Update app.py

app.py

@@ -9,69 +9,49 @@ import cv2
 model_path = "fahrnphi_exam_project.keras"
 model = tf.keras.models.load_model(model_path)
 
-# Set image dimensions
-img_height, img_width = 150, 150  # Input size for the model
-
-# Define a function for prediction and returning labels and probabilities
-def predict_labels_and_probabilities(image_path):
-    # Load the image using OpenCV
-    img = cv2.imdecode(np.frombuffer(image_path.read(), np.uint8), cv2.IMREAD_COLOR)
-    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+# Define the core prediction function
+def predict_ingredient(image):
+    # Preprocess image
+    image = image.resize((150, 150))  # Resize the image to 150x150
+    image = image.convert('RGB')  # Ensure image has 3 channels
+    image = np.array(image)
+    image = np.expand_dims(image, axis=0)  # Add batch dimension
+    
+    # Predict
+    prediction = model.predict(image)
     
-    # Scan the image in a grid-like fashion
-    step_size = 50  # Step size for the grid
-    predictions = []
+    # Apply softmax to get probabilities for each class
+    probabilities = tf.nn.softmax(prediction, axis=1)
     
-    for y in range(0, img_rgb.shape[0] - img_height + 1, step_size):
-        for x in range(0, img_rgb.shape[1] - img_width + 1, step_size):
-            patch = img_rgb[y:y+img_height, x:x+img_width]
-            patch_resized = cv2.resize(patch, (img_height, img_width))
-            patch_array = image.img_to_array(patch_resized)
-            patch_array = np.expand_dims(patch_array, axis=0)
-            patch_array /= 255.  # Scale pixel values
-            
-            preds = model.predict(patch_array)
-            class_idx = np.argmax(preds[0])
-            
-            # Map class indices to class names
-            class_labels = {
-                0: 'Bell Pepper', 1: 'Carrot', 2: 'Garlic', 3: 'Ginger',
-                4: 'Jalapeno', 5: 'Onion', 6: 'Potato', 7: 'Sweetpotato', 8: 'Tomato'
-            }
-            predicted_class = class_labels[class_idx]
-            probability = preds[0][class_idx]
-            
-            if probability > 0.5:  # Threshold to filter out low confidence predictions
-                predictions.append((predicted_class, probability, x, y, x+img_width, y+img_height))
-                # Draw rectangle around detected ingredients
-                cv2.rectangle(img_rgb, (x, y), (x+img_width, y+img_height), (255, 0, 0), 2)
+    # Map probabilities to ingredient classes
+    class_names = ['Peperoni', 'Carrot', 'Garlic', 'Ginger', 'Jalapeno', 'Onion', 'Potato', 'Sweetpotato', 'Tomato']
+    probabilities_dict = {ingredient_class: round(float(probability), 2) for ingredient_class, probability in zip(class_names, probabilities.numpy()[0])}
     
-    return predictions, img_rgb
+    return probabilities_dict
 
-# Streamlit App
-st.title("Intelligent Recipe Finder Classification")
+# Streamlit interface
+st.title("Ingredient Classifier")
+st.write("A simple MLP classification model for image classification using a pretrained model.")
 
-uploaded_file = st.file_uploader("Choose an ingredients image...", type="jpg")
+# Upload image
+uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "png"])
 
-if uploaded_file is not None:
-    # Display the uploaded image
-    st.image(uploaded_file, caption='Uploaded Ingredient Image.', use_column_width=True)
+if uploaded_image is not None:
+    image = Image.open(uploaded_image)
+    st.image(image, caption='Uploaded Image.', use_column_width=True)
+    st.write("")
+    st.write("Classifying...")
     
-    # Perform the prediction and display the results
-    predictions, img_with_boxes = predict_labels_and_probabilities(uploaded_file)
-    st.write("Predictions for detected ingredients in the image:")
-    
-    for i, (label, probability, x1, y1, x2, y2) in enumerate(predictions):
-        st.write(f"Ingredient {i+1}:")
-        st.write(f"Prediction: {label}")
-        st.write(f"Probability: {probability}")
-        st.write(f"Location: ({x1}, {y1}) to ({x2}, {y2})")
-        
-    # Display the image with rectangles
-    st.image(img_with_boxes, caption='Detected Ingredients', use_column_width=True)
+    predictions = predict_ingredient(image)
 
-    # Debugging information
-    if not predictions:
-        st.write("No ingredients detected with probability above the threshold.")
-    else:
-        st.write(f"Total detected patches: {len(predictions)}")
+    # Display predictions as a DataFrame
+    st.write("### Prediction Probabilities")
+    df = pd.DataFrame(predictions.items(), columns=["ingredient", "Probability"])
+    st.dataframe(df)
+    
+    # Display predictions as a pie chart
+    st.write("### Prediction Chart")
+    fig, ax = plt.subplots()
+    ax.pie(df["Probability"], labels=df["ingredient"], autopct='%1.1f%%', colors=plt.cm.Paired.colors)
+    ax.set_title('Prediction Probabilities')
+    st.pyplot(fig)