Spaces:
Sleeping
Sleeping
Upload 14 files
Browse files- app.py +241 -0
- assets/picture1.jpg +0 -0
- assets/picture2.jpg +0 -0
- assets/picture3.jpg +0 -0
- assets/picture4.jpg +0 -0
- assets/picture5.jpg +0 -0
- assets/picture6.jpg +0 -0
- repvit_sam.pt +3 -0
- requirements.txt +5 -0
- utils/__init__.py +0 -0
- utils/tools.py +406 -0
- utils/tools_gradio.py +192 -0
app.py
ADDED
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
|
3 |
+
import gradio as gr
|
4 |
+
import numpy as np
|
5 |
+
import torch
|
6 |
+
from repvit_sam import SamAutomaticMaskGenerator, SamPredictor, sam_model_registry
|
7 |
+
from PIL import ImageDraw
|
8 |
+
from utils.tools import box_prompt, format_results, point_prompt
|
9 |
+
from utils.tools_gradio import fast_process
|
10 |
+
|
11 |
+
# Most of our demo code is from [FastSAM Demo](https://huggingface.co/spaces/An-619/FastSAM). Huge thanks for AN-619.
|
12 |
+
|
13 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
14 |
+
|
15 |
+
# Load the pre-trained model
|
16 |
+
sam_checkpoint = "repvit_sam.pt"
|
17 |
+
model_type = "repvit"
|
18 |
+
|
19 |
+
repvit_sam = sam_model_registry[model_type](checkpoint=sam_checkpoint)
|
20 |
+
repvit_sam = repvit_sam.to(device=device)
|
21 |
+
repvit_sam.eval()
|
22 |
+
|
23 |
+
mask_generator = SamAutomaticMaskGenerator(repvit_sam)
|
24 |
+
predictor = SamPredictor(repvit_sam)
|
25 |
+
|
26 |
+
# Description
|
27 |
+
title = "<center><strong><font size='8'>RepViT-SAM<font></strong></center>"
|
28 |
+
|
29 |
+
description_e = """This is a demo of [RepViT-SAM](https://github.com/THU-MIG/RepViT).
|
30 |
+
|
31 |
+
We will provide box mode soon.
|
32 |
+
|
33 |
+
Enjoy!
|
34 |
+
|
35 |
+
"""
|
36 |
+
|
37 |
+
description_p = """ Instructions for point mode
|
38 |
+
|
39 |
+
0. Restart by click the Restart button
|
40 |
+
1. Select a point with Add Mask for the foreground (Must)
|
41 |
+
2. Select a point with Remove Area for the background (Optional)
|
42 |
+
3. Click the Start Segmenting.
|
43 |
+
|
44 |
+
Github [link](https://github.com/THU-MIG/RepViT)
|
45 |
+
|
46 |
+
"""
|
47 |
+
|
48 |
+
examples = [
|
49 |
+
["app/assets/picture3.jpg"],
|
50 |
+
["app/assets/picture4.jpg"],
|
51 |
+
["app/assets/picture6.jpg"],
|
52 |
+
["app/assets/picture1.jpg"],
|
53 |
+
]
|
54 |
+
|
55 |
+
default_example = examples[0]
|
56 |
+
|
57 |
+
css = "h1 { text-align: center } .about { text-align: justify; padding-left: 10%; padding-right: 10%; }"
|
58 |
+
|
59 |
+
def segment_with_points(
|
60 |
+
image,
|
61 |
+
original_image,
|
62 |
+
input_size=1024,
|
63 |
+
better_quality=False,
|
64 |
+
withContours=True,
|
65 |
+
use_retina=True,
|
66 |
+
mask_random_color=True,
|
67 |
+
):
|
68 |
+
global global_points
|
69 |
+
global global_point_label
|
70 |
+
|
71 |
+
input_size = int(input_size)
|
72 |
+
w, h = image.size
|
73 |
+
scale = input_size / max(w, h)
|
74 |
+
new_w = int(w * scale)
|
75 |
+
new_h = int(h * scale)
|
76 |
+
image = image.resize((new_w, new_h))
|
77 |
+
|
78 |
+
scaled_points = np.array(
|
79 |
+
[[int(x * scale) for x in point] for point in global_points]
|
80 |
+
)
|
81 |
+
scaled_point_label = np.array(global_point_label)
|
82 |
+
|
83 |
+
if scaled_points.size == 0 and scaled_point_label.size == 0:
|
84 |
+
print("No points selected")
|
85 |
+
return image, image
|
86 |
+
|
87 |
+
nd_image = np.array(original_image.resize((new_w, new_h)))
|
88 |
+
predictor.set_image(nd_image)
|
89 |
+
masks, scores, logits = predictor.predict(
|
90 |
+
point_coords=scaled_points,
|
91 |
+
point_labels=scaled_point_label,
|
92 |
+
multimask_output=False,
|
93 |
+
)
|
94 |
+
|
95 |
+
results = format_results(masks, scores, logits, 0)
|
96 |
+
|
97 |
+
annotations, _ = point_prompt(
|
98 |
+
results, scaled_points, scaled_point_label, new_h, new_w
|
99 |
+
)
|
100 |
+
annotations = np.array([annotations])
|
101 |
+
|
102 |
+
fig = fast_process(
|
103 |
+
annotations=annotations,
|
104 |
+
image=image,
|
105 |
+
device=device,
|
106 |
+
scale=(1024 // input_size),
|
107 |
+
better_quality=better_quality,
|
108 |
+
mask_random_color=mask_random_color,
|
109 |
+
bbox=None,
|
110 |
+
use_retina=use_retina,
|
111 |
+
withContours=withContours,
|
112 |
+
)
|
113 |
+
|
114 |
+
global_points = []
|
115 |
+
