File size: 10,530 Bytes
5521308
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a9c5d5
 
 
 
 
 
5521308
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a9c5d5
 
 
 
 
 
5521308
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
# Code credit: [EdgeSAM Demo](https://huggingface.co/spaces/chongzhou/EdgeSAM).

import torch
import gradio as gr
import numpy as np
from tinysam import sam_model_registry, SamPredictor
from PIL import ImageDraw
from utils.tools_gradio import fast_process
import copy
import argparse

snapshot_download("merve/tinysam", local_dir="tinysam")

model_type = "vit_t"
sam = sam_model_registry[model_type](checkpoint="./tinysam/tinysam.pth")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
sam.to(device=device)
sam.eval()
predictor = SamPredictor(sam)

examples = [
    ["assets/1.jpg"],
    ["assets/2.jpg"],
    ["assets/3.jpg"],
    ["assets/4.jpeg"],
    ["assets/5.jpg"],
    ["assets/6.jpeg"]
]

# Description
title = "<center><strong><font size='8'>TinySAM<font></strong> <a href='https://github.com/xinghaochen/TinySAM'><font size='6'>[GitHub]</font></a> </center>"

description_p = """ # Instructions for point mode

                1. Upload an image or click one of the provided examples.
                2. Select the point type.
                3. Click once or multiple times on the image to indicate the object of interest.
                4. The Clear button clears all the points.
                5. The Reset button resets both points and the image.

              """

description_b = """ # Instructions for box mode

                1. Upload an image or click one of the provided examples.
                2. Click twice on the image (diagonal points of the box).
                3. The Clear button clears the box.
                4. The Reset button resets both the box and the image.

              """

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


def reset(session_state):
    session_state['coord_list'] = []
    session_state['label_list'] = []
    session_state['box_list'] = []
    session_state['ori_image'] = None
    session_state['image_with_prompt'] = None
    session_state['feature'] = None
    return None, session_state


def reset_all(session_state):
    session_state['coord_list'] = []
    session_state['label_list'] = []
    session_state['box_list'] = []
    session_state['ori_image'] = None
    session_state['image_with_prompt'] = None
    session_state['feature'] = None
    return None, None, session_state


def clear(session_state):
    session_state['coord_list'] = []
    session_state['label_list'] = []
    session_state['box_list'] = []
    session_state['image_with_prompt'] = copy.deepcopy(session_state['ori_image'])
    return session_state['ori_image'], session_state


def on_image_upload(
    image,
    session_state,
    input_size=1024
):
    session_state['coord_list'] = []
    session_state['label_list'] = []
    session_state['box_list'] = []

    input_size = int(input_size)
    w, h = image.size
    scale = input_size / max(w, h)
    new_w = int(w * scale)
    new_h = int(h * scale)
    image = image.resize((new_w, new_h))
    session_state['ori_image'] = copy.deepcopy(image)
    session_state['image_with_prompt'] = copy.deepcopy(image)
    print("Image changed")
    nd_image = np.array(image)
    session_state['feature'] = None #predictor.set_image(nd_image)

    return image, session_state


def convert_box(xyxy):
    min_x = min(xyxy[0][0], xyxy[1][0])
    max_x = max(xyxy[0][0], xyxy[1][0])
    min_y = min(xyxy[0][1], xyxy[1][1])
    max_y = max(xyxy[0][1], xyxy[1][1])
    xyxy[0][0] = min_x
    xyxy[1][0] = max_x
    xyxy[0][1] = min_y
    xyxy[1][1] = max_y
    return xyxy


def segment_with_points(
    label,
    session_state,
    evt: gr.SelectData,
    input_size=1024,
    better_quality=False,
    withContours=True,
    use_retina=True,
    mask_random_color=False,
):
    x, y = evt.index[0], evt.index[1]
    point_radius, point_color = 5, (97, 217, 54) if label == "Positive" else (237, 34, 13)
    session_state['coord_list'].append([x, y])
    session_state['label_list'].append(1 if label == "Positive" else 0)

    print(f"coord_list: {session_state['coord_list']}")
    print(f"label_list: {session_state['label_list']}")

    draw = ImageDraw.Draw(session_state['image_with_prompt'])
    draw.ellipse(
        [(x - point_radius, y - point_radius), (x + point_radius, y + point_radius)],
        fill=point_color,
    )
    image = session_state['image_with_prompt']

    coord_np = np.array(session_state['coord_list'])
    label_np = np.array(session_state['label_list'])
    masks, scores, logits = predictor.predict(
        point_coords=coord_np,
        point_labels=label_np,
    )
    print(f'scores: {scores}')
    area = masks.sum(axis=(1, 2))
    print(f'area: {area}')

    annotations = np.expand_dims(masks[scores.argmax()], axis=0)

    seg = fast_process(
        annotations=annotations,
        image=image,
        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 seg, session_state


