Spaces:
Sleeping
Sleeping
File size: 13,737 Bytes
1bf7e5e 6a34377 d33cca1 6a34377 1bf7e5e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 |
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('./FastSAM.pt')
device = torch.device(
"cuda"
if torch.cuda.is_available()
else "mps"
if torch.backends.mps.is_available()
else "cpu"
)
# Description
title = "<center><strong><font size='8'>🏃 Fast Segment Anything 🤗</font></strong></center>"
news = """ # 📖 News
🔥 2023/07/14: Add a "wider result" button in text mode (Thanks for [gaoxinge](https://github.com/CASIA-IVA-Lab/FastSAM/pull/95)).
🔥 2023/06/29: Support the text mode (Thanks for [gaoxinge](https://github.com/CASIA-IVA-Lab/FastSAM/pull/47)).
🔥 This is a copy of the model created by these amazing guys above to learn.
"""
description_e = """This is a demo on Github project 🏃 [Fast Segment Anything Model](https://github.com/CASIA-IVA-Lab/FastSAM). Welcome to give a star ⭐️ to it.
🎯 Upload an Image, segment it with Fast Segment Anything (Everything mode). The other modes will come soon.
🏠 Check out our [Model Card 🏃](https://huggingface.co/An-619/FastSAM) - Orginal
"""
description_p = """ # 🎯 Instructions for points mode
This is a demo on Github project 🏃 [Fast Segment Anything Model](https://github.com/CASIA-IVA-Lab/FastSAM). Welcome to give a star ⭐️ to it.
"""
examples = [["examples/dogs.jpg"], ["examples/fruits.jpg"], ["examples/flowers.jpg"],]
default_example = examples[0]
css = "h1 { text-align: center } .about { text-align: justify; padding-left: 10%; padding-right: 10%; }"
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) # 确保 imgsz 是整数
# Thanks for the suggestion by hysts in HuggingFace.
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) # 确保 imgsz 是整数
# Thanks for the suggestion by hysts in HuggingFace.
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')
# 创建一个可以在图像上绘图的对象
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.Column(scale=1):
# News
gr.Markdown(news)
with gr.Tab("Everything mode"):
# Images
with gr.Row(variant="panel"):
with gr.Column(scale=1):
cond_img_e.render()
with gr.Column(scale=1):
segm_img_e.render()
# Submit & Clear
with gr.Row():
with gr.Column():
input_size_slider.render()
with gr.Row():
contour_check = gr.Checkbox(value=True, label='withContours', info='draw the edges of the masks')
with gr.Column():
segment_btn_e = gr.Button("Segment Everything", variant='primary')
clear_btn_e = gr.Button("Clear", variant="secondary")
gr.Markdown("Try some of the examples below ⬇️")
gr.Examples(examples=examples,
inputs=[cond_img_e],
outputs=segm_img_e,
fn=segment_everything,
cache_examples=True,
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')
with gr.Column():
retina_check = gr.Checkbox(value=True, label='use_retina', info='draw high-resolution segmentation masks')
# Description
gr.Markdown(description_e)
segment_btn_e.click(segment_everything,
inputs=[
cond_img_e,
input_size_slider,
iou_threshold,
conf_threshold,
mor_check,
contour_check,
retina_check,
],
outputs=segm_img_e)
with gr.Tab("Points mode"):
# Images
with gr.Row(variant="panel"):
with gr.Column(scale=1):
cond_img_p.render()
with gr.Column(scale=1):
segm_img_p.render()
# Submit & Clear
with gr.Row():
with gr.Column():
with gr.Row():
add_or_remove = gr.Radio(["Add Mask", "Remove Area"], value="Add Mask", label="Point_label (foreground/background)")
with gr.Column():
segment_btn_p = gr.Button("Segment with points prompt", variant='primary')
clear_btn_p = gr.Button("Clear points", variant='secondary')
gr.Markdown("Try some of the examples below ⬇️")
gr.Examples(examples=examples,
inputs=[cond_img_p],
# outputs=segm_img_p,
# fn=segment_with_points,
# cache_examples=True,
examples_per_page=4)
with gr.Column():
# Description
gr.Markdown(description_p)
cond_img_p.select(get_points_with_draw, [cond_img_p, add_or_remove], cond_img_p)
segment_btn_p.click(segment_with_points,
inputs=[cond_img_p],
outputs=[segm_img_p, cond_img_p])
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],
# outputs=segm_img_e,
# fn=segment_everything,
# cache_examples=True,
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')
# Description
gr.Markdown(description_e)
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() |