Upload README.md with huggingface_hub

README.md

@@ -1,5 +1,5 @@
 ---
-language: sr
+language: eng
 license: apache-2.0
 tags:
 - image-classification
@@ -19,10 +19,10 @@ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https:
 ## Model Description
 
 This Vision Transformer (ViT) model has been fine-tuned to classify house images into four condition categories:
-- **dobre** (good condition)
-- **nepoznato** (unknown condition)
-- **oronule** (dilapidated condition)
-- **srednje** (medium condition)
+- **good**
+- **unknown**
+- **ruined**
+- **medium**
 
 ## Training Details
 
@@ -47,17 +47,17 @@ This Vision Transformer (ViT) model has been fine-tuned to classify house images
 ### Per-Class Metrics (Validation)
 | Class      | Precision | Recall | F1-Score | Support |
 |------------|-----------|--------|----------|----------|
-| dobre      | 0.83      | 0.50   | 0.62     | 10       |
-| nepoznato  | 1.00      | 0.83   | 0.91     | 24       |
-| oronule    | 0.71      | 0.80   | 0.75     | 15       |
-| srednje    | 0.73      | 0.87   | 0.79     | 31       |
+| good      | 0.83      | 0.50   | 0.62     | 10       |
+| unknown  | 1.00      | 0.83   | 0.91     | 24       |
+| ruined    | 0.71      | 0.80   | 0.75     | 15       |
+| medium    | 0.73      | 0.87   | 0.79     | 31       |
 
 ### Confusion Matrix (Validation)
 ```
-[[ 5  0  0  5]    # dobre
- [ 1 20  1  2]    # nepoznato
- [ 0  0 12  3]    # oronule
- [ 0  0  4 27]]   # srednje
+[[ 5  0  0  5]    # good
+ [ 1 20  1  2]    # unknown
+ [ 0  0 12  3]    # ruined
+ [ 0  0  4 27]]   # medium
 ```
 
 ## Usage
@@ -94,7 +94,7 @@ for idx, prob in enumerate(probs):
 ## Limitations and Bias
 
 - The model was trained on a specific dataset of house images and may not generalize well to different architectural styles or regions
-- Performance varies by class, with lower recall for the "dobre" (good condition) class
+- Performance varies by class, with lower recall for the "good" (good condition) class
 - The model may have difficulty distinguishing between similar condition categories
 - Training set is relatively small (757 images)