def segment_with_box(
        session_state,
        evt: gr.SelectData,
        input_size=1024,
        better_quality=False,
        withContours=True,
        use_retina=True,
        mask_random_color=False,
):
    x, y = evt.index[0], evt.index[1]
    point_radius, point_color, box_outline = 5, (97, 217, 54), 5
    box_color = (0, 255, 0)

    if len(session_state['box_list']) == 0:
        session_state['box_list'].append([x, y])
    elif len(session_state['box_list']) == 1:
        session_state['box_list'].append([x, y])
    elif len(session_state['box_list']) == 2:
        session_state['image_with_prompt'] = copy.deepcopy(session_state['ori_image'])
        session_state['box_list'] = [[x, y]]

    print(f"box_list: {session_state['box_list']}")

    draw = ImageDraw.Draw(session_state['image_with_prompt'])
    draw.ellipse(
        [(x - point_radius, y - point_radius), (x + point_radius, y + point_radius)],
        fill=point_color,
    )
    image = session_state['image_with_prompt']

    if len(session_state['box_list']) == 2:
        box = convert_box(session_state['box_list'])
        xy = (box[0][0], box[0][1], box[1][0], box[1][1])
        draw.rectangle(
            xy,
            outline=box_color,
            width=box_outline
        )

        box_np = np.array(xy)
        masks, scores, _ = predictor.predict(
            point_coords=None,
            point_labels=None,
            box=box_np[None, :],
        )
        annotations = np.expand_dims(masks[scores.argmax()], axis=0)

        seg = fast_process(
            annotations=annotations,
            image=image,
            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 seg, session_state
    return image, session_state


img_p = gr.Image(label="Input with points", type="pil")
img_b = gr.Image(label="Input with box", type="pil")

with gr.Blocks(css=css, title="EdgeSAM") as demo:
    session_state = gr.State({
        'coord_list': [],
        'label_list': [],
        'box_list': [],
        'ori_image': None,
        'image_with_prompt': None,
        'feature': None
    })

    with gr.Row():
        with gr.Column(scale=1):
            # Title
            gr.Markdown(title)

    with gr.Tab("Point mode") as tab_p:
        # Images
        with gr.Row(variant="panel"):
            with gr.Column(scale=1):
                img_p.render()
            with gr.Column(scale=1):
                with gr.Row():
                    add_or_remove = gr.Radio(
                        ["Positive", "Negative"],
                        value="Positive",
                        label="Point Type"
                    )

                    with gr.Column():
                        clear_btn_p = gr.Button("Clear", variant="secondary")
                        reset_btn_p = gr.Button("Reset", variant="secondary")
                with gr.Row():
                    gr.Markdown(description_p)

        with gr.Row():
            with gr.Column():
                gr.Markdown("Try some of the examples below ⬇️")
                gr.Examples(
                    examples=examples,
                    inputs=[img_p, session_state],
                    outputs=[img_p, session_state],
                    examples_per_page=8,
                    fn=on_image_upload,
                    run_on_click=True
                )

    with gr.Tab("Box mode") as tab_b:
        # Images
        with gr.Row(variant="panel"):
            with gr.Column(scale=1):
                img_b.render()
            with gr.Row():
                with gr.Column():
                    clear_btn_b = gr.Button("Clear", variant="secondary")
                    reset_btn_b = gr.Button("Reset", variant="secondary")
                    gr.Markdown(description_b)

        with gr.Row():
            with gr.Column():
                gr.Markdown("Try some of the examples below ⬇️")
                gr.Examples(
                    examples=examples,
                    inputs=[img_b, session_state],
                    outputs=[img_b, session_state],
                    examples_per_page=8,
                    fn=on_image_upload,
                    run_on_click=True
                )

    with gr.Row():
        with gr.Column(scale=1):
            gr.Markdown(
                "<center><img src='https://visitor-badge.laobi.icu/badge?page_id=chongzhou/edgesam' alt='visitors'></center>")

    img_p.upload(on_image_upload, [img_p, session_state], [img_p, session_state])
    img_p.select(segment_with_points, [add_or_remove, session_state], [img_p, session_state])

    clear_btn_p.click(clear, [session_state], [img_p, session_state])
    reset_btn_p.click(reset, [session_state], [img_p, session_state])
    tab_p.select(fn=reset_all, inputs=[session_state], outputs=[img_p, img_b, session_state])

    img_b.upload(on_image_upload, [img_b, session_state], [img_b, session_state])
    img_b.select(segment_with_box, [session_state], [img_b, session_state])

    clear_btn_b.click(clear, [session_state], [img_b, session_state])
    reset_btn_b.click(reset, [session_state], [img_b, session_state])
    tab_b.select(fn=reset_all, inputs=[session_state], outputs=[img_p, img_b, session_state])

demo.queue()
demo.launch()