YOLO-NAS: Step by Step Guide To Custom Object Detection Training

In this computer vision tutorial video, we will train Yolo-NAS on a custom data set and test it over an unseen set.
The primary claim of Yolo-NAS is that it can detect small objects better than the previous models.
Although we can run several inference experiments to analyze the results, training it on a challenging data set will give us a better understanding.

What is YOLO-NAS?

YOLO-NAS is a game-changer in object detection model developed by Deci and delivers superior real-time object detection capabilities and production-ready for production. YOLO-NAS models outperformed models like YOLOv7, and YOLOv8, including the recently launched YOLOv6-v3.0.
Please refer to our previous video : "Introducing YOLO-NAS: One of The Most Efficient Object Detection Algorithms"

Topics Covered
✅The Object Detection Dataset to Train YOLO NAS
✅Train YOLO NAS on Custom Dataset
✅Fine Tuning YOLO NAS Models
✅Inference on Test Images using the Trained YOLO NAS Model
✅YOLO NAS Trained Model Video Inference Results

⭐️ Time Stamps:⭐️
00:00-00:28: Introduction
00:28-01:18: The Dataset
01:18-01:43: Annotations
01:43-10:50: Training the Models
10:50-11:08: Video Inference
11:08-11:30: Outro

Resources:

Processing, Image Classification, Object Detection, Face Detection, Face Recognition, YOLO, Segmentation, Pose Estimation, and many more using OpenCV(Python/C++), PyTorch, and TensorFlow.

🤖 Learn from the experts on AI: Computer Vision and AI Courses
YOU have an opportunity to join the over 5300+ (and counting) researchers, engineers, and students who have benefited from these courses and take your knowledge of computer vision, AI, and deep learning to the next level.🤖

#️⃣ Connect with Us #️⃣

🔖Hashtags🔖
#Yolo-NAS #Yolo #yolomodels #objectdetection #deeplearning #computervision #learnopencv #opencv #yolov8 #yolov7 #yolov5

[readbhagwatgeeta]

Can anyone please how to save the model after training on custom dataset, so that I don't have to train again and again for inference in different type of videos

[sadibhassan]

I can not find where the graphs are generated, even in their main github repo, i could not find any instructions where i can find the training graphs

[phibansabethnongkseh]

Whenever i try to run yolonas model in my jupyter notebook i always get error no module found for super gradient even after i have pip install super-gradients too how to solve this in jupyter notebook? Do we need to install additional library?

[.annisamutiarahman]

Hi, can i convert YOLOv8 model to YOLO NAS model

[janibashashaik]

How to get the live feed of the camera after training is completed?

[iyshwaryakannan]

Hi, how to filter out a specific class in YOLO-nas eg. if I want to detect only 'Person',
what should be modified here out = model.predict("/content/1.jpg", conf=0.25)

[jozbrpw]

Great! How to resume to training process if it pauses.

[janibashashaik]

you given the best files of the yolo nas. now i want to run in raspberry pi or jetson nano can you give the procedure or any suggestion for these.

[bahikhalil]

great guide, can anyone help me visualize the results like the p pr f1 score and the loss graphs other yolo models used to automatically generate the graphs after training but not yolo nas

[thangdaoxuan]

I have a YOLO NAS model for animal detection. I ran the model for 25 epochs and have got the best.pth weights. I need to add more epochs, to train it more from where i left off. I have read somewhere that YOLO V5 have such an option. Does YOLO NAS have the same option? If so how can i implement it in colab?

PS. It took me 10 - 15 hours to train for 25 epochs. So I am tight on time. I am not sure whether I am doing something wrong, but I am training using A100 GPU in Colab and its taking this much time. Please advice. I have 17.8 GB of data which has around 38790 images, so i guess it makes sense to take that much time?

I tried looking through the YOLO NAS documentation and google searched it, but couldn't get any concrete ideas.

[buzhrmj]

Can you provide the code to generate the graphs for training the model or can you explain how did you generated the graphs.

[ConsultingjoeOnline]

Is this any better than using Ultralytics Yolov8? That is what I use, very easy and less coding.

[akashparua]

Whenever I try to train the YOLO-NAS model on colab, the instance automatically restarts, can you suggest any solution?

[BPJennieYeager]

When I try to install super-gradients==3.1.1, I keep getting the following error:
Failed to build pycocotools
ERROR: Could not build wheels for pycocotools, which is required to install pyproject.toml-based projects

Anybody know how to solve this? Thanks.

[ameremortal]

Would you recommend object tracking for tracking a syringe in a botox training simulator? Or do you think the tech isn’t quite there for such small visual changes?

[sigmadews]

Would be possible to run YOLO NAS on edge devices like Jetson Nano?

[iyshwaryakannan]

how to import dataset from roboflow to train YOLO NAS, it would be great if you release a video on comparative analysis of YOLO models as you always do

[dharivinod]

How to use multiple GPUs for training?