Update README.md

README.md

@@ -1,3 +1,17 @@
+readme_text = f"""
+---
+language: en
+library_name: pytorch
+tags:
+- image-classification
+- efficientnet
+- fruits
+- vegetables
+datasets:
+- kritikseth/fruit-and-vegetable-image-recognition
+license: mit
+pipeline_tag: image-classification
+---
 
 # EfficientNet-B0 Fruit & Vegetable Classifier 🍎🥕🌽
 
@@ -7,17 +21,17 @@ It is trained on the [Fruit and Vegetable Image Recognition dataset](https://www
 ---
 
 ## 📊 Dataset Statistics
-- Training Images: 3115
-- Validation Images: 351
-- Test Images: 359
-- Classes: 36 → ['apple', 'banana', 'beetroot', 'bell pepper', 'cabbage', 'capsicum', 'carrot', 'cauliflower', 'chilli pepper', 'corn', 'cucumber', 'eggplant', 'garlic', 'ginger', 'grapes', 'jalepeno', 'kiwi', 'lemon', 'lettuce', 'mango', 'onion', 'orange', 'paprika', 'pear', 'peas', 'pineapple', 'pomegranate', 'potato', 'raddish', 'soy beans', 'spinach', 'sweetcorn', 'sweetpotato', 'tomato', 'turnip', 'watermelon']
+- Training Images: {len(train_dataset)}
+- Validation Images: {len(val_dataset)}
+- Test Images: {len(test_dataset)}
+- Classes: {len(class_names)} → {class_names}
 
 ---
 
 ## 🏆 Results
-- Final Training Accuracy: 72.50%
-- Final Validation Accuracy: 87.75%
-- Final Test Accuracy: 87.47%
+- Final Training Accuracy: {train_acc:.2f}%
+- Final Validation Accuracy: {val_acc:.2f}%
+- Final Test Accuracy: {test_acc:.2f}%
 
 ---
 
@@ -31,7 +45,7 @@ model = models.efficientnet_b0(pretrained=False)
 num_features = model.classifier[1].in_features
 model.classifier = torch.nn.Sequential(
     torch.nn.Dropout(0.3),
-    torch.nn.Linear(num_features, 36)
+    torch.nn.Linear(num_features, {len(class_names)})
 )
 
 # Load weights