Update README.md

README.md

@@ -9,4 +9,92 @@ library_name: transformers
 tags:
 - text-generation-inference
 - mobile-gui-detection
----
+---
+
+## Quick Start with Transformers
+
+```
+pip install torch==2.8.0 --index-url https://download.pytorch.org/whl/cu128
+pip install torchvision==0.23.0 transformers==5.9.0 accelerate gradio==6.19.0
+```
+
+```py
+import gradio as gr
+import torch
+from PIL import Image, ImageDraw
+
+from transformers import AutoImageProcessor, RfDetrForObjectDetection
+
+# Load model and processor
+model_name = "prithivMLmods/rf-detr-mobile-gui-detection"
+
+processor = AutoImageProcessor.from_pretrained(model_name)
+model = RfDetrForObjectDetection.from_pretrained(model_name)
+
+# Detection threshold
+THRESHOLD = 0.35
+
+
+def detect_gui(image):
+    image = Image.fromarray(image).convert("RGB")
+
+    inputs = processor(images=image, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    target_sizes = torch.tensor([image.size[::-1]])
+    results = processor.post_process_object_detection(
+        outputs,
+        target_sizes=target_sizes,
+        threshold=THRESHOLD,
+    )[0]
+
+    draw = ImageDraw.Draw(image)
+
+    detections = []
+
+    for score, label, box in zip(
+        results["scores"],
+        results["labels"],
+        results["boxes"],
+    ):
+        box = [round(x, 2) for x in box.tolist()]
+        label_name = model.config.id2label[label.item()]
+        confidence = round(score.item(), 3)
+
+        # Draw bounding box
+        draw.rectangle(box, outline="red", width=3)
+
+        # Draw label
+        draw.text(
+            (box[0] + 4, max(0, box[1] - 16)),
+            f"{label_name} {confidence:.2f}",
+            fill="red",
+        )
+
+        detections.append(
+            {
+                "Label": label_name,
+                "Confidence": confidence,
+                "Bounding Box": box,
+            }
+        )
+
+    return image, detections
+
+
+demo = gr.Interface(
+    fn=detect_gui,
+    inputs=gr.Image(type="numpy", label="Upload Mobile UI Screenshot"),
+    outputs=[
+        gr.Image(type="pil", label="Detected GUI Elements"),
+        gr.JSON(label="Detections"),
+    ],
+    title="RF-DETR Mobile GUI Detection",
+    description="Upload a mobile UI screenshot to detect GUI elements using RF-DETR.",
+)
+
+if __name__ == "__main__":
+    demo.launch()
+```