Update app.py

app.py

@@ -126,18 +126,16 @@ if canvas_result.image_data is not None:
     img = 255 - img  # Invert colors
     
     # Resize image to match the expected model input shape
-    img_resized = cv2.resize(img, (100, 28))  # Resize to match multi-digit model input shape
+    img_resized = cv2.resize(img, (28, 28))  # Resize to 28x28 for single digit model
     img_normalized = img_resized / 255.0
-    final_img = img_normalized.reshape(1, 28, 100, 1)  # Adjust to model input shape
-
-    # === Choose which model to use based on the image size ===
-    # If image is more likely to be a single digit (e.g., smaller width), use the single digit model
-    if img_resized.shape[1] < 50:  # This is an arbitrary threshold for width
+    final_img = img_normalized.reshape(1, 28, 28, 1)  # Adjust to model input shape
+    
+    # Choose the model based on image characteristics (height/width ratio, etc.)
+    if img_resized.shape[1] < 50:  # If the image is narrow, assume it's a single digit
         model_to_use = single_digit_model
-        final_img = final_img.reshape(1, 28, 28, 1)  # For single digit, reshape accordingly
     else:
         model_to_use = multi_digit_model
-
+    
     # Predict using the selected model
     preds = model_to_use.predict(final_img)
     
@@ -151,4 +149,3 @@ if canvas_result.image_data is not None:
 
     # Show prediction result
     st.markdown(f"### 🧠 Predicted Number: **{predicted_str}**")
-