Train YOLO-NAS - SOTA Object Detection Model - on Custom Dataset

Подписаться 37 тыс.

Просмотров 18 тыс.

50% 1

Discover the power of YOLO-NAS, Deci's next-generation object detection model, in this comprehensive guide. We'll walk you through the Python setup, installing YOLO-NAS, running inferences with the pre-trained COCO model, and even training YOLO-NAS on your custom dataset. Dive into the superior real-time object detection capabilities of this game-changing model and learn how to use it to optimize your own AI projects.
Chapters:
00:00 Introduction and Model Overview
01:57 Python Environment Setup and Installing YOLO-NAS
04:56 Inference with pre-trained COCO model
07:21 YOLO-NAS Inference Output Format
09:06 Finding Open-source Datasets
10:19 Training YOLO-NAS on Custom Dataset
16:34 Evaluate Trained Model
17:28 Inference with Trained Model
18:39 Conclusion
Resources:
🌏 Roboflow: roboflow.com
🌌 Roboflow Universe: universe.roboflow.com
📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks
📚 How to Train YOLO-NAS on a Custom Dataset blog post: blog.roboflow.com/yolo-nas-ho...
📓 How to Train YOLO-NAS on a Custom Dataset notebook: colab.research.google.com/git...
❓ Why do we need to restart Google Colab? github.com/obss/sahi/discussi...
🎬 YOLOv8: How to Train for Object Detection on a Custom Dataset: • YOLOv8: How to Train f...
Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀
#YOLO_NAS #Deci #ObjectDetection #NeuralArchitectureSearch #Python #COCO #MachineLearning #ArtificialIntelligence #CustomDataset #Inference #ModelEvaluation #OpenSource #Datasets

Наука

Опубликовано:

5 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 98

@elbaz_afandy Год назад

error ImportError Traceback (most recent call last) in () ----> 1 from super_gradients.training import models 2 3 model = models.get(MODEL_ARCH, pretrained_weights="coco").to(DEVICE) 13 frames /usr/local/lib/python3.10/dist-packages/PIL/ImageFont.py in 36 from . import Image 37 from ._deprecate import deprecate ---> 38 from ._util import is_directory, is_path 39 40 ImportError: cannot import name 'is_directory' from 'PIL._util' (/usr/local/lib/python3.10/dist-packages/PIL/_util.py)

@elbaz_afandy Год назад

solution install at first !pip install --upgrade pillow==6.2.2

@Roboflow Год назад

@@elbaz_afandy ir just restart the environment :) Does that fix with pillow==6.2.2 work? I tried that and it didn't :/

@elbaz_afandy Год назад

@@Roboflow you maybe correct, just restating is the problem solution

@Roboflow Год назад

@@elbaz_afandy I'll pin your comment. I expect others may face similar issues.

@seroshmannan Год назад

restart runtime

@yashrathod5614 Год назад

This tutorial is awesome I was successfully able to train the model. Also I would like to see a video on model selection too. Thank you so much for such an amazing work. ❤

@user-us2lf2kv9h Год назад

best yolo NAS custom dataset tutorial , ever !

@Roboflow Год назад

Haha thanks a lot 🙏🏻! Part 2 coming soon!

@vivaliberte Год назад

Thanks Peter. I just start to try it on my dataset.

@SinMxchine Год назад

As someone that's just getting into this, I really like how user friendly Roboflow is. Only thing stopping me from continuing to use it unfortunately is the price point per month on top of only allowing 5,000 images per month with the paid plan. I really wish you all had 4 tiers. Free can stay the same, add the first paid plan for $100 that gives users 4K images, mid tier plan for $200 that gives users 8K images, and top tier plan for $250 that give 10K images + some extra bonuses. This is more competitive imo and would bring more people to the platform over finding cheaper alternatives that allow more freedom to try out multiple new things. I could see you guys being the top dog in this market with how easy setup is and with your RU-vid guides which are easy and fast to understand. It's that price point to image ratio that is truly killing me here.

@TheEBcodkings Год назад

please make a video on model selection, its a great idea!

@Roboflow Год назад

That’s what I wanted to hear 🙏🏻

@marilynlucas5128 Год назад

Amazing channel. I am enjoying your work a lot. Keep it up

@Roboflow Год назад

Thanks a loooot!

@liliyalopez8998 10 месяцев назад

Clear instructions and a very well-documented Google Colab notebook. Thank you!

@Roboflow 10 месяцев назад

Thanks for watching 🙏🏻

@ParthPatel-vi5hi 9 месяцев назад

@@Roboflow heyy, so while i execute trainer, my session is getting crashed automatically... any solutions for that

@crusaix Год назад

super good video! very interested in the model selections

@Roboflow Год назад

Awesome! Thanks a lot!

