Download app.py from VIDraft/Yolo26: direct link, hf CLI and curl.
- Browser
- Download file 18.6 kB
-
https://huggingface.co/spaces/VIDraft/Yolo26/resolve/main/app.py
- Command line
-
hf download hf://spaces/VIDraft/Yolo26/app.py
-
curl -L -o app.py https://huggingface.co/spaces/VIDraft/Yolo26/resolve/main/app.py
18.6 kB
| import spaces | |
| import gradio as gr | |
| from PIL import Image, ImageDraw, ImageFont | |
| from ultralytics import YOLO | |
| import cv2 | |
| import tempfile | |
| import numpy as np | |
| # ----------------------------- | |
| # Neumorphism CSS Theme | |
| # ----------------------------- | |
| NEUMORPHISM_CSS = """ | |
| /* โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| ๐ NEUMORPHISM ์คํ์ผ for Gradio | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ */ | |
| /* ๐จ ํต์ฌ ์์ ํ๋ ํธ */ | |
| :root { | |
| --neu-bg: #e0e5ec; | |
| --neu-shadow-dark: #b8bec5; | |
| --neu-shadow-light: #ffffff; | |
| --neu-text: #6d7b8d; | |
| --neu-text-dark: #5a6677; | |
| --neu-accent: #6366f1; | |
| --neu-accent-light: #818cf8; | |
| } | |
| /* ๐ฆ ์ ์ฒด ๋ฐฐ๊ฒฝ */ | |
| body, .gradio-container { | |
| background: var(--neu-bg) !important; | |
| font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; | |
| } | |
| .main, .contain { | |
| background: var(--neu-bg) !important; | |
| } | |
| /* ๐ฒ ๋ฉ์ธ ์ปจํ ์ด๋ ๋ณผ๋ก ํจ๊ณผ */ | |
| .gradio-container .main { | |
| background: var(--neu-bg) !important; | |
| padding: 30px !important; | |
| } | |
| /* ๐ ์ ๋ชฉ ์คํ์ผ */ | |
| h1, .markdown h1 { | |
| color: var(--neu-text-dark) !important; | |
| text-shadow: | |
| 2px 2px 4px var(--neu-shadow-light), | |
| -1px -1px 3px rgba(0,0,0,0.1) !important; | |
| font-weight: 800 !important; | |
| letter-spacing: -0.5px; | |
| } | |
| .markdown p, .markdown { | |
| color: var(--neu-text) !important; | |
| } | |
| /* ๐ณ ํจ๋ & ๋ฐ์ค - ์ค๋ชฉ/๋ณผ๋ก ํจ๊ณผ */ | |
| .panel, .gr-panel, .gr-box, .gr-form, | |
| .block, .wrap, .container { | |
| background: var(--neu-bg) !important; | |
| border: none !important; | |
| } | |
| /* ํญ ์ปจํ ์ด๋ */ | |
| .tabs { | |
| background: var(--neu-bg) !important; | |
| border-radius: 20px !important; | |
| box-shadow: | |
| 8px 8px 16px var(--neu-shadow-dark), | |
| -8px -8px 16px var(--neu-shadow-light) !important; | |
| padding: 20px !important; | |
| margin: 15px 0 !important; | |
| } | |
| /* ํญ ๋ฒํผ */ | |
| .tab-nav button { | |
| background: var(--neu-bg) !important; | |
| border: none !important; | |
| border-radius: 15px !important; | |
| color: var(--neu-text) !important; | |
| font-weight: 600 !important; | |
| padding: 12px 24px !important; | |
| margin: 5px !important; | |
| box-shadow: | |
| 4px 4px 8px var(--neu-shadow-dark), | |
| -4px -4px 8px var(--neu-shadow-light) !important; | |
| transition: all 0.3s ease !important; | |
| } | |
| .tab-nav button:hover { | |
| color: var(--neu-accent) !important; | |
| box-shadow: | |
| 2px 2px 4px var(--neu-shadow-dark), | |
| -2px -2px 4px var(--neu-shadow-light) !important; | |
