Hugging Face's logo

Spaces:
strikerhell
/
SEER
Build error

App Files Community
SEER
File size: 4,248 Bytes 
e2a72e7
 
4bfb63b
e2a72e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4bfb63b
e2a72e7
 
 
 
 
 
 
 
 
4bfb63b
e2a72e7
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
 
from typing import Optional

import gradio as gr
import numpy as np
import torch
from PIL import Image
import io

import spaces
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

# Model source: https://huggingface.co/strikerhell/SEER-model
# gr.load("models/strikerhell/SEER-model").launch()
MODEL="strikerhell/SEER-model"
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")
platform = 'pc'
if platform == 'pc':
    draw_bbox_config = {
        'text_scale': 0.8,
        'text_thickness': 2,
        'text_padding': 2,
        'thickness': 2,
    }
elif platform == 'web':
    draw_bbox_config = {
        'text_scale': 0.8,
        'text_thickness': 2,
        'text_padding': 3,
        'thickness': 3,
    }
elif platform == 'mobile':
    draw_bbox_config = {
        'text_scale': 0.8,
        'text_thickness': 2,
        'text_padding': 3,
        'thickness': 3,
    }



MARKDOWN = """
# SEER for Pure Vision Based General GUI Agent 🔥

SEER is a screen parsing tool to convert general GUI screen to structured elements. 
"""

DEVICE = torch.device('cuda')

# @spaces.GPU
@torch.inference_mode()
@torch.autocast(device_type="cuda", dtype=torch.bfloat16)
@spaces.GPU
def process(
    image_input,
    box_threshold=0.01,
    iou_threshold=0.01
) -> Optional[Image.Image]:

    image_save_path = 'imgs/saved_image_demo.png'
    image_input.save(image_save_path)
    # import pdb; pdb.set_trace()

    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})
    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)
    image = Image.open(io.BytesIO(base64.b64decode(dino_labled_img)))
    print('finish processing')
    parsed_content_list = '\n'.join(parsed_content_list)
    return image, str(parsed_content_list)

examples = [
    ["./imgs/google_page.png", 0.05, 0.1],
    ["./imgs/logo.png", 0.2, 0.15],
    ["./imgs/windows_home.png", 0.1, 0.05],
    ["./imgs/windows_multitab.png", 0.1, 0.05]
]


with gr.Blocks() as demo:
    gr.Markdown(MARKDOWN)
    with gr.Row():
        with gr.Column():
            image_input_component = gr.Image(
                type='pil', label='Upload image')
            # set the threshold for removing the bounding boxes with low confidence, default is 0.05
            box_threshold_component = gr.Slider(
                label='Box Threshold', minimum=0.01, maximum=1.0, step=0.01, value=0.05)
            # set the threshold for removing the bounding boxes with large overlap, default is 0.1
            iou_threshold_component = gr.Slider(
                label='IOU Threshold', minimum=0.01, maximum=1.0, step=0.01, value=0.1)
            submit_button_component = gr.Button(
                value='Submit', variant='primary')
        with gr.Column():
            image_output_component = gr.Image(type='pil', label='Image Output')
            text_output_component = gr.Textbox(label='Parsed screen elements', placeholder='Text Output')

    gr.Examples(
        examples=examples,
        inputs=[image_input_component],
        outputs=[image_output_component, text_output_component],
        fn=process,  # Function to execute
        cache_examples="lazy"  # Enables lazy caching for examples
    )


    submit_button_component.click(
        fn=process,
        inputs=[
            image_input_component,
            box_threshold_component,
            iou_threshold_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')