How to Deploy YOLOv5 Model with OpenCV and Python

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 Deploy a YOLOv5 Object Detection Model with OpenCV. We will create a class where you can put in a youtube video that you want to detect objects in. We will go over each line of the code, talk about how to set it up, and how to run the program.

If you enjoyed this video, be sure to press the 👍 button so that I know what content you guys like to see.

_____________________________________________________________

_____________________________________________________________

_____________________________________________________________

📞 Connect with Me:

_____________________________________________________________

🎮 My Gear (Affiliate links):
🖥️ Desktop PC:

_____________________________________________________________

Timestamps:
0:00 Intro
1:05 Install
4:56 YOLOv5 Class
18:54 Inference Results

Tags:
#YOLOv5 #ObjectDetection #DeepLearning #DeployModels

[NicolaiAI]

Join My AI Career Program
Enroll in My School and Technical Courses

[weareone]

Hey Nicolai. Amazing video. Your content is really helpful for me. Quick question - How do I get the probability score for each predicted class on the top of the bounding boxes besides the class labels here?

[IlayAsis]

hi, how I can to display on the box that box the confidence of detection for each object that been detection?

[tomscott]

This video is awesome, thank you. Are there any changes you need to make to enable it to read multiple prediction classes? I am taking a stab that you need to adapt the plot_boxes function to adapt to each class? But I might be wrong!

[afrahthahir]

Sir I would like to know how can I detect objects from rtsp link of the live cctv feed using yolov5?

[zarafshantariq]

Plzz make a video on face mask and social distance on yolov5 in pycharm editor

[ahuman]

Hi sir, can you please do one tutorial to deploy yolov5 using taco datasets? I face many problems with it.

[zainulhaq]

Thanks for this video. Can you tell me how can I set the confidence level here while making the predictions ?

[hankeylankey]

Could you make a video on processing live window capture with a trained model? I've been trying to figure out a method for my own model which involves a video game. I know some other creators have used usb video capture devices to run through the model. I thought to loop windowcapture screenshots then process them through the model in real time, not sure how that will affect fps although.

[melissagabay]

Hey Nicolai its an amazing vudeo and very comprehensible. Could you please share the link of the code?

[fernandobarajas]

Hey Nicolai. Amazing video. Your content is really helpful for me. Quick question - How can i read a model with onnx and opencv, is posible?

[jamadarzoya]

If I have custom object detection model what changes should I make in the def load_model(self): function ??

[LimChinHong-jufo]

Hi Nicolai, great video and I learn a lot! May I know that is it possibe for me to create a python class that can load the .pt file from yolo and return the number of classes, the classes names, and class identifier?

[Inspiration_video]

How to define roi in this model. Actually I want to detect the objects in only the roi area using ip camera

[jstransportation]

I got a bad results when i used on a video but then I did screenshot on that video and used a model on that screenshot picture, I got a good result. Why the detected result on images are better than video or stream at a same frame?

[reza]

Please teach deep learning and machine vision in C ++ with pytorch c++

[snehitvaddi]

Nicolai, wouldn't it be easier and more convenient, to provide a direct link to the relevant code rather than your Github profile?

[qusaybtoush]

from where you got the data, like train and test ?

[aradalterfire]

where can i see the python code ? cant find it in the github

[benyajamiu]

But how to we use Video, if its not YouTube sir?