eel4759_classification

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

classification_report.txt (600B)

      1 Experiment: efficientnet_b0_clahe=True
      2 
      3                       precision    recall  f1-score   support
      4 
      5          Healthy (0)       0.86      0.91      0.88      3872
      6        Mild NPDR (1)       0.17      0.08      0.11       366
      7    Moderate NPDR (2)       0.55      0.53      0.54       794
      8      Severe NPDR (3)       0.40      0.52      0.45       131
      9 Proliferative DR (4)       0.62      0.58      0.60       106
     10 
     11             accuracy                           0.78      5269
     12            macro avg       0.52      0.52      0.51      5269
     13         weighted avg       0.75      0.78      0.76      5269