demo ready

app.py

@@ -70,8 +70,6 @@ def create_XML(full_pred, text_mapping, scale):
         'event': (43.2, 43.2),
         'parallelGateway': (60, 60),
         'sequenceFlow': (180, 12),
-        'pool': (300, 120),
-        'lane': (240, 120),
         'dataObject': (48, 72),
         'dataStore': (72, 72),
         'subProcess': (144, 108),
@@ -80,8 +78,6 @@ def create_XML(full_pred, text_mapping, scale):
     }
 
 
-
-
     definitions = ET.Element('bpmn:definitions', {
         'xmlns:xsi': namespaces['xsi'],
         'xmlns:bpmn': namespaces['bpmn'],
@@ -92,6 +88,9 @@ def create_XML(full_pred, text_mapping, scale):
         'id': "simpleExample"
     })
 
+    #modify the boxes positions
+    full_pred = modif_box_pos(full_pred, size_elements)
+
     # Create BPMN collaboration element
     collaboration = ET.SubElement(definitions, 'bpmn:collaboration', id='collaboration_1')
 
@@ -286,6 +285,8 @@ def main():
     st.sidebar.text("6. You can now see the annotation \n   and the BPMN XML result")
     st.sidebar.text("7. You can modify and download \n   the result in right format")
 
+    st.sidebar.text("If there is an error, try to:\n change the score threshold \n recrop the image.")
+
     st.sidebar.subheader("You can close this sidebar")
 
     # Set the title of the app
@@ -334,13 +335,12 @@ def main():
                 st.session_state.scale = st.slider("Set scale for XML file", min_value=0.1, max_value=2.0, value=1.0, step=0.1)
 
             # Launch the prediction when the user clicks the button    
-            #if st.button("Launch Prediction"):
-            st.session_state.crop_image = cropped_image
-            with st.spinner('Processing...'):
-                perform_inference(model_object, model_arrow, st.session_state.crop_image, score_threshold)
-                st.session_state.prediction = modif_box_pos(st.session_state.prediction, object_dict)                    
-                st.success('Detection completed!')
-                print('Detection completed!')
+            if st.button("Launch Prediction"):
+                st.session_state.crop_image = cropped_image
+                with st.spinner('Processing...'):
+                    perform_inference(model_object, model_arrow, st.session_state.crop_image, score_threshold)
+                    st.session_state.prediction = modif_box_pos(st.session_state.prediction, object_dict)                    
+                    st.balloons()
 
 
     # If the prediction has been made and the user has uploaded an image, display the options for the user to annotate the image