 0.5508, test accuracy: 0.7487
|
| 19 |
+
After 29103 steps, test loss: 0.5503, test accuracy: 0.7478
|
| 20 |
+
After 29430 steps, test loss: 0.5510, test accuracy: 0.7483
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
| Image | Prediction |
|
| 24 |
+
| ----- | ---------- |
|
| 25 |
+
|  | Model Prediction - Cat (65.70%), Dog (34.30%) |
|
| 26 |
+
|  | Model Prediction - Cat (68.18%), Dog (31.82%) |
|
| 27 |
+
|  | Model Prediction - Cat (72.47%), Dog (27.53%) |
|
| 28 |
+
|  | Model Prediction - Cat (50.73%), Dog (49.27%) |
|
| 29 |
+
|  | Model Prediction - Cat (53.57%), Dog (46.43%) |
|