Research Article
Recognition of Gurmukhi Handwritten City Names Using Deep Learning and Cloud Computing
Table 4
Results obtained with a LR of 0.1 by employing Adam optimizer.
| Epoch | Training loss | Validation loss | Validation accuracy (%) | Validation precision | Validation recall |
| 1 | 1.12 | 0.17 | 93.5 | 0.94 | 0.92 | 2 | 0.32 | 0.05 | 98.3 | 0.98 | 0.98 | 3 | 0.21 | 0.01 | 98.5 | 0.99 | 0.99 | 4 | 0.18 | 0.11 | 99 | 0.99 | 0.99 | 5 | 0.10 | 0.02 | 99.5 | 0.99 | 0.99 | 6 | 0.14 | 0.00 | 99.6 | 0.99 | 0.99 | 7 | 0.11 | 0.01 | 99.5 | 0.99 | 0.99 | 8 | 0.11 | 0.02 | 99.1 | 0.99 | 0.98 | 9 | 0.09 | 0.02 | 99.4 | 0.99 | 0.98 | 10 | 0.10 | 0.00 | 99.3 | 0.99 | 0.99 |
|
|