🔗 YOLO11 Docs: docs.ultralytics.com/models/yolo11/ 🔗 YOLO11 Blog Post: www.ultralytics.com/blog/all-you-need-to-know-about-ultralytics-yolo11-and-its-applications
@Ultralytics2 ай бұрын
Thanks Nicolai for this fantastic overview of Ultralytics YOLO11! 🚀 Really appreciate the detailed walkthrough, benchmarks, and live demos you provided. It's exciting to see the model's potential in action and how it pushes the boundaries of object detection. Keep up the great work! 💥
@YogendraSingh-jh1lz2 ай бұрын
Can't wait to apply this to my own projects. Thanks for sharing! 🥰
@Ultralytics2 ай бұрын
That's awesome to hear! I'm glad you're excited. If you need any help getting started with YOLO11, feel free to check out our documentation docs.ultralytics.com/models/yolo11/. Happy coding! 🚀
@キラキラ輝く-c9e28 күн бұрын
Marvelous!New YOLO series model emerges!I just hope that it's not too late for me to learn i!😂🤣
@Ultralytics28 күн бұрын
It's never too late to start learning, especially with YOLO11! Its user-friendly features make it perfect for beginners and pros alike. Dive in through the Ultralytics Python package pypi.org/project/ultralytics/ or the intuitive Ultralytics HUB www.ultralytics.com/hub to explore and experiment with ease. Happy learning! 🚀
@TejasNarkhede-u6e6 күн бұрын
Thank you for important info!!
@Ultralytics6 күн бұрын
You're very welcome! Glad you found it helpful 😊 Feel free to explore more about Ultralytics' mission, values, and workflows in our Handbook handbook.ultralytics.com/ as we continue to build it out! 🚀
@josetomasl.46112 ай бұрын
loved it, gonna teach on Monday!
@Ultralytics2 ай бұрын
That's awesome! Glad you enjoyed it. Have fun teaching on Monday! 😊 If you need any resources, check out our documentation docs.ultralytics.com/models/yolo11/.
@TeamDman2 ай бұрын
WOOHOO! Nice, thank you for sharing!
@Ultralytics2 ай бұрын
You're welcome! Glad you enjoyed it! If you have any questions about YOLO11 or need more info, feel free to ask. 😊🚀
@salmankmohammedАй бұрын
Thanks, Nicolai. I am working on a project and want to train the Yolov11 from scratch. However, I don't know which parameter to recognize to choose the best number of epochs. Could you guide me well, please!
@UltralyticsАй бұрын
Hey! Choosing the right number of epochs depends on monitoring your model's performance. Watch for when the validation loss stops decreasing or starts increasing, which might indicate overfitting. You can also use early stopping to automate this process. For more tips, check out our guide here: docs.ultralytics.com/guides/model-training-tips/ 😊
@lekha77722 күн бұрын
Hi! What's editor you used in this video?
@Ultralytics22 күн бұрын
Hi! The editor used in our videos is Visual Studio Code. It's lightweight, versatile, and perfect for working with Ultralytics YOLO models. You can explore our guide on optimizing your experience with VSCode here: docs.ultralytics.com/integrations/vscode/ 😊
@haseebkhawaja10502 ай бұрын
I wanted to ask that does all yolo models above yolov8 use same YOLOv8 format. I have my data ready in yolov8 version but I also want to test yolov10 and yolov11 so same format can be used for these updated models
@Ultralytics2 ай бұрын
Yes, YOLOv10 and YOLO11 use the same format as YOLOv8. You can seamlessly test your data with these models. For more details, check out the YOLOv10 documentation: YOLOv10 Documentation docs.ultralytics.com/models/yolov10/ 🚀
@haseebkhawaja10502 ай бұрын
@@Ultralytics Hy there. I hope I will get the response. I wanted to ask about imgsz parameter in YOLO does (1440, 1920) mean that width is 1440 and height is 1920 or vice versa I am so confused about this. I have data ready in 1440 (width) and 1920(height) and i want to train on the exact same size so i get good results on a real time video please help because I searched a lot on web and didn't find CLEAR answer
@haseebkhawaja10502 ай бұрын
@@Ultralytics and plz plz tell me that predict also uses exactly the same order (width, height) or vice versa so I don't again get confused
@Ultralytics2 ай бұрын
Hey there! 😊 In YOLO, the `imgsz` parameter is typically specified as (width, height). So for your data, you would set it to (1440, 1920). This applies to both training and prediction. For more info, check out the YOLO documentation: docs.ultralytics.com/guides/preprocessing_annotated_data/
@loulamicha11 күн бұрын
If i have a special dataset of cars on motion at night ..is yolo11 annotate automaticly sir ...??...also you speak very fast ...
@Ultralytics11 күн бұрын
Yes, YOLO11 can help automate annotation using its tools, but you'll need to preprocess your dataset for best results. Check out our guide here: docs.ultralytics.com/reference/data/annotator/ 😊 And sorry if I was too fast-I'll keep it slower next time! Let me know if you need more clarification. 🚗✨
@rasheedhb3558Ай бұрын
Is there any way to fix the ID assigned? In this case, we want to keep the ID:3 fixed for that car so that when it reappears on the frame, it shows as ID:3 instead of ID:7. This will allow us to count the cars or people that appeared in the video.
