Development of Paddy Rice Seed Classification Process using Machine Learning Techniques for Automatic Grading Machine

Table 2

Deep learning experimental results with the top layer set at 1024 nodes and input image size set at pixel.

Model	Number of bottom layer frozen	Acc200 (%)	Accl (%)	Test time per image (ms)	Model training time (hour)
InceptionResNetV2	0	94.74	95.14	17.00	89 : 03
Xception	0	94.3	93.82	13.92	80 : 36
Xception	108	90.34	90.38	13.92	53 : 15
InceptionV3	249	84.24	85.32	7.64	32 : 44
VGG16	15	88.62	89.45	11.95	33 : 38
VGG19	15	88.74	90.94	13.73	34 : 12