Update README.md

README.md

@@ -57,14 +57,15 @@ Inference time to evaluate real-time feasibility.
 Using CodeCarbon, the model's carbon footprint and energy consumption will be tracked, this information will help ensure the model's alignment with the sustainability objectives of the Frugal AI Challenge.
 
 ## Results:
-Since this challenge's evaluation is based on 20% of the train dataset, we need to be vigilant when discussing model performance.  
+At the beginning of this challenge's evaluation was based on 20% of the train dataset, we had to be vigilant when discussing model performance.  
 Indeed, a high accuracy in this part of the train dataset could hide the over-fitting of the model.
 
 That is what I've been dealing with when reaching 0.911 accuracy of the model and 0.817 mean_iou on the train dataset: 
 I can see over-fitting while over-performance on the train dataset (see picture below).  
-Due to this challenge evaluation criteria ,this model is used for submission and is called [yolo11_tr_20012025_frugalAIchal.pt](https://huggingface.co/spaces/tom-b974/Frugal_AI_image_2025/blob/main/yolo11_tr_20012025_frugalAIchal.pt)
+Due to this challenge evaluation criteria ,this model was used for submission (before update of the 27-01-2025)
 <img src="https://cdn-uploads.huggingface.co/production/uploads/666354284044e2b1c3287c22/LptPoEeSGH22MG_XftxdP.png" alt="over-fitting" width="600">
 
-As a professional data scientist, I have trained anther model that has been evaluated on the "val" dataset (see picture below)
+As a professional data scientist, I have trained another model that has been evaluated on the "val" dataset (see picture below)
 <img src="https://cdn-uploads.huggingface.co/production/uploads/666354284044e2b1c3287c22/k00JqZDpHxGqKMweZQzw0.png" alt="No over-fitting" width="600">
-Still reaching a model accuracy of 0.907 and max iou of 0.808.
+Still reaching a model accuracy of 0.907 and max iou of 0.808 (before update of the 27-01-2025 - on 20% of'train')
+UPDATE: A model accuracy of 0.799 and max iou of 0.740 (on 'val')