global_point_label = []
|
116 |
+
# return fig, None
|
117 |
+
return fig, original_image.resize((new_w, new_h))
|
118 |
+
|
119 |
+
|
120 |
+
def get_points_with_draw(image, label, evt: gr.SelectData):
|
121 |
+
global global_points
|
122 |
+
global global_point_label
|
123 |
+
|
124 |
+
x, y = evt.index[0], evt.index[1]
|
125 |
+
point_radius, point_color = 15 * ((max(image.width, image.height)) / 1024), (255, 255, 0) if label == "Add Mask" else (
|
126 |
+
255,
|
127 |
+
0,
|
128 |
+
255,
|
129 |
+
)
|
130 |
+
global_points.append([x, y])
|
131 |
+
global_point_label.append(1 if label == "Add Mask" else 0)
|
132 |
+
|
133 |
+
# 创建一个可以在图像上绘图的对象
|
134 |
+
draw = ImageDraw.Draw(image)
|
135 |
+
draw.ellipse(
|
136 |
+
[(x - point_radius, y - point_radius), (x + point_radius, y + point_radius)],
|
137 |
+
fill=point_color,
|
138 |
+
)
|
139 |
+
return image
|
140 |
+
|
141 |
+
|
142 |
+
cond_img_e = gr.Image(label="Input", value=default_example[0], type="pil")
|
143 |
+
cond_img_p = gr.Image(label="Input with points", value=default_example[0], type="pil")
|
144 |
+
|
145 |
+
segm_img_e = gr.Image(label="Segmented Image", interactive=False, type="pil")
|
146 |
+
segm_img_p = gr.Image(
|
147 |
+
label="Segmented Image with points", interactive=True, type="pil"
|
148 |
+
)
|
149 |
+
|
150 |
+
global_points = []
|
151 |
+
global_point_label = []
|
152 |
+
|
153 |
+
input_size_slider = gr.components.Slider(
|
154 |
+
minimum=512,
|
155 |
+
maximum=1024,
|
156 |
+
value=1024,
|
157 |
+
step=64,
|
158 |
+
label="Input_size",
|
159 |
+
info="Our model was trained on a size of 1024",
|
160 |
+
)
|
161 |
+
|
162 |
+
with gr.Blocks(css=css, title="RepViT-SAM") as demo:
|
163 |
+
from PIL import Image
|
164 |
+
original_image = gr.State(value=Image.open(default_example[0]).convert('RGB'))
|
165 |
+
|
166 |
+
with gr.Row():
|
167 |
+
with gr.Column(scale=1):
|
168 |
+
# Title
|
169 |
+
gr.Markdown(title)
|
170 |
+
|
171 |
+
with gr.Tab("Point mode"):
|
172 |
+
# Images
|
173 |
+
with gr.Row(variant="panel"):
|
174 |
+
with gr.Column(scale=1):
|
175 |
+
cond_img_p.render()
|
176 |
+
|
177 |
+
with gr.Column(scale=1):
|
178 |
+
segm_img_p.render()
|
179 |
+
|
180 |
+
# Submit & Clear
|
181 |
+
with gr.Row():
|
182 |
+
with gr.Column():
|
183 |
+
with gr.Row():
|
184 |
+
add_or_remove = gr.Radio(
|
185 |
+
["Add Mask", "Remove Area"],
|
186 |
+
value="Add Mask",
|
187 |
+
)
|
188 |
+
|
189 |
+
with gr.Column():
|
190 |
+
segment_btn_p = gr.Button(
|
191 |
+
"Start segmenting!", variant="primary"
|
192 |
+
)
|
193 |
+
clear_btn_p = gr.Button("Restart", variant="secondary")
|
194 |
+
|
195 |
+
gr.Markdown("Try some of the examples below ⬇️")
|
196 |
+
|
197 |
+
gr.Examples(
|
198 |
+
examples=examples,
|
199 |
+
inputs=[cond_img_p],
|
200 |
+
fn=lambda x: x,
|
201 |
+
outputs=[original_image],
|
202 |
+
# fn=segment_with_points,
|
203 |
+
# cache_examples=True,
|
204 |
+
examples_per_page=4,
|
205 |
+
run_on_click=True
|
206 |
+
)
|
207 |
+
|
208 |
+
with gr.Column():
|
209 |
+
# Description
|
210 |
+
gr.Markdown(description_p)
|
211 |
+
|
212 |
+
cond_img_p.select(get_points_with_draw, [cond_img_p, add_or_remove], cond_img_p)
|
213 |
+
cond_img_p.upload(lambda x: x, inputs=[cond_img_p], outputs=[original_image])
|
214 |
+
|
215 |
+
# segment_btn_e.click(
|
216 |
+
# segment_everything,
|
217 |
+
# inputs=[
|
218 |
+
# cond_img_e,
|
219 |
+
# input_size_slider,
|
220 |
+
# mor_check,
|
221 |
+
# contour_check,
|
222 |
+
# retina_check,
|
223 |
+
# ],
|
224 |
+
# outputs=segm_img_e,
|
225 |
+
# )
|
226 |
+
|
227 |
+
segment_btn_p.click(
|
228 |
+
segment_with_points, inputs=[cond_img_p, original_image], outputs=[segm_img_p, cond_img_p]
|
229 |
+
)
|
230 |
+
|
231 |
+
def clear():
|
232 |
+
return None, None
|
233 |
+
|
234 |
+
def clear_text():
|
235 |
+
return None, None, None
|
236 |
+
|
237 |
+
# clear_btn_e.click(clear, outputs=[cond_img_e, segm_img_e])
|
238 |
+
clear_btn_p.click(clear, outputs=[cond_img_p, segm_img_p])
|
239 |
+
|
240 |
+
demo.queue()
|
241 |
+
demo.launch()
|
assets/picture1.jpg
ADDED
assets/picture2.jpg
ADDED
assets/picture3.jpg
ADDED
assets/picture4.jpg
ADDED
assets/picture5.jpg
ADDED
assets/picture6.jpg
ADDED
