Updated readme.md

readme.md

@@ -2,17 +2,17 @@
 
 
 #  pipline of the data engine
-###   read the grounding data from json file
+###   read the grounding data from the JSON file
     for each sample, per-store the others samples sharing the same image.
     add the 
 
-###   model predict and save the jons files
+###   model predict and save the JSON files
 -     visual to check the json files
 -  found that some boxes are overlapped heavily, with different text
 - how to deal with these boxes? 
 
 ###  merge model prediction to label,
-- discard the bbox with higher iou  ( > 0.8, higher iou , no consider the class or text)
+- discard the bbox with higher iou  ( > 0.8, higher iou, no consider the class or text)
 
 
 
@@ -21,7 +21,7 @@
 -    generate the visual prompt embedding for each instance (bbox)
 
 
--    merge bboxes within the same image ( consider the vpe distance  and text similarity ,bbox iou<0.8 )
+-    merge bboxes within the same image ( consider the vpe distance  and text similarity,bbox iou<0.8 )
 
 
 -    transfer to grounding format cache for training
@@ -31,4 +31,4 @@
 
 to do:
 
-write a tools to visual the bbox ious. within the same images 
+Write a tool to visualize the BBox IoUs within the same image.