Multi-Input Convolutional Neural Network for Flower Grading

Table 3

Architecture of single-input models.

Name of models	Convolutional layers
	C1	C2	C3	C4	C5	FC1	FC2	ACC
M24	3 × 3,32	3 × 3,32				32	3
M25	3 × 3,32	3 × 3,32	3 × 3,32	—	—	32	3
M26	3 × 3,32	3 × 3,32	3 × 3,32	3 × 3,64	—	32	3
M27	3 × 3,16	3 × 3,32	3 × 3,32	3 × 3,64	3 × 3,64	32	3	75.5% ± 0.3

C1–C3 represent the layers in three branches before merging. Pooling layers are ignored in this table. Generally, every convolutional layer is followed by a pooling layer. All the sizes and strides of pooling layers are set to 2 × 2.