repvit_sam.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fd2867cf669e6d89b1c91d0eb883d83ef4bcc590143dd2ca35e2705b21a4f2f
|
3 |
+
size 110032539
|
requirements.txt
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
torch
|
2 |
+
torchvision
|
3 |
+
timm
|
4 |
+
opencv-python
|
5 |
+
git+https://git@github.com/THU-RepViT/RepViT.git#subdirectory=sam
|
utils/__init__.py
ADDED
File without changes
|
utils/tools.py
ADDED
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import sys
|
3 |
+
|
4 |
+
import cv2
|
5 |
+
import matplotlib.pyplot as plt
|
6 |
+
import numpy as np
|
7 |
+
import torch
|
8 |
+
from PIL import Image
|
9 |
+
|
10 |
+
|
11 |
+
def convert_box_xywh_to_xyxy(box):
|
12 |
+
x1 = box[0]
|
13 |
+
y1 = box[1]
|
14 |
+
x2 = box[0] + box[2]
|
15 |
+
y2 = box[1] + box[3]
|
16 |
+
return [x1, y1, x2, y2]
|
17 |
+
|
18 |
+
|
19 |
+
def segment_image(image, bbox):
|
20 |
+
image_array = np.array(image)
|
21 |
+
segmented_image_array = np.zeros_like(image_array)
|
22 |
+
x1, y1, x2, y2 = bbox
|
23 |
+
segmented_image_array[y1:y2, x1:x2] = image_array[y1:y2, x1:x2]
|
24 |
+
segmented_image = Image.fromarray(segmented_image_array)
|
25 |
+
black_image = Image.new("RGB", image.size, (255, 255, 255))
|
26 |
+
# transparency_mask = np.zeros_like((), dtype=np.uint8)
|
27 |
+
transparency_mask = np.zeros(
|
28 |
+
(image_array.shape[0], image_array.shape[1]), dtype=np.uint8
|
29 |
+
)
|
30 |
+
transparency_mask[y1:y2, x1:x2] = 255
|
31 |
+
transparency_mask_image = Image.fromarray(transparency_mask, mode="L")
|
32 |
+
black_image.paste(segmented_image, mask=transparency_mask_image)
|
33 |
+
return black_image
|
34 |
+
|
35 |
+
|
36 |
+
def format_results(masks, scores, logits, filter=0):
|
37 |
+
annotations = []
|
38 |
+
n = len(scores)
|
39 |
+
for i in range(n):
|
40 |
+
annotation = {}
|
41 |
+
|
42 |
+
mask = masks[i]
|
43 |
+
tmp = np.where(mask != 0)
|
44 |
+
if np.sum(mask) < filter:
|
45 |
+
continue
|
46 |
+
annotation["id"] = i
|
47 |
+
annotation["segmentation"] = mask
|
48 |
+
annotation["bbox"] = [
|
49 |
+
np.min(tmp[0]),
|
50 |
+
np.min(tmp[1]),
|
51 |
+
np.max(tmp[1]),
|
52 |
+
np.max(tmp[0]),
|
53 |
+
]
|
54 |
+
annotation["score"] = scores[i]
|
55 |
+
annotation["area"] = annotation["segmentation"].sum()
|
56 |
+
annotations.append(annotation)
|
57 |
+
return annotations
|
58 |
+
|
59 |
+
|
60 |
+
def filter_masks(annotations): # filter the overlap mask
|
61 |
+
annotations.sort(key=lambda x: x["area"], reverse=True)
|
62 |
+
to_remove = set()
|
63 |
+
for i in range(0, len(annotations)):
|
64 |
+
a = annotations[i]
|
65 |
+
for j in range(i + 1, len(annotations)):
|
66 |
+
b = annotations[j]
|
67 |
+
if i != j and j not in to_remove:
|
68 |
+
# check if
|
69 |
+
if b["area"] < a["area"]:
|
70 |
+
if (a["segmentation"] & b["segmentation"]).sum() / b[
|
71 |
+
"segmentation"
|
72 |
+
].sum() > 0.8:
|
73 |
+
to_remove.add(j)
|
74 |
+
|
75 |
+
return [a for i, a in enumerate(annotations) if i not in to_remove], to_remove
|
76 |
+
|
77 |
+
|
78 |
+
def get_bbox_from_mask(mask):
|
79 |
+
mask = mask.astype(np.uint8)
|
80 |
+
contours, hierarchy = cv2.findContours(
|
81 |
+
mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
|
82 |
+
)
|
83 |
+
x1, y1, w, h = cv2.boundingRect(contours[0])
|
84 |
+
x2, y2 = x1 + w, y1 + h
|
85 |
+
if len(contours) > 1:
|
86 |
+
for b in contours:
|
87 |
+
x_t, y_t, w_t, h_t = cv2.boundingRect(b)
|
88 |
+
# 将多个bbox合并成一个
|
89 |
+
x1 = min(x1, x_t)
|
90 |
+
y1 = min(y1, y_t)
|
91 |
+
x2 = max(x2, x_t + w_t)
|
92 |
+
y2 = max(y2, y_t + h_t)
|
93 |
+
h = y2 - y1
|
94 |
+
w = x2 - x1
|
95 |
+
return [x1, y1, x2, y2]
|
96 |
+
|
97 |
+
|
98 |
+
def fast_process(
|
99 |
+
annotations, args, mask_random_color, bbox=None, points=None, edges=False
|
100 |
+
):
|
101 |
+
if isinstance(annotations[0], dict):
|
102 |
+
annotations = [annotation["segmentation"] for annotation in annotations]
|
103 |
+
result_name = os.path.basename(args.img_path)
|
104 |
+
image = cv2.imread(args.img_path)
|
105 |
+
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
106 |
+
original_h = image.shape[0]
|
107 |
+
original_w = image.shape[1]
|
108 |
+
if sys.platform == "darwin":
|
109 |
+
plt.switch_backend("TkAgg")
|
110 |
+
plt.figure(figsize=(original_w / 100, original_h / 100))
