File size: 2,304 Bytes
dfdcd97
a3ee867
e9cd6fd
 
c95f3e0
9a34a8b
 
 
 
e0d4d2f
c95f3e0
 
 
9a34a8b
 
3cd1243
9a34a8b
 
 
 
 
 
e0d4d2f
4f39124
 
 
 
72f4c5c
4f39124
 
 
 
72f4c5c
4f39124
 
 
72f4c5c
4f39124
73989e5
 
 
 
 
26c0f04
4f39124
 
26c0f04
9a34a8b
 
3cd1243
4f39124
 
2dd8fe8
9a34a8b
4f39124
73989e5
4f39124
3ba1061
73989e5
 
e0d4d2f
e9cd6fd
 
4f39124
e9cd6fd
4f39124
e9cd6fd
3ba1061
9a34a8b
3ba1061
 
4f39124
 
e0d4d2f
 
e9cd6fd
 
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
import gradio as gr
import torch
import cv2
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import io
from ultralytics import FastSAM
from ultralytics.models.fastsam import FastSAMPrompt

# Set up device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load FastSAM model
model = FastSAM("FastSAM-s.pt")  # or FastSAM-x.pt

def fig2img(fig):
    buf = io.BytesIO()
    fig.savefig(buf)
    buf.seek(0)
    img = Image.open(buf)
    return img

def plot_masks(annotations, output_shape):
    fig, ax = plt.subplots(figsize=(10, 10))
    ax.imshow(annotations[0].orig_img)
    
    for ann in annotations:
        for mask in ann.masks.data:
            mask = cv2.resize(mask.cpu().numpy().astype('uint8'), output_shape[::-1])
            masked = np.ma.masked_where(mask == 0, mask)
            ax.imshow(masked, alpha=0.5, cmap=plt.cm.get_cmap('jet'))

    ax.axis('off')
    plt.close()
    return fig2img(fig)

def segment_everything(input_image):
    try:
        if input_image is None:
            return None, "Please upload an image before submitting."
        
        input_image = Image.fromarray(input_image).convert("RGB")
        
        # Run FastSAM model in "everything" mode
        everything_results = model(input_image, device=device, retina_masks=True, imgsz=1024, conf=0.25, iou=0.9, agnostic_nms=True)
        
        # Prepare a Prompt Process object
        prompt_process = FastSAMPrompt(input_image, everything_results, device=device)
        
        # Get everything segmentation
        ann = prompt_process.everything_prompt()
        
        # Plot the results
        result_image = plot_masks(ann, input_image.size)
        
        return result_image, f"Segmented everything in the image. Found {len(ann[0].masks)} objects."
    
    except Exception as e:
        return None, f"An error occurred: {str(e)}"

# Create Gradio interface
iface = gr.Interface(
    fn=segment_everything,
    inputs=[
        gr.Image(type="numpy", label="Upload an image")
    ],
    outputs=[
        gr.Image(type="pil", label="Segmented Image"),
        gr.Textbox(label="Status")
    ],
    title="FastSAM Everything Segmentation",
    description="Upload an image to segment all objects using FastSAM."
)

# Launch the interface
iface.launch()