Update app.py

app.py

@@ -1,74 +1,18 @@
-import gradio as gr
-from loadimg import load_img
-from transformers import AutoModelForImageSegmentation
-import torch
-from torchvision import transforms
-from typing import Union, Tuple
+from transformers import AutoProcessor, AutoModelForImageSegmentation
 from PIL import Image
+import torch
 
-torch.set_float32_matmul_precision("high")
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-birefnet = AutoModelForImageSegmentation.from_pretrained(
-    "ZhengPeng7/BiRefNet", trust_remote_code=True
-)
-birefnet.to(device)
-
-transform_image = transforms.Compose([
-    transforms.Resize((1024, 1024)),
-    transforms.ToTensor(),
-    transforms.Normalize([0.485, 0.456, 0.406],
-                         [0.229, 0.224, 0.225]),
-])
-
-def process(image: Image.Image) -> Image.Image:
-    image_size = image.size
-    input_images = transform_image(image).unsqueeze(0).to(device)
-    with torch.no_grad():
-        preds = birefnet(input_images)[-1].sigmoid().cpu()
-    pred = preds[0].squeeze()
-    pred_pil = transforms.ToPILImage()(pred)
-    mask = pred_pil.resize(image_size)
-    image.putalpha(mask)
-    return image
-
-def fn(image: Union[Image.Image, str]) -> Tuple[Image.Image, Image.Image]:
-    im = load_img(image, output_type="pil").convert("RGB")
-    origin = im.copy()
-    processed_image = process(im)
-    return processed_image, origin
-
-def process_file(f: str) -> str:
-    name_path = f.rsplit(".", 1)[0] + ".png"
-    im = load_img(f, output_type="pil").convert("RGB")
-    transparent = process(im)
-    transparent.save(name_path)
-    return name_path
-
-slider1 = gr.ImageSlider(label="Processed Image", type="pil", format="png")
-slider2 = gr.ImageSlider(label="Processed Image from URL", type="pil", format="png")
-image_upload = gr.Image(label="Upload an image")
-image_file_upload = gr.Image(label="Upload an image", type="filepath")
-url_input = gr.Textbox(label="Paste an image URL")
-output_file = gr.File(label="Output PNG File")
-
-chameleon = load_img("butterfly.jpg", output_type="pil")
-url_example = "https://hips.hearstapps.com/hmg-prod/images/gettyimages-1229892983-square.jpg"
+# Carica modello e processor
+processor = AutoProcessor.from_pretrained("BritishWerewolf/U-2-Netp")
+model     = AutoModelForImageSegmentation.from_pretrained("BritishWerewolf/U-2-Netp")
 
-tab1 = gr.Interface(fn, inputs=image_upload, outputs=slider1,
-                   examples=[chameleon], api_name="image")
-tab2 = gr.Interface(fn, inputs=url_input, outputs=slider2,
-                   examples=[url_example], api_name="text")
-tab3 = gr.Interface(process_file, inputs=image_file_upload,
-                   outputs=output_file, examples=["butterfly.jpg"],
-                   api_name="png")
+# Prepara l’immagine
+img = Image.open("input.jpg").convert("RGB")
+inputs = processor(images=img, return_tensors="pt")
 
-demo = gr.TabbedInterface(
-    [tab1, tab2, tab3],
-    ["Image Upload", "URL Input", "File Output"],
-    title="Background Removal Tool"
-)
+# Inferenzia maschera
+with torch.no_grad():
+    outputs = model(**inputs)
+    mask = outputs.logits.argmax(dim=1)[0].cpu().numpy()
 
-if __name__ == "__main__":
-    demo.launch(show_error=True, server_name="0.0.0.0", server_port=7860)
+# Applica maschera all’immagine originale...