@UltralyticsАй бұрын
To maintain consistent IDs for objects like cars across frames, you can use a robust object tracking algorithm. YOLO11 supports multi-object tracking that can help with this. Ensure your environment is updated to the latest versions of `ultralytics` and related packages. For more details on tracking with YOLO, check out our documentation: docs.ultralytics.com/modes/track/ 🚗
@rasheedhb3558Ай бұрын
@Ultralytics Thankyou so much. And for re identification of people?
@UltralyticsАй бұрын
For re-identifying people, you can use advanced tracking solutions that incorporate re-identification techniques. These can maintain consistent IDs even after objects leave and re-enter the frame. Check out our tracking guide for more insights: docs.ultralytics.com/modes/track/ 🕵️♂️
@ProfessorK-nx9gl2 ай бұрын
Is this the SOTA for segmentation?
@Ultralytics2 ай бұрын
YOLO11 offers impressive segmentation capabilities, but whether it's the state-of-the-art (SOTA) depends on your specific needs and benchmarks. For more details, check out the YOLO11 documentation docs.ultralytics.com/models/sam/. 😊
@koftigandi3136Ай бұрын
Can it also be converted into tfjs already?
@UltralyticsАй бұрын
Yes, you can export YOLO11 models to TensorFlow.js (TF.js) format. Use the following command to convert your model: ```python from ultralytics import YOLO model = YOLO("yolo11n.pt") model.export(format="tfjs") ``` For more details, check out the Ultralytics documentation on TF.js integration docs.ultralytics.com/integrations/tfjs/. 😊
@iamdihan2 ай бұрын
Looking foward to trying this out
@Ultralytics2 ай бұрын
Awesome! YOLO11 is packed with exciting features. If you need any guidance, feel free to check out our documentation: docs.ultralytics.com/models/yolo11/ 🚀
@neuromaidenАй бұрын
Fantastic tool! I am new to Ultralytics and would like to ask if I can track position and time that an animal spends in specific zone, please. Thank you!!!
@UltralyticsАй бұрын
Absolutely! You can use Ultralytics YOLO models for tracking animals and analyzing their behavior in specific zones. Check out our guides docs.ultralytics.com/guides/ for detailed instructions on setting up tracking and analyzing movement patterns. If you have more questions, feel free to ask! 😊
@neuromaidenАй бұрын
@@Ultralytics Thank you so much!
@UltralyticsАй бұрын
You're welcome! If you have any more questions or need further assistance, feel free to reach out. Happy tracking! 😊
@dianisirimewan3512 ай бұрын
Fantastic ❤
@Ultralytics2 ай бұрын
Glad you enjoyed it! 😊 If you have any questions about YOLO11, feel free to ask. You can also check out the documentation for more details: docs.ultralytics.com/models/yolo11/
@Moneyyfloyd214Ай бұрын
Can i use this for gaming?
@UltralyticsАй бұрын
Absolutely! AI is transforming gaming by creating more immersive and dynamic experiences. With AI, games can have more realistic NPCs, smarter gameplay, and personalized experiences. Check out our blog on AI in gaming for more insights: www.ultralytics.com/blog/ai-in-video-games-shaping-the-future-of-gaming 🎮
@hasibulislam3669Ай бұрын
How I can use my GPU for processing?
@UltralyticsАй бұрын
To use your GPU for processing with Ultralytics, ensure you have the necessary drivers and software installed. If you're using Docker, install the NVIDIA Docker runtime to enable GPU support. Here's a quick command to run a Docker container with GPU access: ```bash sudo docker run -it --ipc=host --gpus all ultralytics/ultralytics:latest ``` Make sure your system has the NVIDIA drivers installed. For more details, check out our Docker Quickstart Guide docs.ultralytics.com/guides/docker-quickstart/. If you're using Kaggle, you can also access GPUs for free. Learn more about using Kaggle here docs.ultralytics.com/integrations/kaggle/. 🚀
@mohammadaghili84222 ай бұрын
This is like a joke. your model is just a little better than v10. But other versions have reasonable improvement compared to last version.
@Ultralytics2 ай бұрын
Thanks for sharing your thoughts! YOLO11 focuses on refining efficiency and accuracy, building on the strengths of YOLOv10. Each version aims to address specific improvements, and feedback like yours is valuable for future updates. For more details, check out the YOLO11 documentation docs.ultralytics.com/models/yolo11/. 😊
@Tungdang-tv7sd15 күн бұрын
how to ultralytics tracking subtitles
@Ultralytics14 күн бұрын
Ultralytics YOLO11 doesn't natively support subtitle generation for tracking, but you can use the tracking data (like object IDs or positions) to overlay subtitles or labels on your video frames. For example, you can use `model.track` to assign object IDs and dynamically add subtitles or labels for each tracked object. Check out our detailed guide on tracking with YOLO11 docs.ultralytics.com/guides/instance-segmentation-and-tracking/ for more insights.
@AWXPlaysАй бұрын
nicee
@UltralyticsАй бұрын
Glad you liked it! 😊 If you have any questions or want to learn more about YOLO11, feel free to ask!