SAM3Test / app.py
Studentepercaso's picture
Update app.py
9d1a051 verified
Raw History Blame Contribute Delete
2.69 kB
import gradio as gr
import torch
from transformers import Sam3Processor, Sam3Model
from PIL import Image
import numpy as np
import matplotlib
# Scegli il device
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using device:", device)
# Carichiamo modello e processor UNA SOLA VOLTA (global)
model = Sam3Model.from_pretrained("facebook/sam3").to(device)
processor = Sam3Processor.from_pretrained("facebook/sam3")
def overlay_masks(image: Image.Image, masks: torch.Tensor) -> Image.Image:
"""Applica le maschere colorate sopra l'immagine."""
image = image.convert("RGBA")
masks_np = 255 * masks.cpu().numpy().astype(np.uint8)
n_masks = masks_np.shape[0]
if n_masks == 0:
return image
cmap = matplotlib.colormaps.get_cmap("rainbow").resampled(n_masks)
colors = [
tuple(int(c * 255) for c in cmap(i)[:3])
for i in range(n_masks)
]
for mask, color in zip(masks_np, colors):
mask_img = Image.fromarray(mask)
overlay = Image.new("RGBA", image.size, color + (0,))
# 0.4 = trasparenza 40%
alpha = mask_img.point(lambda v: int(v * 0.4))
overlay.putalpha(alpha)
image = Image.alpha_composite(image, overlay)
return image
def segment(image, text_prompt):
"""Funzione chiamata da Gradio: prende immagine + testo e ritorna immagine con maschere."""
if image is None or not text_prompt:
return image
# Pre-process
inputs = processor(
images=image,
text=text_prompt,
return_tensors="pt"
).to(device)
# Forward
with torch.no_grad():
outputs = model(**inputs)
# Post-process: maschere alla risoluzione originale
results = processor.post_process_instance_segmentation(
outputs,
threshold=0.5,
mask_threshold=0.5,
target_sizes=inputs["original_sizes"].tolist()
)[0]
masks = results["masks"] # [N, H, W]
print("Found", len(masks), "objects for prompt:", text_prompt)
if len(masks) == 0:
# Nessun oggetto trovato → ritorno immagine originale
return image
# Applica overlay
out_img = overlay_masks(image, masks)
return out_img
# Interfaccia Gradio
demo = gr.Interface(
fn=segment,
inputs=[
gr.Image(type="pil", label="Immagine"),
gr.Textbox(label="Prompt (es. 'cat', 'dog', 'ear')", value="cat"),
],
outputs=gr.Image(type="pil", label="Risultato"),
title="SAM3 – Promptable Concept Segmentation",
description="Carica un'immagine, scrivi un concetto (es. 'cat', 'dog', 'ear') e SAM3 segmenterà tutte le istanze trovate."
)
if __name__ == "__main__":
demo.launch()