Update README.md

README.md

@@ -116,7 +116,7 @@ Utilizes custom scale, combining default Booru sizes with quite freeform upper r
 
 | Model                       | Target                |Classes        |Dataset size|Training Resolution|
 | --------------------------- | --------------------- |---------------|------------|-------------------|
-  | [Anzhcs Breast Size det cls v8.pt]()| Breasts: illustration and real |15(size range)|~16100        |640|
+  | [Anzhcs Breast Size det cls v8 y11m.pt](https://huggingface.co/Anzhc/Anzhcs_YOLOs/blob/main/Anzhcs%20Breast%20size%20det%20cls%20v8%20640%20y11m.pt)| Breasts: illustration and real |15(size range)|~16100        |640|
 
 mAPs are not displayed in table, because i think we need more complex stats for this model.
 
@@ -140,6 +140,8 @@ Misclassification is quite rare, and im happy with model performance in that reg
 Missing predictions is unfortunately over 10%, but data is highly skewed with classes 0-2, which are hard to detect.  
 FPR for v8 is very reasonable, assuming confused detections(of 2 classes at once) are counted as FPR. Size range is smooth, and lots of cases where both classes could be applied.  
 
+Last class(unmeasurable) is used for classifying outliers that are hard to measure in currently visible area(e.g. mostly out of frame), but model will try to reasonably predict obstructed and partially visible instances.
+
 All ratios are calculated relative to their respective GT instance count.  
 
 I will continue to use this benchmark approach for future detection models.