|
111 |
+
# Add subplot with no margin.
|
112 |
+
plt.subplots_adjust(top=1, bottom=0, right=1, left=0, hspace=0, wspace=0)
|
113 |
+
plt.margins(0, 0)
|
114 |
+
plt.gca().xaxis.set_major_locator(plt.NullLocator())
|
115 |
+
plt.gca().yaxis.set_major_locator(plt.NullLocator())
|
116 |
+
plt.imshow(image)
|
117 |
+
if args.better_quality == True:
|
118 |
+
if isinstance(annotations[0], torch.Tensor):
|
119 |
+
annotations = np.array(annotations.cpu())
|
120 |
+
for i, mask in enumerate(annotations):
|
121 |
+
mask = cv2.morphologyEx(
|
122 |
+
mask.astype(np.uint8), cv2.MORPH_CLOSE, np.ones((3, 3), np.uint8)
|
123 |
+
)
|
124 |
+
annotations[i] = cv2.morphologyEx(
|
125 |
+
mask.astype(np.uint8), cv2.MORPH_OPEN, np.ones((8, 8), np.uint8)
|
126 |
+
)
|
127 |
+
if args.device == "cpu":
|
128 |
+
annotations = np.array(annotations)
|
129 |
+
fast_show_mask(
|
130 |
+
annotations,
|
131 |
+
plt.gca(),
|
132 |
+
random_color=mask_random_color,
|
133 |
+
bbox=bbox,
|
134 |
+
points=points,
|
135 |
+
point_label=args.point_label,
|
136 |
+
retinamask=args.retina,
|
137 |
+
target_height=original_h,
|
138 |
+
target_width=original_w,
|
139 |
+
)
|
140 |
+
else:
|
141 |
+
if isinstance(annotations[0], np.ndarray):
|
142 |
+
annotations = torch.from_numpy(annotations)
|
143 |
+
fast_show_mask_gpu(
|
144 |
+
annotations,
|
145 |
+
plt.gca(),
|
146 |
+
random_color=args.randomcolor,
|
147 |
+
bbox=bbox,
|
148 |
+
points=points,
|
149 |
+
point_label=args.point_label,
|
150 |
+
retinamask=args.retina,
|
151 |
+
target_height=original_h,
|
152 |
+
target_width=original_w,
|
153 |
+
)
|
154 |
+
if isinstance(annotations, torch.Tensor):
|
155 |
+
annotations = annotations.cpu().numpy()
|
156 |
+
if args.withContours == True:
|
157 |
+
contour_all = []
|
158 |
+
temp = np.zeros((original_h, original_w, 1))
|
159 |
+
for i, mask in enumerate(annotations):
|
160 |
+
if type(mask) == dict:
|
161 |
+
mask = mask["segmentation"]
|
162 |
+
annotation = mask.astype(np.uint8)
|
163 |
+
if args.retina == False:
|
164 |
+
annotation = cv2.resize(
|
165 |
+
annotation,
|
166 |
+
(original_w, original_h),
|
167 |
+
interpolation=cv2.INTER_NEAREST,
|
168 |
+
)
|
169 |
+
contours, hierarchy = cv2.findContours(
|
170 |
+
annotation, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE
|
171 |
+
)
|
172 |
+
for contour in contours:
|
173 |
+
contour_all.append(contour)
|
174 |
+
cv2.drawContours(temp, contour_all, -1, (255, 255, 255), 2)
|
175 |
+
color = np.array([0 / 255, 0 / 255, 255 / 255, 0.8])
|
176 |
+
contour_mask = temp / 255 * color.reshape(1, 1, -1)
|
177 |
+
plt.imshow(contour_mask)
|
178 |
+
|
179 |
+
save_path = args.output
|
180 |
+
if not os.path.exists(save_path):
|
181 |
+
os.makedirs(save_path)
|
182 |
+
plt.axis("off")
|
183 |
+
fig = plt.gcf()
|
184 |
+
plt.draw()
|
185 |
+
|
186 |
+
try:
|
187 |
+
buf = fig.canvas.tostring_rgb()
|
188 |
+
except AttributeError:
|
189 |
+
fig.canvas.draw()
|
190 |
+
buf = fig.canvas.tostring_rgb()
|
191 |
+
|
192 |
+
cols, rows = fig.canvas.get_width_height()
|
193 |
+
img_array = np.fromstring(buf, dtype=np.uint8).reshape(rows, cols, 3)
|
194 |
+
cv2.imwrite(
|
195 |
+
os.path.join(save_path, result_name), cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR)
|
196 |
+
)
|
197 |
+
|
198 |
+
|
199 |
+
# CPU post process
|
200 |
+
def fast_show_mask(
|
201 |
+
annotation,
|
202 |
+
ax,
|
203 |
+
random_color=False,
|
204 |
+
bbox=None,
|
205 |
+
points=None,
|
206 |
+
point_label=None,
|
207 |
+
retinamask=True,
|
208 |
+
target_height=960,
|
209 |
+
target_width=960,
|
210 |
+
):
|
211 |
+
msak_sum = annotation.shape[0]
|
212 |
+
