Image Recognition for Garbage Classification Based on Transfer Learning and Model Fusion

Table 1

Transfer learning experiment parameter settings.

Training methods	Training parameters
	Training from scratch	Fine-tuning training
Learning rate	0.001	0.0001
Optimizers	Adam	Adam
Number of iterations	30	30
Lot size	32	32
Datasets	Raw dataset	Raw dataset
Number of training levels	All layers	All layers
Loss function	Cross-entropy function	Cross-entropy function