Table 3 The effect of different depths on model’s performance.

From: ResNeXt-CC: a novel network based on cross-layer deep-feature fusion for white blood cell classification

s

Accuracy (%)

F1-score (%)

AUROC (%)

Specificity (%)

ResNeXt-5024

85.91

89.14

92.51

74.53

ResNeXt-10124

84.41

88.57

90.65

75.00

  1. Better values are highlighted in bold.
Back to article page