@petrykpyatochkin6050 Год назад

thank you for the video. Would be very interesting in model selection video. Thank you!

@Roboflow Год назад

Awesome! I see a lot of positive feedback for that idea.

@sulaimanmahmoud7120 Год назад

As usual 🎉🎉 Hero

@Roboflow Год назад

Thanks a lot! 🙏

@irinahetman Год назад

Hi Piotr! Greetings from Middle Earth. Yes please, I would like to know more on different models selection depending on use case.

@Roboflow Год назад

Looks like we will do video about it within the next 2 weeks.

@bhooshandeshpande6982 Год назад

Definitely need a video on model selection

@Roboflow Год назад

hahaha working on it :D

@fazlehasan9428 Год назад

Yes we want a video on model selection please make it

@Roboflow Год назад

Hi, it is Peter from the video. We discussed this idea yesterday. I don't want to promise anything but it looks like we will release this video in the next 2 weeks.

@irfankobber7097 Год назад

You should make a video on training the model. The entire process till it achieves good result

@shubhamkapadia6337 Год назад

Is there any activation function used in YOLO NAS. If yes, which one and where can I find that information?

@sarahhesham6309 Год назад

Also, my dataset images are of size not equal to 640x640 , where can I apply this in the coding?

@victorarayal Год назад

Is it possible to connect archives in my local Notebook to googoe colab? Or you just have all in Google drive?

@sarahhesham6309 Год назад

What extension can my custom dataset have? I saw you using yolov5 as extension, is yolov8 also valid??

@user-qr3yi8xx5m 4 месяца назад

is there any need to define TensorBoard ? or it's automatically connected when model is finished ?

@user-jo2zb1rp5w Год назад

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

@mxmolina Год назад

It's there a way we can create a real example from this? I have a football 360 video from my son playing 9v9. The idea would be to keep the focus on the ball/play using Yolo Nas. It's that even possible?

@helloansuman Год назад

How to train this on 8 GPUs on DGX A100?

@judeloza1554 5 дней назад

For those of you having issues with the Visualize Inference Result section of the Colab below I have an updated version that should extinguish any errors. import supervision as sv import numpy as np import cv2 import matplotlib.pyplot as plt # Assuming result.prediction contains the predictions and result.class_names contains the class names detections = sv.Detections( xyxy=result.prediction.bboxes_xyxy, confidence=result.prediction.confidence, class_id=result.prediction.labels.astype(int) ) # Create BoxAnnotator object box_annotator = sv.BoxAnnotator() # Annotate the image annotated_frame = box_annotator.annotate( scene=image.copy(), detections=detections ) # Generate labels labels = [ f"{result.class_names[class_id]} {confidence:0.2f}" for confidence, class_id in zip(result.prediction.confidence, result.prediction.labels.astype(int)) ] # Add labels to the annotated frame for (bbox, label) in zip(result.prediction.bboxes_xyxy, labels): x_min, y_min, x_max, y_max = bbox cv2.putText( annotated_frame, label, (int(x_min), int(y_min) - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 255, 255), 2 ) # Convert the image from BGR to RGB annotated_frame_rgb = cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB) # Display the annotated image %matplotlib inline plt.figure(figsize=(12, 12)) plt.imshow(annotated_frame_rgb) plt.axis('off') plt.show()

@cutepuppies6483 Год назад

Please post the second part❤❤

@Roboflow Год назад

Hi, it is Peter from the video! 👋 I hope I will be able to give you this video.

@michaelscheinfeild9768 Год назад

can you explain how to train on my dataset , how to organize images and ground truth. also how i add different augmentations.

@greyyshellirl 2 месяца назад

Does this work in detecting real time with camera? And If i can ask, how to?

@albertofernandez055 Год назад

Hi Piotr, very good video. I like also your supervision package and all the notebooks you have been publishing in roboflow. Just one quick question: I have trained YOLO NAS (small version) with a custom dataset. I have seen that inference (CPU) is quite slow. I mean, compared to YOLO V5 or 8 it is much slower. Have you also noticed this? Many thanks!

@Roboflow Год назад

I noticed that too. But I have not investigated that issue :/ I accidentally stumbled on that issue when I loaded the model on the CPU and not on GPU. Did you try the quantized version too?

@FahadRamzan-ri4cr 9 месяцев назад

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. super-gradients 3.3.0+master requires pyparsing==2.4.5, but you have pyparsing 2.4.7 which is incompatible.

@mikeazatov1537 Год назад

Thanks for the tutorial! Is there a way to change the input dimensions? The default is (640,640) and I wanted to try out the larger size.

