Skip to main content

Table 9 Results achieved by the Resnet50-SSD model by using 512 × 512 × 3 image size in detecting different blood cells in microscopic smear images when the hyperparameters combination given by the Matlab example was used in three independent experimental runs

From: Automatic identifying and counting blood cells in smear images by using single shot detector and Taguchi method

Model

Dataset

mAP-Experiment no

Average mAP

SD

η value

mAP-1

mAP-2

mAP-3

Resnet50-SSD

Training set

0.7374

0.7408

0.7326

0.7369

0.0041

11.5987

Test set

0.7383

0.757

0.7471

0.7475

0.0094

11.9536

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us