-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
241 lines (195 loc) · 7.51 KB
/
utils.py
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
import matplotlib.pyplot as plt
import numpy as np
import random
from PIL import Image
import torch
def resize_image(image, 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))
return image
def format_results(result, filter=0):
annotations = []
n = len(result.masks.data)
for i in range(n):
annotation = {}
mask = result.masks.data[i] == 1.0
if torch.sum(mask) < filter:
continue
annotation["id"] = i
annotation["segmentation"] = mask.cpu().numpy()
annotation["bbox"] = result.boxes.data[i]
annotation["score"] = result.boxes.conf[i]
annotation["area"] = annotation["segmentation"].sum()
annotations.append(annotation)
return annotations
def box_prompt(masks, bbox):
h = masks.shape[1]
w = masks.shape[2]
bbox[0] = round(bbox[0]) if round(bbox[0]) > 0 else 0
bbox[1] = round(bbox[1]) if round(bbox[1]) > 0 else 0
bbox[2] = round(bbox[2]) if round(bbox[2]) < w else w
bbox[3] = round(bbox[3]) if round(bbox[3]) < h else h
# IoUs = torch.zeros(len(masks), dtype=torch.float32)
bbox_area = (bbox[3] - bbox[1]) * (bbox[2] - bbox[0])
masks_area = torch.sum(masks[:, bbox[1] : bbox[3], bbox[0] : bbox[2]], dim=(1, 2))
orig_masks_area = torch.sum(masks, dim=(1, 2))
union = bbox_area + orig_masks_area - masks_area
IoUs = masks_area / union
max_iou_index = torch.argmax(IoUs)
return masks[max_iou_index].cpu().numpy(), max_iou_index
def point_prompt(masks, points, point_label): # numpy 处理
h = masks[0]["segmentation"].shape[0]
w = masks[0]["segmentation"].shape[1]
onemask = np.zeros((h, w))
masks = sorted(masks, key=lambda x: x['area'], reverse=True)
for i, annotation in enumerate(masks):
if type(annotation) == dict:
mask = annotation['segmentation']
else:
mask = annotation
for i, point in enumerate(points):
if mask[point[1], point[0]] == 1 and point_label[i] == 1:
onemask[mask] = 1
if mask[point[1], point[0]] == 1 and point_label[i] == 0:
onemask[mask] = 0
onemask = onemask >= 1
return onemask, 0
def show_masks_on_image(image, masks):
# Create a mask image (assuming binary mask)
#image_with_mask = Image.open(image_path).convert("RGBA")
image_with_mask = image.convert("RGBA")
for mask in masks:
#mask = mask.cpu().numpy()
height, width = mask.shape
mask_array = np.zeros((height, width, 4), dtype=np.uint8)
color = [random.randint(0, 255), random.randint(0, 255), random.randint(0, 255), 150]
mask_array[mask, :] = color
mask_image = Image.fromarray(mask_array)
width, height = image_with_mask.size
mask_image = mask_image.resize((width, height))
# Overlay the mask on the image
image_with_mask = Image.alpha_composite(
image_with_mask,
mask_image)
# Display the result
image_with_mask.show()
def show_box(box, ax):
x0, y0 = box[0], box[1]
w, h = box[2] - box[0], box[3] - box[1]
ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))
def show_boxes_on_image(raw_image, boxes):
plt.figure(figsize=(10,10))
plt.imshow(raw_image)
for box in boxes:
show_box(box, plt.gca())
plt.axis('on')
plt.show()
def show_points_on_image(raw_image, input_points, input_labels=None):
plt.figure(figsize=(10,10))
plt.imshow(raw_image)
input_points = np.array(input_points)
if input_labels is None:
labels = np.ones_like(input_points[:, 0])
else:
labels = np.array(input_labels)
show_points(input_points, labels, plt.gca())
plt.axis('on')
plt.show()
import matplotlib.pyplot as plt
import numpy as np
def show_mask(mask, ax, random_color=False):
if random_color:
color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
else:
color = np.array([30/255, 144/255, 255/255, 0.6])
h, w = mask.shape[-2:]
mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
ax.imshow(mask_image)
def show_box(box, ax):
x0, y0 = box[0], box[1]
w, h = box[2] - box[0], box[3] - box[1]
ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))
def show_boxes_on_image(raw_image, boxes):
plt.figure(figsize=(10,10))
plt.imshow(raw_image)
for box in boxes:
show_box(box, plt.gca())
plt.axis('on')
plt.show()
def show_points_on_image(raw_image, input_points, input_labels=None):
plt.figure(figsize=(10,10))
plt.imshow(raw_image)
input_points = np.array(input_points)
if input_labels is None:
labels = np.ones_like(input_points[:, 0])
else:
labels = np.array(input_labels)
show_points(input_points, labels, plt.gca())
plt.axis('on')
plt.show()
def show_points_and_boxes_on_image(raw_image, boxes, input_points, input_labels=None):
plt.figure(figsize=(10,10))
plt.imshow(raw_image)
input_points = np.array(input_points)
if input_labels is None:
labels = np.ones_like(input_points[:, 0])
else:
labels = np.array(input_labels)
show_points(input_points, labels, plt.gca())
for box in boxes:
show_box(box, plt.gca())
plt.axis('on')
plt.show()
def show_points_and_boxes_on_image(raw_image, boxes, input_points, input_labels=None):
plt.figure(figsize=(10,10))
plt.imshow(raw_image)
input_points = np.array(input_points)
if input_labels is None:
labels = np.ones_like(input_points[:, 0])
else:
labels = np.array(input_labels)
show_points(input_points, labels, plt.gca())
for box in boxes:
show_box(box, plt.gca())
plt.axis('on')
plt.show()
def show_points(coords, labels, ax, marker_size=375):
pos_points = coords[labels==1]
neg_points = coords[labels==0]
ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
def show_masks_on_image(image, masks):
# Create a mask image (assuming binary mask)
#image_with_mask = Image.open(image_path).convert("RGBA")
image_with_mask = image.convert("RGBA")
for mask in masks:
#mask = mask.cpu().numpy()
height, width = mask.shape
mask_array = np.zeros((height, width, 4), dtype=np.uint8)
color = [random.randint(0, 255), random.randint(0, 255), random.randint(0, 255), 150]
mask_array[mask, :] = color
mask_image = Image.fromarray(mask_array)
width, height = image_with_mask.size
mask_image = mask_image.resize((width, height))
# Overlay the mask on the image
image_with_mask = Image.alpha_composite(
image_with_mask,
mask_image)
# Display the result
return image_with_mask
def show_binary_mask(masks, scores):
if len(masks.shape) == 4:
masks = masks.squeeze()
if scores.shape[0] == 1:
scores = scores.squeeze()
fig, ax = plt.subplots(figsize=(15, 15))
idx = scores.tolist().index(max(scores))
mask = masks[idx].cpu().detach()
ax.imshow(np.array(masks[0,:,:]), cmap='gray')
score = scores[idx]
ax.title.set_text(f"Score: {score.item():.3f}")
ax.axis("off")
plt.show()