delete some print

.gitignore

@@ -13,3 +13,7 @@ VISION_KEY.json
 backup/
 
 temp.jpg
+
+Evaluation.ipynb
+
+study/

app.py

@@ -222,7 +222,7 @@ def display_options(image, score_threshold):
     annotated_image = draw_stream(
         np.array(image), prediction=st.session_state.prediction, text_predictions=st.session_state.text_pred,
         draw_keypoints=draw_keypoints, draw_boxes=draw_boxes, draw_links=draw_links, draw_twins=False, draw_grouped_text=draw_text,
-        write_class=write_class, write_text=write_text, keypoints_correction=True, write_idx=write_idx, only_print=selected_option,
+        write_class=write_class, write_text=write_text, keypoints_correction=True, write_idx=write_idx, only_show=selected_option,
         score_threshold=score_threshold, write_score=write_score, resize=True, return_image=True, axis=True
     )
 
@@ -254,7 +254,7 @@ def perform_inference(model_object, model_arrow, image, score_threshold):
     ocr_results = text_prediction(uploaded_image)
 
     # Filter and map OCR results to prediction results
-    st.session_state.text_pred = filter_text(ocr_results, threshold=0.5)
+    st.session_state.text_pred = filter_text(ocr_results, threshold=0.6)
     st.session_state.text_mapping = mapping_text(st.session_state.prediction, st.session_state.text_pred, print_sentences=False, percentage_thresh=0.5)
                 
     # Remove the original image display
@@ -300,7 +300,7 @@ def main():
     st.sidebar.subheader("Instructions:")
     st.sidebar.text("1. Upload you image")
     st.sidebar.text("2. Crop the image \n  (try to put the BPMN diagram \n   in the center of the image)")
-    st.sidebar.text("3. Set the score threshold \n   for prediction (default is 0.5)")
+    st.sidebar.text("3. Set the score threshold \n   for prediction (default is 0.6)")
     st.sidebar.text("4. Click on 'Launch Prediction'")
     st.sidebar.text("5. You can now see the annotation \n   and the BPMN XML result")
     st.sidebar.text("6. You can change the scale for \n   the XML file (default is 1.0)")
@@ -371,7 +371,7 @@ def main():
         if cropped_image is not None:
             col1, col2, col3 = st.columns(3)
             with col1:
-                score_threshold = st.slider("Set score threshold for prediction", min_value=0.0, max_value=1.0, value=0.5, step=0.05)
+                score_threshold = st.slider("Set score threshold for prediction", min_value=0.0, max_value=1.0, value=0.6, step=0.05)
             
             if st.button("Launch Prediction"):
                 st.session_state.crop_image = cropped_image

modules/display.py

@@ -25,7 +25,7 @@ def draw_stream(image,
                 write_idx=False,
                 keypoints_correction=False,
                 new_size=(1333, 1333),
-                only_print=None,
+                only_show=None,
                 axis=False,
                 return_image=False,
                 resize=False):
@@ -48,7 +48,7 @@ def draw_stream(image,
     - write_score (bool): Flag to write scores near the annotations.
     - write_text (bool): Flag to write OCR recognized text.
     - score_threshold (float): Threshold for scores above which annotations will be drawn.
-    - only_print (str): Specific class name to filter annotations by.
+    - only_show (str): Specific class name to filter annotations by.
     - resize (bool): Whether to resize annotations to fit the image size.
     """
 
@@ -74,8 +74,11 @@ def draw_stream(image,
         if score < score_threshold:
             continue
         if draw_boxes:
-            if only_print is not None and only_print != 'all':
-                if prediction['labels'][i] != list(class_dict.values()).index(only_print):
+            if only_show is not None and only_show != 'all':
+                if prediction['labels'][i] != list(class_dict.values()).index(only_show):
+                    continue
+            #dont show the lanes
+            if prediction['labels'][i] == list(class_dict.values()).index('lane'):
                     continue
             cv2.rectangle(image_copy, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 0), int(2*scale))
         if write_score:

modules/eval.py

@@ -9,6 +9,8 @@ from modules.utils import is_vertical
 
 
 def non_maximum_suppression(boxes, scores, labels=None, iou_threshold=0.5):
+    exception = ['pool', 'lane']
+
     idxs = np.argsort(scores)  # Sort the boxes according to their scores in ascending order
     selected_boxes = []
 
@@ -17,7 +19,7 @@ def non_maximum_suppression(boxes, scores, labels=None, iou_threshold=0.5):
         i = idxs[last]
 
         # Skip if the label is a lane
-        if labels is not None and class_dict[labels[i]] == 'lane':
+        if labels is not None and (class_dict[labels[i]] in exception):
             selected_boxes.append(i)
             idxs = np.delete(idxs, last)
             continue
@@ -360,7 +362,7 @@ def full_prediction(model_object, model_arrow, image, score_threshold=0.5, iou_t
 
     # Load an image
     with torch.no_grad():  # Disable gradient calculation for inference
-        _, objects_pred = object_prediction(model_object, image, score_threshold=score_threshold, iou_threshold=iou_threshold)
+        _, objects_pred = object_prediction(model_object, image, score_threshold=score_threshold, iou_threshold=0.1)
         _, arrow_pred = arrow_prediction(model_arrow, image, score_threshold=score_threshold, iou_threshold=iou_threshold, distance_treshold=distance_treshold)
         
         #print('Object prediction:', objects_pred)
@@ -377,7 +379,7 @@ def full_prediction(model_object, model_arrow, image, score_threshold=0.5, iou_t
         #give a link to event to allow the creation of the BPMN id with start, indermediate and end event
         flow_links = give_link_to_element(flow_links, labels)
         
-        boxes,labels,scores,keypoints,flow_links,best_points,pool_dict = last_correction(boxes,labels,scores,keypoints,flow_links,best_points, pool_dict)            
+        boxes,labels,scores,keypoints,flow_links,best_points,pool_dict = last_correction(boxes,labels,scores,keypoints,flow_links,best_points, pool_dict)         
 
         image = image.permute(1, 2, 0).cpu().numpy()
         image = (image * 255).astype(np.uint8)
@@ -399,11 +401,14 @@ def full_prediction(model_object, model_arrow, image, score_threshold=0.5, iou_t
             'BPMN_id': bpmn_id,
         }
 
+
         # give a unique BPMN id to each element
         data = create_BPMN_id(data)   
 
         
 
+        
+
         return image, data
 
 def evaluate_model_by_class(pred_boxes, true_boxes, pred_labels, true_labels, model_dict, iou_threshold=0.5):

modules/toXML.py

@@ -236,7 +236,7 @@ def create_bpmn_object(process, bpmnplane, text_mapping, definitions, size, data
 
         # Data Object
         elif element_type == 'dataObject' or element_type == 'dataStore':
-            print('ici dataObject', element_id)
+            #print('ici dataObject', element_id)
             dataObject_idx = element_id.split('_')[1]
             dataObject_ref = f'DataObjectReference_{dataObject_idx}'
             element = ET.SubElement(process, 'bpmn:dataObjectReference', id=dataObject_ref, dataObjectRef=element_id, name=text_mapping[element_id])