Downloads · 30 days
0
nakasiga/tbx11k-object-detection-centernet
tbx11k-object-detection-centernet is a object detection model from nakasiga. Use it when you need objects located in an image. The card lists the license as mit.
Trained on 11701 validated records with a WeightedRandomSampler (sqrt strategy) to handle severe class imbalance.
Downloads · 30 days
0
Access
Public
Updated Jul 16, 2026
Repo size
262 MB
Likes
0
Public
Click a slice to open those files.
.pt262 MB · 100%
From the Hugging Face model README
Trained on 11701 validated records with a WeightedRandomSampler (sqrt strategy) to handle severe class imbalance.
Through inference-time hyperparameter sweep optimization, this frozen network can be deployed at two distinct clinical operating configurations without any retraining:
| Class | [email protected] (Balanced Mode, thresh=0.15) | True Sensitivity (Triage Mode, thresh=0.05) |
|---|---|---|
| healthy | 0.0450 | N/A (Background Suppression) |
| sick_non_tb | 0.1980 | 95.20% |
| active_tb | 0.0000 | 97.41% |
| latent_tb | 0.0000 | 88.50% |
| Metric | Score |
|---|---|
| [email protected] | 0.1310 |
| [email protected]:0.95 | 0.0928 |
| [email protected] | 0.0546 |
0: healthy | 1: sick_non_tb | 2: active_tb | 3: latent_tb