Combine detection button into sidebar.

app.py

@@ -80,7 +80,7 @@ def draw_bbox(image, bbox):
 
 model = load_model()
 
-uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+# uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
 
 if uploaded_file is not None:
     file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
@@ -88,33 +88,33 @@ if uploaded_file is not None:
 
     st.image(image, caption='Uploaded Image.', use_column_width=True)
 
-    if st.button('Detect'):
-        st.write("Processing...")
-        input_image = preprocess_image(image)
-        pred_bbox, pred_label, pred_label_confidence = predict(model, input_image)
-
-        # Updated label mapping based on the dataset
-        label_mapping = {
-            0: 'Atelectasis',
-            1: 'Cardiomegaly',
-            2: 'Effusion',
-            3: 'Infiltrate',
-            4: 'Mass',
-            5: 'Nodule',
-            6: 'Pneumonia',
-            7: 'Pneumothorax'
-        }
-
-        if pred_label_confidence < 0.2:
-            st.write("May not detect a disease.")
-        else:
-            pred_label_name = label_mapping[pred_label]
-            st.write(f"Prediction Label: {pred_label_name}")
-            st.write(f"Prediction Bounding Box: {pred_bbox}")
-            st.write(f"Prediction Confidence: {pred_label_confidence:.2f}")
-
-            output_image = draw_bbox(image.copy(), pred_bbox)
-            st.image(output_image, caption='Detected Image.', use_column_width=True)
+    # if st.button('Detect'):
+        # st.write("Processing...")
+        # input_image = preprocess_image(image)
+        # pred_bbox, pred_label, pred_label_confidence = predict(model, input_image)
+
+        # # Updated label mapping based on the dataset
+        # label_mapping = {
+        #     0: 'Atelectasis',
+        #     1: 'Cardiomegaly',
+        #     2: 'Effusion',
+        #     3: 'Infiltrate',
+        #     4: 'Mass',
+        #     5: 'Nodule',
+        #     6: 'Pneumonia',
+        #     7: 'Pneumothorax'
+        # }
+
+        # if pred_label_confidence < 0.2:
+        #     st.write("May not detect a disease.")
+        # else:
+        #     pred_label_name = label_mapping[pred_label]
+        #     st.write(f"Prediction Label: {pred_label_name}")
+        #     st.write(f"Prediction Bounding Box: {pred_bbox}")
+        #     st.write(f"Prediction Confidence: {pred_label_confidence:.2f}")
+
+        #     output_image = draw_bbox(image.copy(), pred_bbox)
+        #     st.image(output_image, caption='Detected Image.', use_column_width=True)
     
 
 # Utility Functions
@@ -469,31 +469,32 @@ if uploaded_file is not None:
 
     with col2:
         if st.button('Auto Detect'):
-            name = uploaded_file.name.split("/")[-1].split(".")[0]
-            true_bbox_row = df[df['Image Index'] == uploaded_file.name]
-
-            if not true_bbox_row.empty:
-                x1, y1 = int(true_bbox_row['Bbox [x']), int(true_bbox_row['y'])
-                x2, y2 = int(true_bbox_row['x_max']), int(true_bbox_row['y_max'])
-                true_bbox = [x1, y1, x2, y2]
-                label = true_bbox_row['Finding Label'].values[0]
-
-                pred_bbox = predict(image)
-                iou = cal_iou(true_bbox, pred_bbox)
-
-                image = cv2.rectangle(image, (x1, y1), (x2, y2), (255, 0, 0), 5)  # BLUE
-                image = cv2.rectangle(image, (pred_bbox[0], pred_bbox[1]), (pred_bbox[2], pred_bbox[3]), (0, 0, 255), 5)  # RED
-
-                x_pos = int(image.shape[1] * 0.05)
-                y_pos = int(image.shape[0] * 0.05)
-                font_size = 0.7
-
-                cv2.putText(image, f"IoU: {iou:.4f}", (x_pos, y_pos), cv2.FONT_HERSHEY_SIMPLEX, font_size, (255, 0, 0), 2)
-                cv2.putText(image, f"Label: {label}", (x_pos, y_pos + 30), cv2.FONT_HERSHEY_SIMPLEX, font_size, (255, 255, 255), 2)
-
-                st.image(image, channels="BGR")
+            st.write("Processing...")
+            input_image = preprocess_image(image)
+            pred_bbox, pred_label, pred_label_confidence = predict(model, input_image)
+    
+            # Updated label mapping based on the dataset
+            label_mapping = {
+                0: 'Atelectasis',
+                1: 'Cardiomegaly',
+                2: 'Effusion',
+                3: 'Infiltrate',
+                4: 'Mass',
+                5: 'Nodule',
+                6: 'Pneumonia',
+                7: 'Pneumothorax'
+            }
+    
+            if pred_label_confidence < 0.2:
+                st.write("May not detect a disease.")
             else:
-                st.write("No bounding box and label found for this image.")
+                pred_label_name = label_mapping[pred_label]
+                st.write(f"Prediction Label: {pred_label_name}")
+                st.write(f"Prediction Bounding Box: {pred_bbox}")
+                st.write(f"Prediction Confidence: {pred_label_confidence:.2f}")
+    
+                output_image = draw_bbox(image.copy(), pred_bbox)
+                st.image(output_image, caption='Detected Image.', use_column_width=True)
     
     with col3:
         if st.button('Generate Grad-CAM'):