Yolov3 Object Detection Tutorial #6 - Deploying Your Model | OpenCV Python | Computer Vision 2020

Want to Learn YOLOv7 and solve real-world problems?
====================

Yolo v3 Tutorial #6 - Deploying Your Neural Network model using OpenCV Python in this Computer Vision tutorial:

In the last lecture, I showed you how to train YoloV3. Today you are going to be learning how to execute the trained Yolov3 weights for your own objection detector, using PyTorch. As you may know, we have already established the base for our PyTorch YoloV3 in the first lecture and the results were great.

I will also show how you take the new weights from Supervisely, and run the Xbox, PlayStation object detector with GPU acceleration. As you can see from this demo, the detector works quite well, considering that we have less than 200 images for each class.

If you implemented data augmentation, your results will be much better. I will show you a video in a following lecture to compare the results of the trained YoloV3 with and without data augmentation.

Okay so let’s start with the deploying our YoloV3 gaming console detector.

------------------------------------------------------------
Support us on Patreon
Chat to us on Discord
Interact with us on Facebook
Check my latest work on Instagram
Learn Advanced Tutorials on Udemy
------------------------------------------------------------
To learn more on Artificial Intelligence, Augmented Reality IoT, Deep Learning FPGAs, Arduinos, PCB Design and Image Processing then check out

Please Like and Subscribe for more videos :)

[HemangJoshi]

Please make more like this videos. Your videos are awesome.

[joelchristian]

Thank you so much that you put this course on Youtube for free.
This has helped me to complete the final year project of my engineering.
You are GREAT!!!

[purushottam]

You're videos are brilliant!
Thank you!

[woosal-kctr]

Where can we get the demo video of xbox and playstation?

[songhoyun]

Thank you for your nice lecture.
It had to be applied to a project that was currently in progress.
So, I waited for the today lecture more than anyone else.
Is it possible to augmentation image at Supervise.ly?
Could you let me know if you have any documentation or links what to do?
Thank you again for taking a good lecture.

[csproject]

Did you change anyth8ing from the video_demo.py file or the darknet.py?

[machain]

Thanks for the videos, man. I am interested joining your AI curses.

[janhavimasodkar]

Nice Video! can you please tell me how can we deploy a yolov3 project on server??? Please respond🥺🥺

[JohnSmith-rnvl]

I've been programming for 12 years .... i liked this series but you left out the most interesting part which is how to get the final results out from the code to use in other apps and languages. The most interesting thing about object detection is being able to fire events when the object you are looking for is detected but you didn't cover how you could do that which was a pity. Otherwise quite interesting.

[kumarpavan]

Hello, Could you give your udemy link to join in your course.

[jacobhellmark]

hi when i run the code with my own wight i keep getting this error what can i do about it? thanks
Traceback (most recent call last):
File "cam_demo.py", line 151, in <module>
list(map(lambda x: write(x, orig_im), output))
File "cam_demo.py", line 151, in <lambda>
list(map(lambda x: write(x, orig_im), output))
File "cam_demo.py", line 47, in write
label = "{0}".format(classes[cls])
IndexError: list index out of range

[machain]

Can you please upload your .json, .cfg and your .weights file?

[poloalo]

cont_msg=CUDA Error: no kernel image is available for execution on the device
what is this error during training

[rakumarudu]

What is the process to use the supervisely Models on Movidius stick?