Update app.py

app.py

@@ -2,69 +2,192 @@ import gradio as gr
 from PIL import Image, ImageDraw, ImageFont
 from ultralytics import YOLO
 import spaces
+import cv2
+import numpy as np
+import tempfile
 
 @spaces.GPU
-def yolo_inference(images, model_id, conf_threshold, iou_threshold, max_detection):
-    if images is None:
-        # Create a blank image
-        width, height = 640, 480
-        blank_image = Image.new("RGB", (width, height), color="white")
-        draw = ImageDraw.Draw(blank_image)
-        message = "No image provided"
-        font = ImageFont.load_default(size=40)
-        bbox = draw.textbbox((0, 0), message, font=font)
-        text_width = bbox[2] - bbox[0]
-        text_height = bbox[3] - bbox[1]
-        text_x = (width - text_width) / 2
-        text_y = (height - text_height) / 2
-        draw.text((text_x, text_y), message, fill="black", font=font)
-        return blank_image
-    
-    model = YOLO(model_id)
-    results = model.predict(
-        source=images,
-        conf=conf_threshold,
-        iou=iou_threshold,
-        imgsz=640,
-        max_det=max_detection,
-        show_labels=True,
-        show_conf=True,
+def yolo_inference(input_type, image, video, model_id, conf_threshold, iou_threshold, max_detection):
+    if input_type == "Image":
+        if image is None:
+            width, height = 640, 480
+            blank_image = Image.new("RGB", (width, height), color="white")
+            draw = ImageDraw.Draw(blank_image)
+            message = "No image provided"
+            font = ImageFont.load_default(size=40)
+            bbox = draw.textbbox((0, 0), message, font=font)
+            text_width = bbox[2] - bbox[0]
+            text_height = bbox[3] - bbox[1]
+            text_x = (width - text_width) / 2
+            text_y = (height - text_height) / 2
+            draw.text((text_x, text_y), message, fill="black", font=font)
+            return blank_image, None
+
+        model = YOLO(model_id)
+        results = model.predict(
+            source=image,
+            conf=conf_threshold,
+            iou=iou_threshold,
+            imgsz=640,
+            max_det=max_detection,
+            show_labels=True,
+            show_conf=True,
+        )
+        for r in results:
+            image_array = r.plot()
+            annotated_image = Image.fromarray(image_array[..., ::-1])
+        return annotated_image, None
+
+    elif input_type == "Video":
+        if video is None:
+            width, height = 640, 480
+            blank_image = Image.new("RGB", (width, height), color="white")
+            draw = ImageDraw.Draw(blank_image)
+            message = "No video provided"
+            font = ImageFont.load_default(size=40)
+            bbox = draw.textbbox((0, 0), message, font=font)
+            text_width = bbox[2] - bbox[0]
+            text_height = bbox[3] - bbox[1]
+            text_x = (width - text_width) / 2
+            text_y = (height - text_height) / 2
+            draw.text((text_x, text_y), message, fill="black", font=font)
+            temp_video_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name
+            fourcc = cv2.VideoWriter_fourcc(*"mp4v")
+            out = cv2.VideoWriter(temp_video_file, fourcc, 1, (width, height))
+            frame = cv2.cvtColor(np.array(blank_image), cv2.COLOR_RGB2BGR)
+            out.write(frame)
+            out.release()
+            return None, temp_video_file
+
+        model = YOLO(model_id)
+        cap = cv2.VideoCapture(video)
+        fps = cap.get(cv2.CAP_PROP_FPS) if cap.get(cv2.CAP_PROP_FPS) > 0 else 25
+        frames = []
+        while True:
+            ret, frame = cap.read()
+            if not ret:
+                break
+            pil_frame = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+            results = model.predict(
+                source=pil_frame,
+                conf=conf_threshold,
+                iou=iou_threshold,
+                imgsz=640,
+                max_det=max_detection,
+                show_labels=True,
+                show_conf=True,
+            )
+            for r in results:
+                annotated_frame_array = r.plot()
+                annotated_frame = cv2.cvtColor(annotated_frame_array, cv2.COLOR_BGR2RGB)
+            frames.append(annotated_frame)
+        cap.release()
+        if len(frames) == 0:
+            return None, None
+
+        height_out, width_out, _ = frames[0].shape
+        temp_video_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name
+        fourcc = cv2.VideoWriter_fourcc(*"mp4v")
+        out = cv2.VideoWriter(temp_video_file, fourcc, fps, (width_out, height_out))
+        for f in frames:
+            f_bgr = cv2.cvtColor(f, cv2.COLOR_RGB2BGR)
+            out.write(f_bgr)
+        out.release()
+        return None, temp_video_file
+
+    else:
+        return None, None
+
+def update_visibility(input_type):
+    """
+    Show/hide image/video input and output depending on input_type.
+    """
+    if input_type == "Image":
+        # image, video, output_image, output_video
+        return gr.update(visible=True), gr.update(visible=False), gr.update(visible=True), gr.update(visible=False)
+    else:
+        return gr.update(visible=False), gr.update(visible=True), gr.update(visible=False), gr.update(visible=True)
+
+def yolo_inference_for_examples(image, model_id, conf_threshold, iou_threshold, max_detection):
+    """
+    This is called by gr.Examples. We force the radio to 'Image'
+    and then do a standard image inference, returning both updated radio
+    value and the annotated image.
+    """
+    annotated_image, _ = yolo_inference(
+        input_type="Image",
+        image=image,
+        video=None,
+        model_id=model_id,
+        conf_threshold=conf_threshold,
+        iou_threshold=iou_threshold,
+        max_detection=max_detection
     )
+    return gr.update(value="Image"), annotated_image
 