height = annotation.shape[1]
|
213 |
+
weight = annotation.shape[2]
|
214 |
+
# 将annotation 按照面积 排序
|
215 |
+
areas = np.sum(annotation, axis=(1, 2))
|
216 |
+
sorted_indices = np.argsort(areas)
|
217 |
+
annotation = annotation[sorted_indices]
|
218 |
+
|
219 |
+
index = (annotation != 0).argmax(axis=0)
|
220 |
+
if random_color == True:
|
221 |
+
color = np.random.random((msak_sum, 1, 1, 3))
|
222 |
+
else:
|
223 |
+
color = np.ones((msak_sum, 1, 1, 3)) * np.array(
|
224 |
+
[30 / 255, 144 / 255, 255 / 255]
|
225 |
+
)
|
226 |
+
transparency = np.ones((msak_sum, 1, 1, 1)) * 0.6
|
227 |
+
visual = np.concatenate([color, transparency], axis=-1)
|
228 |
+
mask_image = np.expand_dims(annotation, -1) * visual
|
229 |
+
|
230 |
+
show = np.zeros((height, weight, 4))
|
231 |
+
h_indices, w_indices = np.meshgrid(
|
232 |
+
np.arange(height), np.arange(weight), indexing="ij"
|
233 |
+
)
|
234 |
+
indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
|
235 |
+
# 使用向量化索引更新show的值
|
236 |
+
show[h_indices, w_indices, :] = mask_image[indices]
|
237 |
+
if bbox is not None:
|
238 |
+
x1, y1, x2, y2 = bbox
|
239 |
+
ax.add_patch(
|
240 |
+
plt.Rectangle(
|
241 |
+
(x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1
|
242 |
+
)
|
243 |
+
)
|
244 |
+
# draw point
|
245 |
+
if points is not None:
|
246 |
+
plt.scatter(
|
247 |
+
[point[0] for i, point in enumerate(points) if point_label[i] == 1],
|
248 |
+
[point[1] for i, point in enumerate(points) if point_label[i] == 1],
|
249 |
+
s=20,
|
250 |
+
c="y",
|
251 |
+
)
|
252 |
+
plt.scatter(
|
253 |
+
[point[0] for i, point in enumerate(points) if point_label[i] == 0],
|
254 |
+
[point[1] for i, point in enumerate(points) if point_label[i] == 0],
|
255 |
+
s=20,
|
256 |
+
c="m",
|
257 |
+
)
|
258 |
+
|
259 |
+
if retinamask == False:
|
260 |
+
show = cv2.resize(
|
261 |
+
show, (target_width, target_height), interpolation=cv2.INTER_NEAREST
|
262 |
+
)
|
263 |
+
ax.imshow(show)
|
264 |
+
|
265 |
+
|
266 |
+
def fast_show_mask_gpu(
|
267 |
+
annotation,
|
268 |
+
ax,
|
269 |
+
random_color=False,
|
270 |
+
bbox=None,
|
271 |
+
points=None,
|
272 |
+
point_label=None,
|
273 |
+
retinamask=True,
|
274 |
+
target_height=960,
|
275 |
+
target_width=960,
|
276 |
+
):
|
277 |
+
msak_sum = annotation.shape[0]
|
278 |
+
height = annotation.shape[1]
|
279 |
+
weight = annotation.shape[2]
|
280 |
+
areas = torch.sum(annotation, dim=(1, 2))
|
281 |
+
sorted_indices = torch.argsort(areas, descending=False)
|
282 |
+
annotation = annotation[sorted_indices]
|
283 |
+
# 找每个位置第一个非零值下标
|
284 |
+
index = (annotation != 0).to(torch.long).argmax(dim=0)
|
285 |
+
if random_color == True:
|
286 |
+
color = torch.rand((msak_sum, 1, 1, 3)).to(annotation.device)
|
287 |
+
else:
|
288 |
+
color = torch.ones((msak_sum, 1, 1, 3)).to(annotation.device) * torch.tensor(
|
289 |
+
[30 / 255, 144 / 255, 255 / 255]
|
290 |
+
).to(annotation.device)
|
291 |
+
transparency = torch.ones((msak_sum, 1, 1, 1)).to(annotation.device) * 0.6
|
292 |
+
visual = torch.cat([color, transparency], dim=-1)
|
293 |
+
mask_image = torch.unsqueeze(annotation, -1) * visual
|
294 |
+
# 按index取数,index指每个位置选哪个batch的数,把mask_image转成一个batch的形式
|
295 |
+
show = torch.zeros((height, weight, 4)).to(annotation.device)
|
296 |
+
h_indices, w_indices = torch.meshgrid(
|
297 |
+
torch.arange(height), torch.arange(weight), indexing="ij"
|
298 |
+
)
|
299 |
+
indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
|
300 |
+
# 使用向量化索引更新show的值
|
301 |
+
show[h_indices, w_indices, :] = mask_image[indices]
|
302 |
+
show_cpu = show.cpu().numpy()
|
303 |
+
if bbox is not None:
|
304 |
+
x1, y1, x2, y2 = bbox
|
305 |