| } | |
| .tab-nav button.selected { | |
| background: var(--neu-bg) !important; | |
| color: var(--neu-accent) !important; | |
| box-shadow: | |
| inset 4px 4px 8px var(--neu-shadow-dark), | |
| inset -4px -4px 8px var(--neu-shadow-light) !important; | |
| } | |
| /* ๐ผ๏ธ ์ด๋ฏธ์ง/๋น๋์ค ์ ๋ก๋ ์์ญ - ์ค๋ชฉ ํจ๊ณผ */ | |
| .image-container, .video-container, | |
| .upload-container, .gr-image, .gr-video, | |
| [data-testid="image"], [data-testid="video"] { | |
| background: var(--neu-bg) !important; | |
| border-radius: 20px !important; | |
| box-shadow: | |
| inset 6px 6px 12px var(--neu-shadow-dark), | |
| inset -6px -6px 12px var(--neu-shadow-light) !important; | |
| border: none !important; | |
| padding: 15px !important; | |
| overflow: hidden; | |
| } | |
| /* ์ ๋ ฅ ํ๋ ์์ญ */ | |
| .gr-input, input, select, textarea, | |
| .gr-dropdown, .dropdown-container { | |
| background: var(--neu-bg) !important; | |
| border: none !important; | |
| border-radius: 15px !important; | |
| box-shadow: | |
| inset 4px 4px 8px var(--neu-shadow-dark), | |
| inset -4px -4px 8px var(--neu-shadow-light) !important; | |
| color: var(--neu-text-dark) !important; | |
| padding: 12px 16px !important; | |
| } | |
| .gr-input:focus, input:focus, select:focus, textarea:focus { | |
| outline: none !important; | |
| box-shadow: | |
| inset 6px 6px 12px var(--neu-shadow-dark), | |
| inset -6px -6px 12px var(--neu-shadow-light), | |
| 0 0 0 3px rgba(99, 102, 241, 0.2) !important; | |
| } | |
| /* ๐๏ธ ์ฌ๋ผ์ด๋ ์คํ์ผ */ | |
| .gr-slider input[type="range"] { | |
| background: var(--neu-bg) !important; | |
| border-radius: 10px !important; | |
| box-shadow: | |
| inset 3px 3px 6px var(--neu-shadow-dark), | |
| inset -3px -3px 6px var(--neu-shadow-light) !important; | |
| height: 8px !important; | |
| } | |
| .gr-slider input[type="range"]::-webkit-slider-thumb { | |
| background: var(--neu-bg) !important; | |
| border: none !important; | |
| border-radius: 50% !important; | |
| width: 22px !important; | |
| height: 22px !important; | |
| box-shadow: | |
| 4px 4px 8px var(--neu-shadow-dark), | |
| -4px -4px 8px var(--neu-shadow-light) !important; | |
| cursor: pointer !important; | |
| } | |
| /* ๐ ๋ฒํผ ์คํ์ผ - ๋ณผ๋ก ํจ๊ณผ */ | |
| .gr-button, button.primary, button.secondary, | |
| [data-testid="button"] { | |
| background: var(--neu-bg) !important; | |
| border: none !important; | |
| border-radius: 50px !important; | |
| padding: 14px 40px !important; | |
| color: var(--neu-text) !important; | |
| font-weight: 700 !important; | |
| font-size: 14px !important; | |
| letter-spacing: 0.5px !important; | |
| box-shadow: | |
| 6px 6px 12px var(--neu-shadow-dark), | |
| -6px -6px 12px var(--neu-shadow-light) !important; | |
| transition: all 0.2s ease !important; | |
| cursor: pointer !important; | |
| } | |
| .gr-button:hover, button:hover { | |
| box-shadow: | |
| 4px 4px 8px var(--neu-shadow-dark), | |
| -4px -4px 8px var(--neu-shadow-light) !important; | |
| color: var(--neu-accent) !important; | |
