Recognition of Gurmukhi Handwritten City Names Using Deep Learning and Cloud Computing

Table 3

Results obtained with a LR of 0.01 by employing Adam optimizer.

Epoch	Training loss	Validation loss	Validation accuracy (%)	Validation precision	Validation recall
1	0.58	0.12	95	0.95	0.95
2	0.28	0.74	90	0.90	0.89
3	0.18	0.19	97	0.97	0.97
4	0.15	0.04	98	0.98	0.98
5	0.12	0.25	94	0.95	0.94
6	0.14	0.38	97	0.96	0.96
7	0.10	0.49	99	0.99	0.99
8	0.14	0.32	98	0.98	0.98
9	0.10	0.24	99	0.99	0.99
10	0.11	0.01	99	0.99	0.99