Table 2 Hyperparameter tuning.

From: A dual-track feature fusion model utilizing Group Shuffle Residual DeformNet and swin transformer for the classification of grape leaf diseases

Parameter

Search space

Optimal value

Weight decay

[0,1e–2, 1e–3, 1e–4, 2e–4, 5e–4]

2e–4

Learning rate

[1e–2, 1e–3, 2e–3, 1e–4]

1e–2

Dropout

[3e–1,4e–1,5e–1]

3e–1

Optimizer

SGD, ADAM

ADAM

Back to article page