-    for r in results:
-        image_array = r.plot()
-        image = Image.fromarray(image_array[..., ::-1])
-    return image
+with gr.Blocks() as app:
+    gr.Markdown("# Yolo11: Object Detection, Instance Segmentation, Pose/Keypoints, Oriented Detection, Classification")
+    gr.Markdown("Upload image(s) or video(s) for inference using the latest Ultralytics YOLO11 models.")
+    
+    with gr.Row():
+        with gr.Column():
+            image = gr.Image(type="pil", label="Image", visible=True)
+            video = gr.Video(label="Video", visible=False)
+            input_type = gr.Radio(
+                choices=["Image", "Video"],
+                value="Image",
+                label="Input Type",
+            )
+            model_id = gr.Dropdown(
+                label="Model Name",
+                choices=[
+                    'yolo11n.pt', 'yolo11s.pt', 'yolo11m.pt', 'yolo11l.pt', 'yolo11x.pt', 
+                    'yolo11n-seg.pt', 'yolo11s-seg.pt', 'yolo11m-seg.pt', 'yolo11l-seg.pt', 'yolo11x-seg.pt',
+                    'yolo11n-pose.pt', 'yolo11s-pose.pt', 'yolo11m-pose.pt', 'yolo11l-pose.pt', 'yolo11x-pose.pt',
+                    'yolo11n-obb.pt', 'yolo11s-obb.pt', 'yolo11m-obb.pt', 'yolo11l-obb.pt', 'yolo11x-obb.pt',
+                    'yolo11n-cls.pt', 'yolo11s-cls.pt', 'yolo11m-cls.pt', 'yolo11l-cls.pt', 'yolo11x-cls.pt'
+                ],
+                value="yolo11n.pt",
+            )
+            conf_threshold = gr.Slider(minimum=0, maximum=1, value=0.25, label="Confidence Threshold")
+            iou_threshold = gr.Slider(minimum=0, maximum=1, value=0.45, label="IoU Threshold")
+            max_detection = gr.Slider(minimum=1, maximum=300, step=1, value=300, label="Max Detection")
+            infer_button = gr.Button("Detect Objects")
+        with gr.Column():
+            output_image = gr.Image(type="pil", label="Annotated Image", visible=True)
+            output_video = gr.Video(label="Annotated Video", visible=False)
+    
+    # Toggle input/output visibility
+    input_type.change(
+        fn=update_visibility,
+        inputs=input_type,
+        outputs=[image, video, output_image, output_video],
+    )
+    
+    # Main inference for button click
+    infer_button.click(
+        fn=yolo_inference,
+        inputs=[input_type, image, video, model_id, conf_threshold, iou_threshold, max_detection],
+        outputs=[output_image, output_video],
+    )
+    
+    # Examples for images only
+    gr.Examples(
+        examples=[
+            ["zidane.jpg", "yolo11s.pt", 0.25, 0.45, 300],
+            ["bus.jpg", "yolo11m.pt", 0.25, 0.45, 300],
+            ["yolo_vision.jpg", "yolo11x.pt", 0.25, 0.45, 300],
+            ["Tricycle.jpg", "yolo11x-cls.pt", 0.25, 0.45, 300],
+            ["tcganadolu.jpg", "yolo11m-obb.pt", 0.25, 0.45, 300],
+            ["San Diego Airport.jpg", "yolo11x-seg.pt", 0.25, 0.45, 300],
+            ["Theodore_Roosevelt.png", "yolo11l-pose.pt", 0.25, 0.45, 300],
+        ],
+        fn=yolo_inference_for_examples,
+        inputs=[image, model_id, conf_threshold, iou_threshold, max_detection],
+        outputs=[input_type, output_image],
+        label="Examples (Images)",
+        cache_examples=True,
+    )
 
