Delete u2net_utils.py

u2net_utils.py

@@ -1,59 +0,0 @@
-
-import os
-import torch
-import requests
-from PIL import Image
-import numpy as np
-from torchvision import transforms
-from model.u2net import U2NET
-
-MODEL_DIR = "model"
-MODEL_NAME = "u2net.pth"
-MODEL_PATH = 'model/u2net.pth'
-MODEL_URL = "https://huggingface.co/blurred-png/u2net-pth/resolve/main/u2net.pth"
-
-def download_model():
-    if not os.path.exists(MODEL_PATH):
-        print("Downloading model from Hugging Face...")
-        os.makedirs(MODEL_DIR, exist_ok=True)
-        r = requests.get(MODEL_URL, stream=True)
-        with open(MODEL_PATH, "wb") as f:
-            for chunk in r.iter_content(chunk_size=8192):
-                if chunk:
-                    f.write(chunk)
-        print("Download complete.")
-
-def load_model():
-    download_model()
-    net = U2NET(3, 1)
-    net.load_state_dict(torch.load(MODEL_PATH, map_location="cpu", weights_only=False))
-    net.eval()
-    return net
-
-model = load_model()
-
-def preprocess(image):
-    transform = transforms.Compose([
-        transforms.Resize((320, 320)),
-        transforms.ToTensor(),
-        transforms.Normalize(mean=[0.485, 0.456, 0.406],
-                             std=[0.229, 0.224, 0.225])
-    ])
-    return transform(image).unsqueeze(0)
-
-def postprocess(mask, original_size):
-    mask = mask.squeeze().cpu().data.numpy()
-    mask = (mask - mask.min()) / (mask.max() - mask.min())
-    mask = Image.fromarray((mask * 255).astype(np.uint8)).resize(original_size, Image.BILINEAR)
-    return mask
-
-def remove_background(image):
-    original_size = image.size
-    tensor = preprocess(image)
-    with torch.no_grad():
-        d = model(tensor)[0][:, 0, :, :]
-    mask = postprocess(d, original_size)
-    image = image.convert("RGBA")
-    r, g, b, _ = image.split()
-    merged = Image.merge("RGBA", (r, g, b, mask))
-    return merged