+
ax.add_patch(
|
306 |
+
plt.Rectangle(
|
307 |
+
(x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1
|
308 |
+
)
|
309 |
+
)
|
310 |
+
# draw point
|
311 |
+
if points is not None:
|
312 |
+
plt.scatter(
|
313 |
+
[point[0] for i, point in enumerate(points) if point_label[i] == 1],
|
314 |
+
[point[1] for i, point in enumerate(points) if point_label[i] == 1],
|
315 |
+
s=20,
|
316 |
+
c="y",
|
317 |
+
)
|
318 |
+
plt.scatter(
|
319 |
+
[point[0] for i, point in enumerate(points) if point_label[i] == 0],
|
320 |
+
[point[1] for i, point in enumerate(points) if point_label[i] == 0],
|
321 |
+
s=20,
|
322 |
+
c="m",
|
323 |
+
)
|
324 |
+
if retinamask == False:
|
325 |
+
show_cpu = cv2.resize(
|
326 |
+
show_cpu, (target_width, target_height), interpolation=cv2.INTER_NEAREST
|
327 |
+
)
|
328 |
+
ax.imshow(show_cpu)
|
329 |
+
|
330 |
+
|
331 |
+
def crop_image(annotations, image_like):
|
332 |
+
if isinstance(image_like, str):
|
333 |
+
image = Image.open(image_like)
|
334 |
+
else:
|
335 |
+
image = image_like
|
336 |
+
ori_w, ori_h = image.size
|
337 |
+
mask_h, mask_w = annotations[0]["segmentation"].shape
|
338 |
+
if ori_w != mask_w or ori_h != mask_h:
|
339 |
+
image = image.resize((mask_w, mask_h))
|
340 |
+
cropped_boxes = []
|
341 |
+
cropped_images = []
|
342 |
+
not_crop = []
|
343 |
+
filter_id = []
|
344 |
+
# annotations, _ = filter_masks(annotations)
|
345 |
+
# filter_id = list(_)
|
346 |
+
for _, mask in enumerate(annotations):
|
347 |
+
if np.sum(mask["segmentation"]) <= 100:
|
348 |
+
filter_id.append(_)
|
349 |
+
continue
|
350 |
+
bbox = get_bbox_from_mask(mask["segmentation"]) # mask 的 bbox
|
351 |
+
cropped_boxes.append(segment_image(image, bbox)) # 保存裁剪的图片
|
352 |
+
# cropped_boxes.append(segment_image(image,mask["segmentation"]))
|
353 |
+
cropped_images.append(bbox) # 保存裁剪的图片的bbox
|
354 |
+
|
355 |
+
return cropped_boxes, cropped_images, not_crop, filter_id, annotations
|
356 |
+
|
357 |
+
|
358 |
+
def box_prompt(masks, bbox, target_height, target_width):
|
359 |
+
h = masks.shape[1]
|
360 |
+
w = masks.shape[2]
|
361 |
+
if h != target_height or w != target_width:
|
362 |
+
bbox = [
|
363 |
+
int(bbox[0] * w / target_width),
|
364 |
+
int(bbox[1] * h / target_height),
|
365 |
+
int(bbox[2] * w / target_width),
|
366 |
+
int(bbox[3] * h / target_height),
|
367 |
+
]
|
368 |
+
bbox[0] = round(bbox[0]) if round(bbox[0]) > 0 else 0
|
369 |
+
bbox[1] = round(bbox[1]) if round(bbox[1]) > 0 else 0
|
370 |
+
bbox[2] = round(bbox[2]) if round(bbox[2]) < w else w
|
371 |
+
bbox[3] = round(bbox[3]) if round(bbox[3]) < h else h
|
372 |
+
|
373 |
+
# IoUs = torch.zeros(len(masks), dtype=torch.float32)
|
374 |
+
bbox_area = (bbox[3] - bbox[1]) * (bbox[2] - bbox[0])
|
375 |
+
|
376 |
+
masks_area = torch.sum(masks[:, bbox[1] : bbox[3], bbox[0] : bbox[2]], dim=(1, 2))
|
377 |
+
orig_masks_area = torch.sum(masks, dim=(1, 2))
|
378 |
+
|
379 |
+
union = bbox_area + orig_masks_area - masks_area
|
380 |
+
IoUs = masks_area / union
|
381 |
+
max_iou_index = torch.argmax(IoUs)
|
382 |
+
|
383 |
+
return masks[max_iou_index].cpu().numpy(), max_iou_index
|
384 |
+
|
385 |
+
|
386 |
+
def point_prompt(masks, points, point_label, target_height, target_width): # numpy 处理
|
387 |
+
h = masks[0]["segmentation"].shape[0]
|
388 |
+
w = masks[0]["segmentation"].shape[1]
|
389 |
+
if h != target_height or w != target_width:
|
390 |
+
points = [
|
391 |
+
[int(point[0] * w / target_width), int(point[1] * h / target_height)]
|
392 |
+
for point in points
|
393 |
+
]
|
394 |
+
onemask = np.zeros((h, w))
|
395 |
+
for i, annotation in enumerate(masks):
|
396 |
+
