feat(release): final training report and checkpoints for KhangTruong/Testing-model (v1)
1d7c979 verified |
Download reports/test_evaluation_report.md from KhangTruong/Testing-model: direct link, hf CLI and curl.
- Browser
- Download file 2.81 kB
-
https://huggingface.co/KhangTruong/Testing-model/resolve/main/reports/test_evaluation_report.md
- Command line
-
hf download hf://KhangTruong/Testing-model/reports/test_evaluation_report.md
-
curl -L -o test_evaluation_report.md https://huggingface.co/KhangTruong/Testing-model/resolve/main/reports/test_evaluation_report.md
2.81 kB
| # SID-UNet Evaluation Report | |
| ### Run Configuration & Hyperparameters | |
| | Hyperparameter / Setting | Configured Value | | |
| |----------------------------|----------------------------------------------------------| | |
| | Project Name | test_smoke | | |
| | Dataset | KhangTruong/IMD2020 | | |
| | Splits | Train: 'train' | Val: 'validation' | Test: 'test' | | |
| | 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 | | |