Update README.md

README.md

@@ -95,7 +95,7 @@ The model demonstrated significant improvement during training, as shown in the
 | mAP50     | 0.089 | 0.598 |
 | mAP50-95  | 0.057 | 0.499 |
 
-Initially, the model would enthusiastically label almost anything as a duck - finding many actual ducks but with overwhelming false positives (being correct less than 1% of the time when it claimed to find a duck). The improved model is much more discerning: now, when it says it's found a duck, it's right about half the time. While this training approach reduced overall sensitivity to duck detection, testing in our specific deployment environment showed improved recall, suggesting better alignment with real-world conditions. This increased reliability, combined with better accuracy in placing bounding boxes around actual ducks, makes the final model much more practical for real-world use. Adjustments to hyperparameters provided a wide range of outcomes suggesting significant potential for additional improvement.
+Initially, the model would enthusiastically label almost anything as a duck, while only finding a few actual ducks (being correct less than 1% of the time when it claimed to find a duck). The improved model is much more discerning: now, when it says it's found a duck, it's right about half the time. While this training approach reduced overall sensitivity to duck detection, testing in our specific deployment environment showed improved recall, suggesting better alignment with real-world conditions. This increased reliability, combined with better accuracy in placing bounding boxes around actual ducks, makes the final model much more practical for real-world use. Adjustments to hyperparameters provided a wide range of outcomes suggesting significant potential for additional improvement.
 
 ### Model Statistics
 - Layers: 168