Individual Fish Recognition Method with Coarse and Fine-Grained Feature Linkage Learning for Precision Aquaculture

Table 1

Comparison of accuracy using different teacher models.

Layer name	Parameters	Output size
Conv1	7 × 7,64, stride 2	32 × 32
Conv2_x	3 × 3, Max pool, stride 2	16 × 16
	Conv3_x			8 × 8
Conv4_x		4 × 4
Conv5_x		2 × 2
Average pool	2 × 2	1 × 1