| } | |
| .gr-button:active, button:active { | |
| box-shadow: | |
| inset 4px 4px 8px var(--neu-shadow-dark), | |
| inset -4px -4px 8px var(--neu-shadow-light) !important; | |
| } | |
| /* Primary ๋ฒํผ (Detect Objects) - ๊ฐ์กฐ */ | |
| button.primary, .gr-button-primary, | |
| button[variant="primary"] { | |
| background: linear-gradient(145deg, #cacfd6, #f0f5fc) !important; | |
| color: var(--neu-accent) !important; | |
| font-weight: 800 !important; | |
| box-shadow: | |
| 8px 8px 16px var(--neu-shadow-dark), | |
| -8px -8px 16px var(--neu-shadow-light) !important; | |
| } | |
| button.primary:hover { | |
| background: linear-gradient(145deg, #d4d9e0, #f5faff) !important; | |
| color: var(--neu-accent-light) !important; | |
| } | |
| /* ๐ ๋๋กญ๋ค์ด */ | |
| .gr-dropdown .wrap { | |
| background: var(--neu-bg) !important; | |
| border-radius: 15px !important; | |
| box-shadow: | |
| inset 4px 4px 8px var(--neu-shadow-dark), | |
| inset -4px -4px 8px var(--neu-shadow-light) !important; | |
| } | |
| .gr-dropdown ul { | |
| background: var(--neu-bg) !important; | |
| border-radius: 15px !important; | |
| box-shadow: | |
| 8px 8px 16px var(--neu-shadow-dark), | |
| -8px -8px 16px var(--neu-shadow-light) !important; | |
| border: none !important; | |
| } | |
| .gr-dropdown li { | |
| background: transparent !important; | |
| color: var(--neu-text) !important; | |
| } | |
| .gr-dropdown li:hover { | |
| background: rgba(99, 102, 241, 0.1) !important; | |
| color: var(--neu-accent) !important; | |
| } | |
| /* ๐๏ธ Accordion ์คํ์ผ */ | |
| .gr-accordion { | |
| background: var(--neu-bg) !important; | |
| border-radius: 20px !important; | |
| box-shadow: | |
| 6px 6px 12px var(--neu-shadow-dark), | |
| -6px -6px 12px var(--neu-shadow-light) !important; | |
| border: none !important; | |
| margin: 15px 0 !important; | |
| overflow: hidden; | |
| } | |
| .gr-accordion > .label-wrap { | |
| background: var(--neu-bg) !important; | |
| padding: 15px 20px !important; | |
| } | |
| .gr-accordion > .label-wrap:hover { | |
| background: rgba(99, 102, 241, 0.05) !important; | |
| } | |
| /* ๐ Examples ์น์ */ | |
| .gr-examples { | |
| background: var(--neu-bg) !important; | |
| border-radius: 20px !important; | |
| padding: 20px !important; | |
| margin-top: 20px !important; | |
| } | |
| .gr-examples .gr-sample { | |
| background: var(--neu-bg) !important; | |
| border-radius: 15px !important; | |
| box-shadow: | |
| 4px 4px 8px var(--neu-shadow-dark), | |
| -4px -4px 8px var(--neu-shadow-light) !important; | |
| border: none !important; | |
| transition: all 0.2s ease !important; | |
| overflow: hidden; | |
| } | |
| .gr-examples .gr-sample:hover { | |
| box-shadow: | |
| 2px 2px 4px var(--neu-shadow-dark), | |
| -2px -2px 4px var(--neu-shadow-light) !important; | |
| transform: translateY(2px); | |
| } | |
| /* ๋ผ๋ฒจ ์คํ์ผ */ | |
| label, .gr-input-label, .label-wrap span { | |
| color: var(--neu-text-dark) !important; | |
| font-weight: 600 !important; | |
| text-shadow: | |