if type(annotation) == dict:
|
397 |
+
mask = annotation["segmentation"]
|
398 |
+
else:
|
399 |
+
mask = annotation
|
400 |
+
for i, point in enumerate(points):
|
401 |
+
if mask[point[1], point[0]] == 1 and point_label[i] == 1:
|
402 |
+
onemask += mask
|
403 |
+
if mask[point[1], point[0]] == 1 and point_label[i] == 0:
|
404 |
+
onemask -= mask
|
405 |
+
onemask = onemask >= 1
|
406 |
+
return onemask, 0
|
utils/tools_gradio.py
ADDED
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
import matplotlib.pyplot as plt
|
3 |
+
import numpy as np
|
4 |
+
import torch
|
5 |
+
from PIL import Image
|
6 |
+
|
7 |
+
|
8 |
+
def fast_process(
|
9 |
+
annotations,
|
10 |
+
image,
|
11 |
+
device,
|
12 |
+
scale,
|
13 |
+
better_quality=False,
|
14 |
+
mask_random_color=True,
|
15 |
+
bbox=None,
|
16 |
+
use_retina=True,
|
17 |
+
withContours=True,
|
18 |
+
):
|
19 |
+
if isinstance(annotations[0], dict):
|
20 |
+
annotations = [annotation["segmentation"] for annotation in annotations]
|
21 |
+
|
22 |
+
original_h = image.height
|
23 |
+
original_w = image.width
|
24 |
+
if better_quality:
|
25 |
+
if isinstance(annotations[0], torch.Tensor):
|
26 |
+
annotations = np.array(annotations.cpu())
|
27 |
+
for i, mask in enumerate(annotations):
|
28 |
+
mask = cv2.morphologyEx(
|
29 |
+
mask.astype(np.uint8), cv2.MORPH_CLOSE, np.ones((3, 3), np.uint8)
|
30 |
+
)
|
31 |
+
annotations[i] = cv2.morphologyEx(
|
32 |
+
mask.astype(np.uint8), cv2.MORPH_OPEN, np.ones((8, 8), np.uint8)
|
33 |
+
)
|
34 |
+
if device == "cpu":
|
35 |
+
annotations = np.array(annotations)
|
36 |
+
inner_mask = fast_show_mask(
|
37 |
+
annotations,
|
38 |
+
plt.gca(),
|
39 |
+
random_color=mask_random_color,
|
40 |
+
bbox=bbox,
|
41 |
+
retinamask=use_retina,
|
42 |
+
target_height=original_h,
|
43 |
+
target_width=original_w,
|
44 |
+
)
|
45 |
+
else:
|
46 |
+
if isinstance(annotations[0], np.ndarray):
|
47 |
+
annotations = np.array(annotations)
|
48 |
+
annotations = torch.from_numpy(annotations)
|
49 |
+
inner_mask = fast_show_mask_gpu(
|
50 |
+
annotations,
|
51 |
+
plt.gca(),
|
52 |
+
random_color=mask_random_color,
|
53 |
+
bbox=bbox,
|
54 |
+
retinamask=use_retina,
|
55 |
+
target_height=original_h,
|
56 |
+
target_width=original_w,
|
57 |
+
)
|
58 |
+
if isinstance(annotations, torch.Tensor):
|
59 |
+
annotations = annotations.cpu().numpy()
|
60 |
+
|
61 |
+
if withContours:
|
62 |
+
contour_all = []
|
63 |
+
temp = np.zeros((original_h, original_w, 1))
|
64 |
+
for i, mask in enumerate(annotations):
|
65 |
+
if type(mask) == dict:
|
66 |
+
mask = mask["segmentation"]
|
67 |
+
annotation = mask.astype(np.uint8)
|
68 |
+
if use_retina == False:
|
69 |
+
annotation = cv2.resize(
|
70 |
+
annotation,
|
71 |
+
(original_w, original_h),
|
72 |
+
interpolation=cv2.INTER_NEAREST,
|
73 |
+
)
|
74 |
+
contours, _ = cv2.findContours(
|
75 |
+
annotation, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE
|
76 |
+
)
|
77 |
+
for contour in contours:
|
78 |
+
contour_all.append(contour)
|
79 |
+
cv2.drawContours(temp, contour_all, -1, (255, 255, 255), 2 // scale)
|
80 |
+
color = np.array([0 / 255, 0 / 255, 255 / 255, 0.9])
|
81 |
+
contour_mask = temp / 255 * color.reshape(1, 1, -1)
|
82 |
+
|
83 |
+
image = image.convert("RGBA")
|
84 |
+
overlay_inner = Image.fromarray((inner_mask * 255).astype(np.uint8), "RGBA")
|
85 |
+
image.paste(overlay_inner, (0, 0), overlay_inner)
|
86 |
+
|
87 |
+
if withContours:
|
88 |
+
overlay_contour = Image.fromarray((contour_mask * 255).astype(np.uint8), "RGBA")
|
89 |
+
image.paste(overlay_contour, (0, 0), overlay_contour)
|
90 |
+
|
91 |
+
return image
|
92 |
+
|
93 |
+
|
94 |
+
