update readme

README.md

@@ -28,9 +28,13 @@ pip install -r requirements.txt
 
 Then download the model ckpts files in: https://huggingface.co/microsoft/OmniParser, and put them under weights/, default folder structure is: weights/icon_detect, weights/icon_caption_florence, weights/icon_caption_blip2. 
 
-Finally, convert the safetensor to .pt file. 
+For v1: 
+convert the safetensor to .pt file. 
 ```python
 python weights/convert_safetensor_to_pt.py
+
+For v1.5: 
+download 'model_v1_5.pt' from https://huggingface.co/microsoft/OmniParser/tree/main/icon_detect_v1_5, make a new dir: weights/icon_detect_v1_5, and put it inside the folder. No weight conversion is needed. 
 ```
 
 ## Examples:
@@ -39,7 +43,10 @@ We put together a few simple examples in the demo.ipynb.
 ## Gradio Demo
 To run gradio demo, simply run:
 ```python
-python gradio_demo.py
+# For v1
+python gradio_demo.py --icon_detect_model weights/icon_detect/best.pt --icon_caption_model florence2
+# For v1.5
+python gradio_demo.py --icon_detect_model weights/icon_detect_v1_5/model_v1_5.pt --icon_caption_model florence2
 ```
 
 ## Model Weights License

gradio_demo.py

@@ -11,10 +11,7 @@ import base64, os
 from utils import check_ocr_box, get_yolo_model, get_caption_model_processor, get_som_labeled_img
 import torch
 from PIL import Image
-
+import argparse
-yolo_model = get_yolo_model(model_path='weights/icon_detect/best.pt')
-caption_model_processor = get_caption_model_processor(model_name="florence2", model_name_or_path="weights/icon_caption_florence")
-# caption_model_processor = get_caption_model_processor(model_name="blip2", model_name_or_path="weights/icon_caption_blip2")
 
 
 
@@ -39,9 +36,9 @@ def process(
     box_threshold,
     iou_threshold,
     use_paddleocr,
-    imgsz
+    imgsz,
+    icon_process_batch_size,
 ) -> Optional[Image.Image]:
-
     image_save_path = 'imgs/saved_image_demo.png'
     image_input.save(image_save_path)
     image = Image.open(image_save_path)
@@ -57,13 +54,26 @@ def process(
     ocr_bbox_rslt, is_goal_filtered = check_ocr_box(image_save_path, display_img = False, output_bb_format='xyxy', goal_filtering=None, easyocr_args={'paragraph': False, 'text_threshold':0.9}, use_paddleocr=use_paddleocr)
     text, ocr_bbox = ocr_bbox_rslt
     # print('prompt:', prompt)
-    dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image_save_path, yolo_model, BOX_TRESHOLD = box_threshold, output_coord_in_ratio=True, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=caption_model_processor, ocr_text=text,iou_threshold=iou_threshold, imgsz=imgsz)  
+    dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image_save_path, yolo_model, BOX_TRESHOLD = box_threshold, output_coord_in_ratio=True, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=caption_model_processor, ocr_text=text,iou_threshold=iou_threshold, imgsz=imgsz, batch_size=icon_process_batch_size)  
     image = Image.open(io.BytesIO(base64.b64decode(dino_labled_img)))
     print('finish processing')
-    parsed_content_list = '\n'.join(parsed_content_list)
+    # parsed_content_list = '\n'.join(parsed_content_list)
+    parsed_content_list = '\n'.join([f'type: {x['type']}, content: {x["content"]}, interactivity: {x["interactivity"]}' for x in parsed_content_list])
     return image, str(parsed_content_list)
 
 
+parser = argparse.ArgumentParser(description='Process model paths and names.')
+parser.add_argument('--icon_detect_model', type=str, required=True, default='weights/icon_detect/best.pt', help='Path to the YOLO model weights')
+parser.add_argument('--icon_caption_model', type=str, required=True, default='florence2',  help='Name of the caption model')
+
+args = parser.parse_args()
+icon_detect_model, icon_caption_model = args.icon_detect_model, args.icon_caption_model
+
+yolo_model = get_yolo_model(model_path=icon_detect_model)
+if icon_caption_model == 'florence2':
+    caption_model_processor = get_caption_model_processor(model_name="florence2", model_name_or_path="weights/icon_caption_florence")
+elif icon_caption_model == 'blip2':
+    caption_model_processor = get_caption_model_processor(model_name="blip2", model_name_or_path="weights/icon_caption_blip2")
 
 with gr.Blocks() as demo:
     gr.Markdown(MARKDOWN)
@@ -78,9 +88,11 @@ with gr.Blocks() as demo:
             iou_threshold_component = gr.Slider(
                 label='IOU Threshold', minimum=0.01, maximum=1.0, step=0.01, value=0.1)
             use_paddleocr_component = gr.Checkbox(
-                label='Use PaddleOCR', value=True)
+                label='Use PaddleOCR', value=False)
             imgsz_component = gr.Slider(
-                label='Icon Detect Image Size', minimum=640, maximum=1920, step=32, value=640)
+                label='Icon Detect Image Size', minimum=640, maximum=3200, step=32, value=1920)
+            icon_process_batch_size_component = gr.Slider(
+                label='Icon Process Batch Size', minimum=1, maximum=256, step=1, value=64)
             submit_button_component = gr.Button(
                 value='Submit', variant='primary')
         with gr.Column():
@@ -94,10 +106,16 @@ with gr.Blocks() as demo:
             box_threshold_component,
             iou_threshold_component,
             use_paddleocr_component,
-            imgsz_component
+            imgsz_component,
+            icon_process_batch_size_component
         ],
         outputs=[image_output_component, text_output_component]
     )
 
 # demo.launch(debug=False, show_error=True, share=True)
-demo.launch(share=True, server_port=7861, server_name='0.0.0.0')
+demo.launch(share=True, server_port=7861, server_name='0.0.0.0')
+
+
+
+# python gradio_demo.py --icon_detect_model weights/icon_detect/best.pt --icon_caption_model florence2
+# python gradio_demo.py --icon_detect_model weights/icon_detect_v1_5/model_v1_5.pt --icon_caption_model florence2

weights/convert_safetensor_to_pt.py

@@ -5,16 +5,13 @@ import argparse
 import yaml
 import os
 
-# accept args to specify v1 or v1_5
+# accept args to specify v1
-parser = argparse.ArgumentParser(description='Specify version v1 or v1_5')
+parser = argparse.ArgumentParser(description='add weight directory')
-parser.add_argument('--weights_dir', type=str, required=True, help='Specify the path to the safetensor file', default='weights/icon_detect_v1_5')
+parser.add_argument('--weights_dir', type=str, required=True, help='Specify the path to the safetensor file', default='weights/icon_detect')
 args = parser.parse_args()
 
 tensor_dict = load_file(os.path.join(args.weights_dir, "model.safetensors"))
 model = DetectionModel(os.path.join(args.weights_dir, "model.yaml"))
-# from ultralytics import YOLO
-# som_model = YOLO("yolo11m.pt")
-# model = som_model.model
 
 model.load_state_dict(tensor_dict)
 save_dict = {'model':model}