| 1px 1px 2px var(--neu-shadow-light) !important; | |
| } | |
| /* Row & Column ๋ ์ด์์ */ | |
| .gr-row, .gr-column { | |
| background: transparent !important; | |
| } | |
| /* ์คํฌ๋กค๋ฐ ์คํ์ผ */ | |
| ::-webkit-scrollbar { | |
| width: 12px; | |
| height: 12px; | |
| } | |
| ::-webkit-scrollbar-track { | |
| background: var(--neu-bg); | |
| border-radius: 10px; | |
| box-shadow: | |
| inset 2px 2px 4px var(--neu-shadow-dark), | |
| inset -2px -2px 4px var(--neu-shadow-light); | |
| } | |
| ::-webkit-scrollbar-thumb { | |
| background: var(--neu-bg); | |
| border-radius: 10px; | |
| box-shadow: | |
| 2px 2px 4px var(--neu-shadow-dark), | |
| -2px -2px 4px var(--neu-shadow-light); | |
| } | |
| /* ๐ DeepLinkButton ์คํ์ผ */ | |
| .deeplink-button { | |
| background: var(--neu-bg) !important; | |
| border-radius: 25px !important; | |
| box-shadow: | |
| 4px 4px 8px var(--neu-shadow-dark), | |
| -4px -4px 8px var(--neu-shadow-light) !important; | |
| } | |
| /* ์ถ๋ ฅ ์ด๋ฏธ์ง/๋น๋์ค ์์ญ */ | |
| .output-image, .output-video { | |
| border-radius: 20px !important; | |
| box-shadow: | |
| 8px 8px 16px var(--neu-shadow-dark), | |
| -8px -8px 16px var(--neu-shadow-light) !important; | |
| } | |
| /* ์ ๋๋ฉ์ด์ */ | |
| @keyframes neu-pulse { | |
| 0%, 100% { | |
| box-shadow: | |
| 6px 6px 12px var(--neu-shadow-dark), | |
| -6px -6px 12px var(--neu-shadow-light); | |
| } | |
| 50% { | |
| box-shadow: | |
| 8px 8px 16px var(--neu-shadow-dark), | |
| -8px -8px 16px var(--neu-shadow-light); | |
| } | |
| } | |
| /* Footer ์จ๊ธฐ๊ธฐ (์ ํ์ฌํญ) */ | |
| footer { | |
| display: none !important; | |
| } | |
| /* Block ์ ๋ชฉ */ | |
| .block-title { | |
| color: var(--neu-text-dark) !important; | |
| font-weight: 700 !important; | |
| } | |
| """ | |
| # ----------------------------- | |
| # Inference | |
| # ----------------------------- | |
| def yolo_inference_image(image, model_id, conf_threshold, iou_threshold, max_detection): | |
| model = YOLO(model_id) | |
| if getattr(model, "task", None) != "classify": | |
| head = model.model.model[-1] | |
| if hasattr(head, "one2one_cv2"): | |
| delattr(head, "one2one_cv2") | |
| if image is None: | |
| w, h = 640, 480 | |
| blank = Image.new("RGB", (w, h), color=(224, 229, 236)) # Neumorphism ๋ฐฐ๊ฒฝ์ | |
| draw = ImageDraw.Draw(blank) | |
| msg = "No image provided" | |
| font = ImageFont.load_default(size=40) | |
| bbox = draw.textbbox((0, 0), msg, font=font) | |
| tw, th = bbox[2] - bbox[0], bbox[3] - bbox[1] | |
| draw.text(((w - tw) / 2, (h - th) / 2), msg, fill=(109, 123, 141), font=font) | |
| return blank | |
| results = model.predict( | |
| source=image, | |
| conf=conf_threshold, | |
| iou=iou_threshold, | |
| imgsz=640, | |
| max_det=max_detection, | |
| show_labels=True, | |
| show_conf=True, | |
| ) | |
| annotated_image = None | |
| for r in results: | |
| img_bgr = r.plot() | |
| annotated_image = Image.fromarray(img_bgr[..., ::-1]) | |
| return annotated_image | |
| def yolo_inference_video(video, model_id, conf_threshold, iou_threshold, max_detection): | |
