File size: 8,428 Bytes
9ba6a01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ac60665
9ba6a01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
from ultralytics import YOLO
import gradio as gr
import torch
from utils.tools_gradio import fast_process
from utils.tools import format_results, box_prompt, point_prompt, text_prompt
from PIL import ImageDraw
import numpy as np

# Load the pre-trained model
model = YOLO('./weights/FastSAM.pt')

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Description
title = "<center><strong><font size='10'> Fast Segment Anything </font></strong></center>"

css = "h1 { text-align: center } .about { text-align: justify; padding-left: 10%; padding-right: 10%; }"

examples = [["examples/sa_8776.jpg"], ["examples/sa_414.jpg"], ["examples/sa_1309.jpg"], ["examples/sa_11025.jpg"],
            ["examples/sa_561.jpg"], ["examples/sa_192.jpg"], ["examples/sa_10039.jpg"], ["examples/sa_862.jpg"]]

default_example = examples[0]

def segment_everything(
    input,
    input_size=1024, 
    iou_threshold=0.7,
    conf_threshold=0.25,
    better_quality=False,
    withContours=True,
    use_retina=True,
    text="",
    wider=False,
    mask_random_color=True,
):
    input_size = int(input_size)  
    w, h = input.size
    scale = input_size / max(w, h)
    new_w = int(w * scale)
    new_h = int(h * scale)
    input = input.resize((new_w, new_h))

    results = model(input,
                    device=device,
                    retina_masks=True,
                    iou=iou_threshold,
                    conf=conf_threshold,
                    imgsz=input_size,)

    if len(text) > 0:
        results = format_results(results[0], 0)
        annotations, _ = text_prompt(results, text, input, device=device, wider=wider)
        annotations = np.array([annotations])
    else:
        annotations = results[0].masks.data
    
    fig = fast_process(annotations=annotations,
                       image=input,
                       device=device,
                       scale=(1024 // input_size),
                       better_quality=better_quality,
                       mask_random_color=mask_random_color,
                       bbox=None,
                       use_retina=use_retina,
                       withContours=withContours,)
    return fig


def segment_with_points(
    input,
    input_size=1024, 
    iou_threshold=0.7,
    conf_threshold=0.25,
    better_quality=False,
    withContours=True,
    use_retina=True,
    mask_random_color=True,
):
    global global_points
    global global_point_label
    
    input_size = int(input_size)
    w, h = input.size
    scale = input_size / max(w, h)
    new_w = int(w * scale)
    new_h = int(h * scale)
    input = input.resize((new_w, new_h))
    
    scaled_points = [[int(x * scale) for x in point] for point in global_points]

    results = model(input,
                    device=device,
                    retina_masks=True,
                    iou=iou_threshold,
                    conf=conf_threshold,
                    imgsz=input_size,)
    
    results = format_results(results[0], 0)
    annotations, _ = point_prompt(results, scaled_points, global_point_label, new_h, new_w)
    annotations = np.array([annotations])

    fig = fast_process(annotations=annotations,
                       image=input,
                       device=device,
                       scale=(1024 // input_size),
                       better_quality=better_quality,
                       mask_random_color=mask_random_color,
                       bbox=None,
                       use_retina=use_retina,
                       withContours=withContours,)

    global_points = []
    global_point_label = []
    return fig, None


def get_points_with_draw(image, label, evt: gr.SelectData):
    global global_points
    global global_point_label

    x, y = evt.index[0], evt.index[1]
    point_radius, point_color = 15, (255, 255, 0) if label == 'Add Mask' else (255, 0, 255)
    global_points.append([x, y])
    global_point_label.append(1 if label == 'Add Mask' else 0)
    
    print(x, y, label == 'Add Mask')
    
    draw = ImageDraw.Draw(image)
    draw.ellipse([(x - point_radius, y - point_radius), (x + point_radius, y + point_radius)], fill=point_color)
    return image


cond_img_e = gr.Image(label="Input", value=default_example[0], type='pil')
cond_img_p = gr.Image(label="Input with points", value=default_example[0], type='pil')
cond_img_t = gr.Image(label="Input with text", value="examples/dogs.jpg", type='pil')

segm_img_e = gr.Image(label="Segmented Image", interactive=False, type='pil')
segm_img_p = gr.Image(label="Segmented Image with points", interactive=False, type='pil')
segm_img_t = gr.Image(label="Segmented Image with text", interactive=False, type='pil')

global_points = []
global_point_label = []

input_size_slider = gr.components.Slider(minimum=512,
                                         maximum=1024,
                                         value=1024,
                                         step=64,
                                         label='Input_size',
                                         info='Our model was trained on a size of 1024')

with gr.Blocks(css=css, title='Fast Segment Anything') as demo:
    with gr.Row():
        with gr.Column(scale=1):
            # Title
            gr.Markdown(title)

    with gr.Tab("Text mode"):
        # Images
        with gr.Row(variant="panel"):
            with gr.Column(scale=1):
                cond_img_t.render()

            with gr.Column(scale=1):
                segm_img_t.render()

        # Submit & Clear
        with gr.Row():
            with gr.Column():
                input_size_slider_t = gr.components.Slider(minimum=512,
                                                           maximum=1024,
                                                           value=1024,
                                                           step=64,
                                                           label='Input_size',
                                                           info='Our model was trained on a size of 1024')
                with gr.Row():
                    with gr.Column():
                        contour_check = gr.Checkbox(value=True, label='withContours', info='draw the edges of the masks')
                        text_box = gr.Textbox(label="text prompt", value="a black dog")

                    with gr.Column():
                        segment_btn_t = gr.Button("Segment with text", variant='primary')
                        clear_btn_t = gr.Button("Clear", variant="secondary")

                gr.Markdown("Try some of the examples below ⬇️")
                gr.Examples(examples=[["examples/dogs.jpg"], ["examples/fruits.jpg"], ["examples/flowers.jpg"]],
                            inputs=[cond_img_t],
                            examples_per_page=4)

            with gr.Column():
                with gr.Accordion("Advanced options", open=False):
                    iou_threshold = gr.Slider(0.1, 0.9, 0.7, step=0.1, label='iou', info='iou threshold for filtering the annotations')
                    conf_threshold = gr.Slider(0.1, 0.9, 0.25, step=0.05, label='conf', info='object confidence threshold')
                    with gr.Row():
                        mor_check = gr.Checkbox(value=False, label='better_visual_quality', info='better quality using morphologyEx')
                        retina_check = gr.Checkbox(value=True, label='use_retina', info='draw high-resolution segmentation masks')
                        wider_check = gr.Checkbox(value=False, label='wider', info='wider result')
    
    segment_btn_t.click(segment_everything,
                        inputs=[
                            cond_img_t,
                            input_size_slider_t,
                            iou_threshold,
                            conf_threshold,
                            mor_check,
                            contour_check,
                            retina_check,
                            text_box,
                            wider_check,
                        ],
                        outputs=segm_img_t)

    def clear():
        return None, None
    
    def clear_text():
        return None, None, None

    clear_btn_e.click(clear, outputs=[cond_img_e, segm_img_e])
    clear_btn_p.click(clear, outputs=[cond_img_p, segm_img_p])
    clear_btn_t.click(clear_text, outputs=[cond_img_p, segm_img_p, text_box])

demo.queue()
demo.launch()