Studentepercaso commited on
Commit
9d1a051
·
verified ·
1 Parent(s): d9ddb7d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +89 -4
app.py CHANGED
@@ -1,7 +1,92 @@
1
  import gradio as gr
 
 
 
 
 
2
 
3
- def greet(name):
4
- return "Hello " + name + "!!"
 
5
 
6
- demo = gr.Interface(fn=greet, inputs="text", outputs="text")
7
- demo.launch()
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  import gradio as gr
2
+ import torch
3
+ from transformers import Sam3Processor, Sam3Model
4
+ from PIL import Image
5
+ import numpy as np
6
+ import matplotlib
7
 
8
+ # Scegli il device
9
+ device = "cuda" if torch.cuda.is_available() else "cpu"
10
+ print("Using device:", device)
11
 
12
+ # Carichiamo modello e processor UNA SOLA VOLTA (global)
13
+ model = Sam3Model.from_pretrained("facebook/sam3").to(device)
14
+ processor = Sam3Processor.from_pretrained("facebook/sam3")
15
+
16
+
17
+ def overlay_masks(image: Image.Image, masks: torch.Tensor) -> Image.Image:
18
+ """Applica le maschere colorate sopra l'immagine."""
19
+ image = image.convert("RGBA")
20
+ masks_np = 255 * masks.cpu().numpy().astype(np.uint8)
21
+
22
+ n_masks = masks_np.shape[0]
23
+ if n_masks == 0:
24
+ return image
25
+
26
+ cmap = matplotlib.colormaps.get_cmap("rainbow").resampled(n_masks)
27
+ colors = [
28
+ tuple(int(c * 255) for c in cmap(i)[:3])
29
+ for i in range(n_masks)
30
+ ]
31
+
32
+ for mask, color in zip(masks_np, colors):
33
+ mask_img = Image.fromarray(mask)
34
+ overlay = Image.new("RGBA", image.size, color + (0,))
35
+ # 0.4 = trasparenza 40%
36
+ alpha = mask_img.point(lambda v: int(v * 0.4))
37
+ overlay.putalpha(alpha)
38
+ image = Image.alpha_composite(image, overlay)
39
+
40
+ return image
41
+
42
+
43
+ def segment(image, text_prompt):
44
+ """Funzione chiamata da Gradio: prende immagine + testo e ritorna immagine con maschere."""
45
+ if image is None or not text_prompt:
46
+ return image
47
+
48
+ # Pre-process
49
+ inputs = processor(
50
+ images=image,
51
+ text=text_prompt,
52
+ return_tensors="pt"
53
+ ).to(device)
54
+
55
+ # Forward
56
+ with torch.no_grad():
57
+ outputs = model(**inputs)
58
+
59
+ # Post-process: maschere alla risoluzione originale
60
+ results = processor.post_process_instance_segmentation(
61
+ outputs,
62
+ threshold=0.5,
63
+ mask_threshold=0.5,
64
+ target_sizes=inputs["original_sizes"].tolist()
65
+ )[0]
66
+
67
+ masks = results["masks"] # [N, H, W]
68
+ print("Found", len(masks), "objects for prompt:", text_prompt)
69
+
70
+ if len(masks) == 0:
71
+ # Nessun oggetto trovato → ritorno immagine originale
72
+ return image
73
+
74
+ # Applica overlay
75
+ out_img = overlay_masks(image, masks)
76
+ return out_img
77
+
78
+
79
+ # Interfaccia Gradio
80
+ demo = gr.Interface(
81
+ fn=segment,
82
+ inputs=[
83
+ gr.Image(type="pil", label="Immagine"),
84
+ gr.Textbox(label="Prompt (es. 'cat', 'dog', 'ear')", value="cat"),
85
+ ],
86
+ outputs=gr.Image(type="pil", label="Risultato"),
87
+ title="SAM3 – Promptable Concept Segmentation",
88
+ description="Carica un'immagine, scrivi un concetto (es. 'cat', 'dog', 'ear') e SAM3 segmenterà tutte le istanze trovate."
89
+ )
90
+
91
+ if __name__ == "__main__":
92
+ demo.launch()