| model = YOLO(model_id) | |
| if getattr(model, "task", None) != "classify": | |
| head = model.model.model[-1] | |
| if hasattr(head, "one2one_cv2"): | |
| delattr(head, "one2one_cv2") | |
| if video is None: | |
| w, h = 640, 480 | |
| blank = Image.new("RGB", (w, h), color=(224, 229, 236)) | |
| draw = ImageDraw.Draw(blank) | |
| msg = "No video provided" | |
| font = ImageFont.load_default(size=40) | |
| bbox = draw.textbbox((0, 0), msg, font=font) | |
| tw, th = bbox[2] - bbox[0], bbox[3] - bbox[1] | |
| draw.text(((w - tw) / 2, (h - th) / 2), msg, fill=(109, 123, 141), font=font) | |
| tmp = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name | |
| fourcc = cv2.VideoWriter_fourcc(*"mp4v") | |
| out = cv2.VideoWriter(tmp, fourcc, 1, (w, h)) | |
| out.write(cv2.cvtColor(np.array(blank), cv2.COLOR_RGB2BGR)) | |
| out.release() | |
| return tmp | |
| cap = cv2.VideoCapture(video) | |
| if not cap.isOpened(): | |
| return None | |
| fps_val = cap.get(cv2.CAP_PROP_FPS) | |
| fps = fps_val if fps_val and fps_val > 0 else 25 | |
| w_val = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) | |
| h_val = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) | |
| w = w_val if w_val and w_val > 0 else 640 | |
| h = h_val if h_val and h_val > 0 else 480 | |
| tmp = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name | |
| fourcc = cv2.VideoWriter_fourcc(*"mp4v") | |
| out = cv2.VideoWriter(tmp, fourcc, fps, (w, h)) | |
| wrote_any = False | |
| while True: | |
| ret, frame = cap.read() | |
| if not ret: | |
| break | |
| results = model.predict( | |
| source=frame, | |
| conf=conf_threshold, | |
| iou=iou_threshold, | |
| imgsz=640, | |
| max_det=max_detection, | |
| show_labels=True, | |
| show_conf=True, | |
| verbose=False, | |
| ) | |
| anno_bgr = frame | |
| for r in results: | |
| anno_bgr = r.plot() | |
| out.write(anno_bgr) | |
| wrote_any = True | |
| cap.release() | |
| out.release() | |
| if not wrote_any: | |
| return None | |
| return tmp | |
| def yolo_inference_for_examples(image, model_id, conf_threshold, iou_threshold, max_detection): | |
| return yolo_inference_image(image, model_id, conf_threshold, iou_threshold, max_detection) | |
| MODEL_CHOICES = [ | |
| "yolo26n.pt", "yolo26s.pt", "yolo26m.pt", "yolo26l.pt", "yolo26x.pt", | |
| "yolo26n-seg.pt", "yolo26s-seg.pt", "yolo26m-seg.pt", "yolo26l-seg.pt", "yolo26x-seg.pt", | |
| "yolo26n-pose.pt", "yolo26s-pose.pt", "yolo26m-pose.pt", "yolo26l-pose.pt", "yolo26x-pose.pt", | |
| "yolo26n-obb.pt", "yolo26s-obb.pt", "yolo26m-obb.pt", "yolo26l-obb.pt", "yolo26x-obb.pt", | |
| "yolo26n-cls.pt", "yolo26s-cls.pt", "yolo26m-cls.pt", "yolo26l-cls.pt", "yolo26x-cls.pt", | |
| ] | |
| with gr.Blocks(css=NEUMORPHISM_CSS, title="YOLO26 - Neumorphism UI") as app: | |
| gr.Markdown("# ๐ YOLO26") | |
| gr.Markdown( | |
| "Image or video inference with detection, segmentation, pose, oriented bounding boxes, and classification using the latest Ultralytics YOLO26 models." | |
| ) | |
