Update README.md

README.md

@@ -28,8 +28,61 @@ The model is designed to produce **pixel-perfect alpha mattes**, handling fine d
 - **Input**: RGB image tensor `(B, 3, H, W)`
 - **Output**: `(semantic, detail, matte)` predictions
 
-This model uses a **custom architecture** and requires loading with:
+## How to Load the Model
 
 ```python
-trust_remote_code=True
+from transformers import AutoModel
+
+model = AutoModel.from_pretrained(
+    "boopathiraj/MODNet",
+    trust_remote_code=True
+)
+
+model.eval()
+```
+
+## Example Inference
+
+```python
+
+import torch
+import cv2
+import numpy as np
+from PIL import Image
+from torchvision import transforms
+
+# Preprocess
+def preprocess(image_path, ref_size=512):
+    image = Image.open(image_path).convert("RGB")
+    w, h = image.size
+
+    scale = ref_size / max(h, w)
+    new_w, new_h = int(w * scale), int(h * scale)
+    image_resized = image.resize((new_w, new_h), Image.BILINEAR)
+
+    transform = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.5, 0.5, 0.5],
+                             std=[0.5, 0.5, 0.5])
+    ])
+
+    tensor = transform(image_resized).unsqueeze(0)
+    return tensor, (w, h)
+
+# Run inference
+inp, original_size = preprocess("input.jpg")
+
+with torch.no_grad():
+    semantic, detail, matte = model(inp, True)
+
+matte = matte[0, 0].cpu().numpy()
+matte = cv2.resize(matte, original_size)
+
+# Save alpha matte
+matte = (matte * 255).astype(np.uint8)
+Image.fromarray(matte).save("alpha_matte.png")
+
+```
+
+
 ---