-interface = gr.Interface(
-    fn=yolo_inference,
-    inputs=[
-        gr.Image(type="pil", label="Upload Image"),
-        gr.Dropdown(
-            choices=['yolo11n.pt', 'yolo11s.pt', 'yolo11m.pt', 'yolo11l.pt', 'yolo11x.pt', 
-                     'yolo11n-seg.pt', 'yolo11s-seg.pt', 'yolo11m-seg.pt', 'yolo11l-seg.pt', 'yolo11x-seg.pt',
-                     'yolo11n-pose.pt', 'yolo11s-pose.pt', 'yolo11m-pose.pt', 'yolo11l-pose.pt', 'yolo11x-pose.pt',
-                     'yolo11n-obb.pt', 'yolo11s-obb.pt', 'yolo11m-obb.pt', 'yolo11l-obb.pt', 'yolo11x-obb.pt',
-                     'yolo11n-cls.pt', 'yolo11s-cls.pt', 'yolo11m-cls.pt', 'yolo11l-cls.pt', 'yolo11x-cls.pt'],
-            label="Model Name",
-            value="yolo11n.pt",
-        ),
-        gr.Slider(minimum=0, maximum=1, value=0.25, label="Confidence Threshold"),
-        gr.Slider(minimum=0, maximum=1, value=0.45, label="IoU Threshold"),
-        gr.Slider(minimum=1, maximum=300, step=1, value=300, label="Max Detection"),
-    ],
-    outputs=gr.Image(type="pil", label="Annotated Image"),
-    cache_examples=True,
-    title="Yolo11: Object Detection, Instance Segmentation, Pose/Keypoints, Oriented Detection, Classification",
-    description="Upload image(s) for inference using the latest Ultralytics YOLO11 models.",
-    examples=[
-        ["zidane.jpg", "yolo11s.pt", 0.25, 0.45, 300],
-        ["bus.jpg", "yolo11m.pt", 0.25, 0.45, 300],
-        ["yolo_vision.jpg", "yolo11x.pt", 0.25, 0.45, 300],
-        ["Tricycle.jpg", "yolo11x-cls.pt", 0.25, 0.45, 300],
-        ["tcganadolu.jpg", "yolo11m-obb.pt", 0.25, 0.45, 300],
-        ["San Diego Airport.jpg", "yolo11x-seg.pt", 0.25, 0.45, 300],
-        ["Theodore_Roosevelt.png", "yolo11l-pose.pt", 0.25, 0.45, 300],
-    ],
-)
-interface.launch()
+if __name__ == '__main__':
+    app.launch()