YOLOv10 is Now Integrated into Ultralytics

Inside my school and program, I teach you my system to become an AI engineer or freelancer. Life-time access, personal help by me and I will show you exactly how I went from below average student to making $250/hr. Join the High Earner AI Career Program here 👉 www.nicolai-nielsen.com/aicareer (PRICES WILL INCREASE SOON)
You will also get access to all the technical courses inside the program, also the ones I plan to make in the future! Check out the technical courses below 👇
_____________________________________________________________
In this video 📝 we are going to see how you can use the new YOLOv10 model with ultralytics in just a few lines of code. First, let's take a look at the documentation and how to use it. We will then jump into the code and run it on a live webcam both for object detection and object tracking. The new YOLOv10 video is faster than all the other yolo models but there are always some trade-offs.
If you enjoyed this video, be sure to press the 👍 button so that I know what content you guys like to see.
_____________________________________________________________
🛠️ Freelance Work: www.nicolai-nielsen.com/nncode
_____________________________________________________________
💻💰🛠️ High Earner AI Career Program: www.nicolai-nielsen.com/aicareer
📈 Investment Course: www.nicos-school.com/p/invest...
⚙️ Real-world AI Technical Courses: (www.nicos-school.com)
📗 OpenCV GPU in Python: www.nicos-school.com/p/opencv...
📕 YOLOv7 Object Detection: www.nicos-school.com/p/yolov7...
📒 Transformer & Segmentation: www.nicos-school.com/p/transf...
📙 YOLOv8 Object Tracking: www.nicos-school.com/p/yolov8...
📘 Research Paper Implementation: www.nicos-school.com/p/resear...
📔 CustomGPT: www.nicos-school.com/p/custom...
_____________________________________________________________
📷 Calibrator 📷
My camera calibration software, CharuCo Boards, and Checker boards
Link to webshop: camera-calibrator.com
_____________________________________________________________
📞 Connect with Me:
🌳 linktr.ee/nicolainielsen
🌍 My Website: www.nicolai-nielsen.com/
🤖 GitHub: github.com/niconielsen32
👉 LinkedIn: / nicolaiai
🐦 X/Twitter: / nielsencv_ai
🌆 Instagram: / nicolaihoeirup
_____________________________________________________________
🎮 My Gear (Affiliate links):
💻 Laptop: amzn.to/49LJkTW
🖥️ Desktop PC:
NVIDIA RTX 4090 24GB: amzn.to/3Uc7yAM
Intel I9-14900K: amzn.to/3W4Z5Cb
Motherboard: amzn.to/4aR6wBC
32GB RAM: amzn.to/3Jt2XVR
🖥️ Monitor: amzn.to/4aLP8hh
🖱️ Mouse: amzn.to/3W501GH
⌨️ Keyboard: amzn.to/3xUGz5b
🎙️ Microphone: amzn.to/3w1F1WK
📷 Camera: amzn.to/4b4Ryr9
_____________________________________________________________
Timestamps:
00:00 Introduction
00:30 Ultralytics Docs
02:39 Code
05:55 YOLOv10 Inference live webcam
07:30 Tracking YOLOv10 live webcam
09:17 Outro
Tags: #yolov10 #Yolov10Tracking #computervision #Obejctdetection

[@NicolaiAI]

Join My AI Career Program
👉 www.nicolai-nielsen.com/aicareer
Enroll in the Investing Course outside the AI career program
👉 nicolai-nielsen-s-school.teachable.com/p/investment-course

[@bithigh8301]

Thank you for the video Nico. Yolo is getting better and better and faster and faster

[@NicolaiAI]

Thanks a lot! Yeah for sure, everything in AI is. Cool to follow the progress

[@ibnu7235]

very fast version change of YOLO, amazing video

[@NicolaiAI]

For sure! It’s crazy. Thanks a lot for watching

[@trendcip]

You are videos best man.

[@NicolaiAI]

Thanks a ton mate! Really appreciate it and home you like the significantly upgrade video quality lately

[@EED-qj2tv]

It was an amazing video, I just wondering could we change the configuration or backbone model in YOLO versions.

[@NicolaiAI]

Thanks man! Yeah in the source code you can modify and change the model architectures with layers etc but then you will to retrain from scratch etc

[@user-mc7tg4pf3i]

Hell Sir Thanks for your all videos and efforts. I am following your channel, but I request you please upload one detail video on how to finetune Yolov5 model for custome images classification.

[@ZaidInMeditation]

hey Nicolai, i am so so confused , should i start learning programming or not. As Chatgpt and other ai are improving evryday. please share your thoughts

[@sutirthachakraborty8949]

How to train a custom mediaipipe classifer?

[@mangaenfrancais934]

Thank you Nicolai for the video, it was very informative! Could you advise me on the best way to detect small objects? I'm trying to find defects around 10 pixels in size in images with a resolution of 3168 pixels. Thanks in advance for your help!

[@NicolaiAI]

Thanks a lot! Yeah I have a video about sahi for small object detection here on the channel as well

[@AJ93-lx6on]

can you do yolo v8 custom trained model in c# or c++ dll that can be used in c# with custom model. No body has a tutorial from scratch of training model in yolo google colab then importing that onnx model in c#.

[@KenshiDigital]

it says ModuleNotFoundError how you fix that?
New Problem I cant open the camera, how you open it?

[@vasanth4599]

difference between from ultralytics import YOLOv10 and from ultralytics import YOLO

[@NicolaiAI]

YOLO is the official Ultralytics implementation but was not supported for the first month after release

[@marvinpalencia-ld2ow]

Hello, Nicolai. Is there a way to train a custom model locally? And can it be accelerated using cuda?

[@NicolaiAI]

Yeah for sure! I have a video with the full training pipeline. You can use that locally as well and also use Ultralytics as all the other videos I have

[@kushaal1607]

I am working on a model and I've to compare various yolo versions from v5. But I can't train enough epochs on Google colab since the runtime disconnects everything after like 35 epochs. Tried running on local jupyter on the laptop. But not enough specs for training. Any alternatives which are free like colab for students?

[@jeevans7656]

or just save money or share money with your friends buy google collab pro

[@phes11434]

Thank you Nicolai for the video! I have some question, Yolov10 can achieve real time detection, but using this package, it cannot achieve the same effect. Is there any solution? Thanks in advance for your help!

[@NicolaiAI]

Hey thanks a lot! This def needs a gpu to run in real time. If you have a gpu you just need to install PyTorch with gpu support and it will use that automatically

[@phes11434]

@@NicolaiAI Thanks for your reply, I have gpu support and use pytorch, but in yolov10n I predict that a picture will take 30ms

[@NicolaiAI]

When you run it you can see in the outputs if it’s using cpu or cuda. Most likely u don’t have cuda and PyTorch with gpu support but is just a few installations. 100ms sounds like average cpu

[@chihebnouri5541]

where is the code

[@chihebnouri5541]

it dont worked with trained model

[@cst256]

What's the difference between using model vs model.predict?

[@NicolaiAI]

No difference really. I just prefer to call predict or track.

[@user-xm5wm4zf2r]

its not better than v8.

[@NicolaiAI]

Depends on your use case but generally yolov8 is more accurate but v10 is significantly faster