Deploying Neural Networks with OpenCV DNN and GPU in Python: Achieving 100+ FPS Object Detection

preview_player
Показать описание

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 learn How To Deploy Neural Networks with OpenCV DNN and GPU in Python. We will go over each step in deploying trained neural networks for inference with OpenCV. We will see how to use the methods to load in neural networks with OpenCV and deploy them. At the end of the video, we will see an example with object detection, where we can detect a lot of different objects from the Coco dataset with 100 FPS+ on a GPU with OpenCV.

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:

_____________________________________________________________

Tags:
#OpenCVdnn #OpenCV #DNN #ObjectDetection #ComputerVision #DeepLearning
Рекомендации по теме
Комментарии
Автор

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

NicolaiAI
Автор

The hard part might be how to get a custom trained inference graph .pb file and .pbtxt file. It will be interesting if you make a video on that.

赛尼木
Автор

from where we get the file "forzen_inference_graph.pb" please, I tryied around but I could not find it!!! thank you in advance

baizid
Автор

hey bro thanks so much for this amazing video, can u make a video how we can deploy a custom model in tensorflow (instead of mobilenet) and convert it to pb and config formats and use it in opencv ?

ProfSoft
Автор

Hi! There is a mistake. The second pair of the bbox is the lower right corner of the bbox, not the width and height. Same in cv.rectangle, you should choose one diagonal and give the two ends of it.

ShowTsai
Автор

Hey Nicolai, it seems like you forgot to provide the following file to the GitHub repo pertaining to this example: "forzen_inference_graph.pb". Both the txt files are present but not the pb file. Would it be possible for us to get said file?

zrocity
Автор

Hey, do we need to compile opencv with CUDA support beforehands?

sherafati
Автор

from where we can get the file "forzen_inference_graph.pb" actually other files are available on GitHub but ı couldn't find this one

daphne
Автор

Where to get this frozen_interface file

MrNaved
join shbcf.ru