# CPU post process
|
95 |
+
def fast_show_mask(
|
96 |
+
annotation,
|
97 |
+
ax,
|
98 |
+
random_color=False,
|
99 |
+
bbox=None,
|
100 |
+
retinamask=True,
|
101 |
+
target_height=960,
|
102 |
+
target_width=960,
|
103 |
+
):
|
104 |
+
mask_sum = annotation.shape[0]
|
105 |
+
height = annotation.shape[1]
|
106 |
+
weight = annotation.shape[2]
|
107 |
+
# 将annotation 按照面积 排序
|
108 |
+
areas = np.sum(annotation, axis=(1, 2))
|
109 |
+
sorted_indices = np.argsort(areas)[::1]
|
110 |
+
annotation = annotation[sorted_indices]
|
111 |
+
|
112 |
+
index = (annotation != 0).argmax(axis=0)
|
113 |
+
if random_color == True:
|
114 |
+
color = np.random.random((mask_sum, 1, 1, 3))
|
115 |
+
else:
|
116 |
+
color = np.ones((mask_sum, 1, 1, 3)) * np.array(
|
117 |
+
[30 / 255, 144 / 255, 255 / 255]
|
118 |
+
)
|
119 |
+
transparency = np.ones((mask_sum, 1, 1, 1)) * 0.6
|
120 |
+
visual = np.concatenate([color, transparency], axis=-1)
|
121 |
+
mask_image = np.expand_dims(annotation, -1) * visual
|
122 |
+
|
123 |
+
mask = np.zeros((height, weight, 4))
|
124 |
+
|
125 |
+
h_indices, w_indices = np.meshgrid(
|
126 |
+
np.arange(height), np.arange(weight), indexing="ij"
|
127 |
+
)
|
128 |
+
indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
|
129 |
+
|
130 |
+
mask[h_indices, w_indices, :] = mask_image[indices]
|
131 |
+
if bbox is not None:
|
132 |
+
x1, y1, x2, y2 = bbox
|
133 |
+
ax.add_patch(
|
134 |
+
plt.Rectangle(
|
135 |
+
(x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1
|
136 |
+
)
|
137 |
+
)
|
138 |
+
|
139 |
+
if retinamask == False:
|
140 |
+
mask = cv2.resize(
|
141 |
+
mask, (target_width, target_height), interpolation=cv2.INTER_NEAREST
|
142 |
+
)
|
143 |
+
|
144 |
+
return mask
|
145 |
+
|
146 |
+
|
147 |
+
def fast_show_mask_gpu(
|
148 |
+
annotation,
|
149 |
+
ax,
|
150 |
+
random_color=False,
|
151 |
+
bbox=None,
|
152 |
+
retinamask=True,
|
153 |
+
target_height=960,
|
154 |
+
target_width=960,
|
155 |
+
):
|
156 |
+
device = annotation.device
|
157 |
+
mask_sum = annotation.shape[0]
|
158 |
+
height = annotation.shape[1]
|
159 |
+
weight = annotation.shape[2]
|
160 |
+
areas = torch.sum(annotation, dim=(1, 2))
|
161 |
+
sorted_indices = torch.argsort(areas, descending=False)
|
162 |
+
annotation = annotation[sorted_indices]
|
163 |
+
# 找每个位置第一个非零值下标
|
164 |
+
index = (annotation != 0).to(torch.long).argmax(dim=0)
|
165 |
+
if random_color == True:
|
166 |
+
color = torch.rand((mask_sum, 1, 1, 3)).to(device)
|
167 |
+
else:
|
168 |
+
color = torch.ones((mask_sum, 1, 1, 3)).to(device) * torch.tensor(
|
169 |
+
[30 / 255, 144 / 255, 255 / 255]
|
170 |
+
).to(device)
|
171 |
+
transparency = torch.ones((mask_sum, 1, 1, 1)).to(device) * 0.6
|
172 |
+
visual = torch.cat([color, transparency], dim=-1)
|
173 |
+
mask_image = torch.unsqueeze(annotation, -1) * visual
|
174 |
+
# 按index取数,index指每个位置选哪个batch的数,把mask_image转成一个batch的形式
|
175 |
+
mask = torch.zeros((height, weight, 4)).to(device)
|
176 |
+
h_indices, w_indices = torch.meshgrid(torch.arange(height), torch.arange(weight))
|
177 |
+
indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
|
178 |
+
# 使用向量化索引更新show的值
|
179 |
+
mask[h_indices, w_indices, :] = mask_image[indices]
|
180 |
+
mask_cpu = mask.cpu().numpy()
|
181 |
+
if bbox is not None:
|
182 |
+
x1, y1, x2, y2 = bbox
|
183 |
+
ax.add_patch(
|
184 |
+
plt.Rectangle(
|
185 |
+
(x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1
|
186 |
+
)
|
187 |
+
)
|
188 |
+
if retinamask == False:
|
189 |
+
mask_cpu = cv2.resize(
|
190 |
+
mask_cpu, (target_width, target_height), interpolation=cv2.INTER_NEAREST
|
191 |
+
)
|
192 |
+
return mask_cpu
|