Error when run gradio_demo.py

[JingyuanBai]

I cannot get the result picture when I run in the ubuntu or Windows os, It ocuurs
as "TypeError: 'NoneType' object cannot be interpreted as an integer"
If someone knows this error ,please tell me how to solve this problem, thank you !
All information as follows:
image 1/1 /root/OmniParser/imgs/saved_image_demo.png: 384x640 54 0s, 96.9ms
Speed: 3.7ms preprocess, 96.9ms inference, 209.1ms postprocess per image at shape (1, 3, 384, 640)
Traceback (most recent call last):
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/gradio/queueing.py", line 624, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/gradio/route_utils.py", line 323, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/gradio/blocks.py", line 2015, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/gradio/blocks.py", line 1562, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/anyio/to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 807, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/gradio/utils.py", line 865, in wrapper
response = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/root/OmniParser/gradio_demo.py", line 60, in process
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)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/OmniParser/utils.py", line 442, in get_som_labeled_img
parsed_content_icon = get_parsed_content_icon(filtered_boxes, starting_idx, image_source, caption_model_processor, prompt=prompt,batch_size=batch_size)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vipuser/miniconda3/envs/omni/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/OmniParser/utils.py", line 102, in get_parsed_content_icon
for i in range(0, len(croped_pil_image), batch_size):
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: 'NoneType' object cannot be interpreted as an integer

[Chirag-Mphasis]

I have the same issue. Were you able to resolve it?

[JingyuanBai]

I have the same issue. Were you able to resolve it?

not yet. I am trying to find out where goes wrong

[xiaoyao9184]

OmniParser/utils.py

Line 400 in 2f13aeb

def get_som_labeled_img(img_path, model=None, BOX_TRESHOLD = 0.01, output_coord_in_ratio=False, ocr_bbox=None, text_scale=0.4, text_padding=5, draw_bbox_config=None, caption_model_processor=None, ocr_text=[], use_local_semantics=True, iou_threshold=0.9,prompt=None, scale_img=False, imgsz=None, batch_size=None):

change batch_size=32

but there are still other errors.

You can revert to version ba4e04f.

[fdciabdul]

same issue

is there any solutioin yet?

[asklar]

git checkout ba4e04fccb67070c718530e65570703f9f68a347 worked to convert the safetensors to pt step, and after that I could run the gradio demo

[asklar]

From owners:

With the latest code, to run gradio demo, simply run:

# 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