eel4759_classification

Comparison of different ImageNet-based CNN models for classifying diabetic retinopathy images
Log | Files | Refs | README

classification_report.txt (601B)

      1 Experiment: efficientnet_b0_clahe=False
      2 
      3                       precision    recall  f1-score   support
      4 
      5          Healthy (0)       0.85      0.95      0.90      3872
      6        Mild NPDR (1)       0.25      0.06      0.10       366
      7    Moderate NPDR (2)       0.62      0.53      0.57       794
      8      Severe NPDR (3)       0.51      0.40      0.45       131
      9 Proliferative DR (4)       0.62      0.55      0.58       106
     10 
     11             accuracy                           0.80      5269
     12            macro avg       0.57      0.50      0.52      5269
     13         weighted avg       0.76      0.80      0.78      5269