A Deep Learning Model for Quick and Accurate Rock Recognition with Smartphones

Table 1

ShuffleNet architecture.

Layer	Output size	K size	Stride	Repeat	Output channels ( groups)
					= 1	= 2	= 3	= 4	= 5
Image	224 × 224				3	3	3	3	3
Conv1	112 × 112	3 × 3	2	1	24	24	24	24	24
MaxPool	56 × 56	3 × 3	2	1
Stage	28 × 28		2	1	144	200	240	272	384
	28 × 28		1	3	144	200	240	272	384
Stage 3			2	1	288	400	480	544	768
			1	7	288	400	480	544	768
Stage 4	7 × 7		2	1	576	800	960	1088	1536
	7 × 7		1	3	576	800	960	1088	1536
GlobalPool	1 × 1	7 × 7
FC					1000	1000	1000	1000	1000
Complexity^2					143M	140M	137M	133M	137M