Transfer and Deep Learning-Based Gurmukhi Handwritten Word Classification Model

Table 3

Training parameters of the proposed model.

Adam Optimizer’s specification	Learning rate (LR)	Loss function	Matrix	Number of epochs	Batch size (BS)
Learning rate = 1E − 03, beta1 = 0.9, beta2 = 0.999, epsilon = 1e − 07, and decay = learning rate/epochs	0.0001	Categorical cross entropy	Accuracy	100	20