Update app.py

app.py

@@ -117,31 +117,35 @@ with col2:
         st.image(canvas_result.image_data, use_column_width=True)
 
 # === Image preprocessing and prediction ===
-# Initialize session state for draw count
+# === Sidebar reset ===
+if st.sidebar.button("🔄 Reset"):
+    st.session_state.draw_count = 0
+    st.session_state.last_image = None
+    st.experimental_rerun()
+
+# === Initialize draw counter ===
 if "draw_count" not in st.session_state:
     st.session_state.draw_count = 0
     st.session_state.last_image = None
 
-# === Image preprocessing and prediction ===
+# === Preprocess and predict ===
 if canvas_result.image_data is not None:
     current_image = canvas_result.image_data
 
-    # Compare current image with previous
+    # Check if drawing has changed
     if st.session_state.last_image is None or not np.array_equal(current_image, st.session_state.last_image):
         st.session_state.draw_count += 1
         st.session_state.last_image = current_image
 
     st.markdown(f"### ✏️ Draw Count: {st.session_state.draw_count}")
-
     st.subheader("Preprocessed Image & Prediction")
 
-    # Preprocess image
+    # Convert and preprocess
     img = cv2.cvtColor(current_image.astype("uint8"), cv2.COLOR_RGBA2GRAY)
     img = 255 - img  # Invert colors
 
-    # === Model Selection Based on Draw Count ===
     if st.session_state.draw_count == 1:
-        # Assume single-digit drawing
+        # Single digit
         img_resized = cv2.resize(img, (28, 28))
         img_normalized = img_resized / 255.0
         final_img = img_normalized.reshape(1, 28, 28, 1)
@@ -149,7 +153,7 @@ if canvas_result.image_data is not None:
         preds = model_to_use.predict(final_img)
         predicted_str = str(np.argmax(preds))
     else:
-        # Assume multi-digit drawing
+        # Multi digit
         img_resized = cv2.resize(img, (100, 28))
         img_normalized = img_resized / 255.0
         final_img = img_normalized.reshape(1, 28, 100, 1)
@@ -158,5 +162,5 @@ if canvas_result.image_data is not None:
         predicted_digits = [np.argmax(p[0]) for p in preds]
         predicted_str = ''.join([str(d) for d in predicted_digits])
 
-    # Show result
+    # Output
     st.markdown(f"### 🧠 Predicted Number: **{predicted_str}**")