added dev_segmented_extract,

extracts marked images in 'labelme' tool, that can be used in FANseg training

main.py

@@ -105,6 +105,17 @@ if __name__ == "__main__":
     p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
     p.set_defaults (func=process_dev_test)
     
+    def process_dev_segmented_extract(arguments):
+        osex.set_process_lowest_prio()
+        from mainscripts import dev_misc
+        dev_misc.dev_segmented_extract(arguments.input_dir, arguments.output_dir)
+
+    p = subparsers.add_parser( "dev_segmented_extract", help="")
+    p.add_argument('--input-dir', required=True, action=fixPathAction, dest="input_dir")
+    p.add_argument('--output-dir', required=True, action=fixPathAction, dest="output_dir")
+
+    p.set_defaults (func=process_dev_segmented_extract)
+
     def process_sort(arguments):
         osex.set_process_lowest_prio()
         from mainscripts import Sorter

mainscripts/dev_misc.py

@@ -553,22 +553,19 @@ def dev_test1(input_dir):
             #import code
             #code.interact(local=dict(globals(), **locals()))
 
-#unused in end user workflow
-def dev_test(input_dir ):
+
+def dev_segmented_extract(input_dir, output_dir ):
     # extract and merge .json labelme files within the faces
       
-    
     device_config = nn.DeviceConfig.GPUIndexes( nn.ask_choose_device_idxs(suggest_all_gpu=True) )
     
-    
-    
     input_path = Path(input_dir)
     if not input_path.exists():
         raise ValueError('input_dir not found. Please ensure it exists.')
 
-    output_path = input_path.parent / (input_path.name+'_merged')
-    
-    io.log_info(f'Output dir is % {output_path}')
+    output_path = Path(output_dir)
+    io.log_info("Performing extract segmented faces.")
+    io.log_info(f'Output dir is {output_path}')
     
     if output_path.exists():
         output_images_paths = pathex.get_image_paths(output_path)
@@ -582,27 +579,34 @@ def dev_test(input_dir ):
     images_paths = pathex.get_image_paths(input_path)
 
     extract_data = []    
-    
     images_jsons = {}
+    images_processed = 0
+    
     
     for filepath in io.progress_bar_generator(images_paths, "Processing"):
         filepath = Path(filepath)
-
-
         json_filepath = filepath.parent / (filepath.stem+'.json')        
         
-
         if json_filepath.exists():
+            try:
                 json_dict = json.loads(json_filepath.read_text())
                 images_jsons[filepath] = json_dict
                 
                 total_points = [ [x,y] for shape in json_dict['shapes'] for x,y in shape['points'] ]
                 total_points = np.array(total_points)
 
+                if len(total_points) == 0:
+                    io.log_info(f"No points found in {json_filepath}, skipping.")
+                    continue
+                
                 l,r = int(total_points[:,0].min()), int(total_points[:,0].max())
                 t,b = int(total_points[:,1].min()), int(total_points[:,1].max())
                 
                 extract_data.append ( ExtractSubprocessor.Data(filepath, rects=[ [l,t,r,b] ] ) ) 
+                images_processed += 1
+            except:                
+                io.log_err(f"err {filepath}")
+                return
             
     image_size = 1024
     face_type = FaceType.HEAD  
@@ -629,6 +633,11 @@ def dev_test(input_dir ):
 
         dflimg.embed_and_set (filepath, ie_polys=ie_polys)
                             
+    io.log_info(f"Images found:     {len(images_paths)}")
+    io.log_info(f"Images processed: {images_processed}")
+    
+
+
 """
 #mark only
 for data in extract_data:
@@ -656,5 +665,3 @@ def dev_test(input_dir ):
                                         source_landmarks=data.landmarks[0]
                         )
 """
-                
-    io.log_info("Done.")