Create app.py

app.py

@@ -0,0 +1,142 @@
+import spaces
+import supervision as sv
+import PIL.Image as Image
+from ultralytics import YOLO
+import gradio as gr
+import torch
+
+
+
+model_filenames = [
+    "yolo11n.pt", 
+    "yolo11s.pt",
+    "yolo11m.pt", 
+    "yolo11l.pt", 
+    "yolo11x.pt"
+]
+
+
+
+box_annotator = sv.BoxAnnotator()
+category_dict = {0: 'A', 1: 'B', 2: 'C', 3: 'D', 4: 'E', 5: 'F', 6: 'G', 7: 'H', 8: 'I',
+                 9: 'J', 10: 'K', 11: 'L', 12: 'M', 13: 'N', 14: 'O', 15: 'P', 16: 'Q',
+                 17: 'R', 18: 'S', 19: 'T', 20: 'U', 21: 'V', 22: 'W', 23: 'X', 24: 'Y', 25: 'Z'}
+
+
+
+@spaces.GPU
+def yolo_inference(image, model_id, conf_threshold, iou_threshold, max_detection):
+    # Download models
+
+    
+    model = YOLO(model_id)
+    results = model(source=image, imgsz=640, iou=iou_threshold, conf=conf_threshold, verbose=False, max_det=max_detection)[0]
+    detections = sv.Detections.from_ultralytics(results)
+    
+    labels = [
+        f"{category_dict[class_id]} {confidence:.2f}"
+        for class_id, confidence in zip(detections.class_id, detections.confidence)
+    ]
+    annotated_image = box_annotator.annotate(image, detections=detections, labels=labels)
+
+    return annotated_image
+
+def app():
+    with gr.Blocks():
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image(type="pil", label="Image", interactive=True)
+    
+                model_id = gr.Dropdown(
+                    label="Model",
+                    choices=model_filenames,
+                    value=model_filenames[0] if model_filenames else "",
+                )
+                conf_threshold = gr.Slider(
+                    label="Confidence Threshold",
+                    minimum=0.1,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.25,
+                )
+                iou_threshold = gr.Slider(
+                    label="IoU Threshold",
+                    minimum=0.1,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.45,
+                )
+                
+                max_detection = gr.Slider(
+                    label="Max Detection",
+                    minimum=1,
+                    step=1,
+                    value=1,
+                )
+                yolov_infer = gr.Button(value="Detect Objects")
+
+            with gr.Column():
+                output_image = gr.Image(type="pil", label="Annotated Image", interactive=False)
+
+        yolov_infer.click(
+            fn=yolo_inference,
+            inputs=[
+                image,
+                model_id,
+                conf_threshold,
+                iou_threshold,
+                max_detection,
+            ],
+            outputs=[output_image],
+        )
+
+        gr.Examples(
+            examples=[
+                [
+                    "zidane.jpg",
+                    "yolov11x.pt",
+                    0.25,
+                    0.45,
+                    1,
+                ],
+                
+                [
+                    "bus.jpg",
+                    "yolov11s.pt",
+                    0.25,
+                    0.45,
+                    1,
+                ],
+                [
+                    "yolo_vision.jpg",
+                    "yolov11m.pt",
+                    0.25,
+                    0.45,
+                    1,
+                ],
+            ],
+            fn=yolo_inference,
+            inputs=[
+                image,
+                model_id,
+                conf_threshold,
+                iou_threshold,
+                max_detection,
+            ],
+            outputs=[output_image],
+            cache_examples="lazy",
+        )
+
+gradio_app = gr.Blocks()
+with gradio_app:
+    gr.HTML(
+        """
+    <h1 style='text-align: center'>
+    Yolov11 
+    </h1>
+        """)
+    with gr.Row():
+        with gr.Column():
+            app()
+
+gradio_app.launch()