Skip to main content

Table 3 Parameter values

From: Ancient mural classification methods based on a multichannel separable network

Parameter   Values
Category labels_num 8
Batch size batch_size 16
Learning rate base_lr 0.01
Patch max_step 20,000
Save time snapshot 2000
Hidden unit probability keep_pro 0.5
Smoothing parameter ε 8
Train log train_log_step 100
Test log Val_log_step 200
Scaling factor β 0.2