| with gr.Accordion("๐ Reference", open=False): | |
| gr.Markdown( | |
| """ | |
| **BibTeX:** | |
| ``` | |
| @software{yolo26_ultralytics, | |
| author = {Glenn Jocher and Jing Qiu}, | |
| title = {Ultralytics YOLO26}, | |
| version = {26.0.0}, | |
| year = {2025}, | |
| url = {https://github.com/ultralytics/ultralytics}, | |
| orcid = {0000-0001-5950-6979, 0000-0003-3783-7069}, | |
| license = {AGPL-3.0} | |
| } | |
| ``` | |
| """ | |
| ) | |
| with gr.Tabs() as media_tabs: | |
| with gr.Tab("๐ผ๏ธ Image") as image_tab: | |
| with gr.Row(): | |
| with gr.Column(): | |
| image = gr.Image(type="pil", label="Upload Image") | |
| model_id_img = gr.Dropdown( | |
| label="Model", | |
| choices=MODEL_CHOICES, | |
| value="yolo26n.pt" | |
| ) | |
| conf_img = gr.Slider( | |
| 0, 1, value=0.25, | |
| label="Confidence Threshold" | |
| ) | |
| iou_img = gr.Slider( | |
| 0, 1, value=0.45, | |
| label="IoU Threshold" | |
| ) | |
| max_det_img = gr.Slider( | |
| 1, 300, step=1, value=300, | |
| label="Max Detection" | |
| ) | |
| infer_image_button = gr.Button( | |
| "๐ Detect Objects", | |
| variant="primary" | |
| ) | |
| with gr.Column(): | |
| output_image = gr.Image(type="pil", label="Result") | |
| gr.DeepLinkButton(variant="primary") | |
| gr.Examples( | |
| examples=[ | |
| ["zidane.jpg", "yolo26s.pt", 0.25, 0.45, 300], | |
| ["bus.jpg", "yolo26m.pt", 0.25, 0.45, 300], | |
| ["yolo_vision.jpg", "yolo26x.pt", 0.25, 0.45, 300], | |
| ["Tricycle.jpg", "yolo26x-cls.pt", 0.25, 0.45, 300], | |
| ["tcganadolu.jpg", "yolo26m-obb.pt", 0.25, 0.45, 300], | |
| ["San Diego Airport.jpg", "yolo26x-seg.pt", 0.25, 0.45, 300], | |
| ["Theodore_Roosevelt.png", "yolo26l-pose.pt", 0.25, 0.45, 300], | |
| ], | |
| fn=yolo_inference_for_examples, | |
| inputs=[image, model_id_img, conf_img, iou_img, max_det_img], | |
| outputs=[output_image], | |
| label="Examples", | |
| ) | |
| with gr.Tab("๐ฌ Video") as video_tab: | |
| with gr.Row(): | |
| with gr.Column(): | |
| video = gr.Video(label="Upload Video") | |
| model_id_vid = gr.Dropdown( | |
| label="Model", | |
| choices=MODEL_CHOICES, | |
| value="yolo26n.pt" | |
| ) | |
| conf_vid = gr.Slider( | |
| 0, 1, value=0.25, | |
| label="Confidence Threshold" | |
| ) | |
| iou_vid = gr.Slider( | |
| 0, 1, value=0.45, | |
| label="IoU Threshold" | |
| ) | |
| max_det_vid = gr.Slider( | |
| 1, 300, step=1, value=300, | |
| label="Max Detection" | |
| ) | |
| infer_video_button = gr.Button( | |
| "๐ Detect Objects", | |
| variant="primary" | |
| ) | |
| with gr.Column(): | |
| output_video = gr.Video(label="Result") | |
| gr.DeepLinkButton(variant="primary") | |
| infer_image_button.click( | |
| fn=yolo_inference_image, | |
| inputs=[image, model_id_img, conf_img, iou_img, max_det_img], | |
| outputs=[output_image], | |
| ) | |
| infer_video_button.click( | |
| fn=yolo_inference_video, | |
| inputs=[video, model_id_vid, conf_vid, iou_vid, max_det_vid], | |
| outputs=[output_video], | |
| ) | |
| if __name__ == "__main__": | |
| app.launch(mcp_server=True) |