File size: 1,978 Bytes
e8aa256
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import numpy as np
import torch
import matplotlib.pyplot as plt
import cv2
import sys
sys.path.append("..")
from segment_anything import sam_model_registry, SamPredictor

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_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_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))    
    


sam_checkpoint = "./script/sam_vit_h_4b8939.pth"
model_type = "vit_h"
device = "cuda"
sam = sam_model_registry[model_type](checkpoint=sam_checkpoint)
sam.to(device=device)

predictor = SamPredictor(sam)

save_path = "./validation_demo/Demo/fish/"
image = cv2.imread("./validation_demo/Demo/fish/demo.jpg")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# image = cv2.resize(image,(512,256))
predictor.set_image(image)


input_point = np.array([[714,250]])
input_label = np.array([1])

masks, scores, logits = predictor.predict(
    point_coords=input_point,
    point_labels=input_label,
    multimask_output=True,
)

for i, (mask, score) in enumerate(zip(masks, scores)):
    h, w = mask.shape[-2:] 
#     mask = (mask.reshape(h, w, 1) !=10) * 255
    mask = mask.reshape(h, w, 1) * 255
    
    cv2.imwrite(save_path+str(i)+"_fish2.jpg",mask)
    print(masks.shape)
    print(score)