reports/test_evaluation_report.md

SID-UNet Evaluation Report

Run Configuration & Hyperparameters

Hyperparameter / Setting	Configured Value
Project Name	test_smoke
Dataset	KhangTruong/IMD2020
Splits	Train: 'train'
Streaming	False
Image Size	[32, 32]
Batch Size	16
Epoch Limit / Steps	2 samples/epoch
Model	unet (features=[8, 16], bilinear=True)
Aux Classifier	False (classes=3)
Mask Loss	Combined (BCE: 0.5, Dice: 0.5, Focal: 0.5)
Aux Loss	cross_entropy (wt=0.2)
Post-Processing	Enabled (min_area=64, fill_holes=True, morph=open_close)
Optimizer	adamw (lr=0.001, wd=0.0001)
Scheduler	cosine
Epochs	1
AMP	False

Overall Segmentation & Classification Metrics

Metric	Value
Test Bce Loss	0.6495
Test Dice Loss	0.6683
Test Focal Loss	0.0678
Test Mask Loss	0.6928
Test Total Loss	0.6928
Test Iou	0.2061
Test Dice	0.2918
Test F1	0.2918
Test Pixel F1	0.2918
Test Auroc	0.7468
Test Pixel Auroc	0.7468
Test Pixel Acc	0.6748
Test Precision	0.5
Test Recall	0.2061
Test Specificity	0.9688

Per-Subset Metrics Breakdown

Subset	Mean IoU	Dice / F1	Pixel Accuracy	Sample Count
Label 0 (Real / Black Mask)	0	0	0.9375	1
Label 1 (Synthetic / White Mask)	0.4121	0.5837	0.4121	1
Label 2 (Tampered / Partial Mask)	0	0	0	0