Table 8.

Lists of deep learning architectures selected for the test: layers used and total number of features extracted.

	AlexNET	GoogleNET	ResNET101	NasNETLarge
Layer	‘pool5’	‘pool5’	‘pool5’	‘average_pooling’
N. of features	9216	1024	2048	4032
Input Layer size	227 × 227 × 3	224 × 224 × 3	224 × 224 × 3	331 × 331 × 3