@varunlw 9 месяцев назад

I think u can directly pass it directly and YoloNAS will update its parameter accordingly. I am using 480*640 image size and it working great !

@raffelravionaldo463 Год назад

may i know how to prepare the data before do training with my own images?

@kachaicheung9073 5 месяцев назад

Now the model can't train the model, is the recent update problems?

@user-lu7zd4tm5w Год назад

Thanks a lot for the great work. May I ask for a video tutorial on how to port the YOLOv8 Python app to the Android platform, with people recognition through the phone's camera?

@Roboflow Год назад

If you can, please add this to the list of ideas submitted by the community: github.com/roboflow/notebooks/discussions/categories/video-ideas

@user-ow8nz8xj1w Год назад

Thank You for awesome video, can we use any other pretrained model instead of coco? If any documentation are there please provide me. Thank you so much

@Roboflow Год назад

To the best of my knowledge, no.

@techwithdk6048 Год назад

Im getting below error AttributeError: 'Trainer' object has no attribute 'train_loader' in below code trainer.train(model=model, training_params=train_params, train_loader=train_data, valid_loader=val_data) any reason

@youssefkhaled5331 Год назад

there is a line code in the middel of the notebook import trainer I think that u miss tht

@danielarmandovidalsoroa7787 3 месяца назад

For some reason, this instruction does not work anymore: result = list(model.predict(image, conf=0.35))[0] ----> 4 result = list(model.predict(image, conf=0.35))[0] TypeError: 'ImageDetectionPrediction' object is not iterable I did this instead and it worked result = model.predict(image, conf=0.35) Perhaps the output format from the model has changed during these 11 months, idk. I'm just leaving this here in case others find the same problem

@danielarmandovidalsoroa7787 3 месяца назад

Apparently the sv.Detections class has also changed over these months so this instruction does not work anymore: labels = [ f"{result.class_names[class_id]} {confidence:0.2f}" for _, _, confidence, class_id, _ in detections ] ValueError: too many values to unpack (expected 5) Instead, you have to unpack six values 👍: labels = [ f"{result.class_names[class_id]} {confidence:0.2f}" for _, _, confidence, class_id, _, _ in detections ]

@grecielcasi9200 2 месяца назад

@@danielarmandovidalsoroa7787 thank you so much for providing that information!

@fintech1378 5 месяцев назад

can you cover Llava on video streaming

@Sandykrang Год назад

Hey, great explanation. Is there we have to annotate the testing dada too?

@Roboflow Год назад

Could you elaborate on the question?

@Sandykrang Год назад

@@Roboflow hey thanks for the reply, I am just confused about that, we are here annotating the test data labels too. Then feeding to the model, then where is the learning of the model? How will it make predictions like yolov8?

@benlerer87 Год назад

I would like you to compare it to yolov5/v8 (better to test it on small objects). ty

@Roboflow Год назад

Hopefully, we will be able to do in one of the upcoming RU-vid videos

@hendihart5195 11 месяцев назад

cant open the link anymore

@user-qt7bt6wg8l 5 месяцев назад

I don't know if u'll see the comment or not 😅, but can we use yolo nas on android for object detection. If yes, pls can you make a video on this?

@user-sg6tw4hx3o Год назад

hey bro can we do semantic segmentation using the new YOLO NAS model

@Roboflow Год назад

Nope. It only gives you object detection. At least for now.

@cutepuppies6483 Год назад

And one video about comparison between yoloV8 and Yolo-NAS based on Accuracy

@Roboflow Год назад

We were thinking about doing a video like that. I'm actually curious how many people would be interested.

@alexpandian7402 Год назад

pls make video on model selection

@Roboflow Год назад

Looks like we will make one within the next 2 weeks. Stay tuned!

@DigiDriftZone Год назад

If you want to detect objects like small pieces of trash/garbage, wound out use a pre-trained model or start from scratch? What are some examples for starting from scratch and using pre-trained? - with your football players, if you don’t want to detect anything else like what’s in the coco set, why use pre-trained model? Maybe you can cover it in your upcoming model selection video 😅

@st43r62 Год назад

do you know how to detect with pre-trained model but with excluded classes so not all classes will be detected?

@user-ts8tw8lv1p 5 месяцев назад

where is pt file downoad

@NeuralNetwork-go5zn Год назад

hello, really nice tutorial! I created a custom yolo detection with yolov8m as a base, but when I run it, as soon as the speed of the objects increases, the algorithm loses track of me and starts to "jerk" the video output. Does anyone have an idea how to fix this? (yolov8m algorithm trained on 300 custom images) Thanks so much to anyone who can help me!!

@Roboflow Год назад

Someone today reported a similar problem in the discussions tab on GitHub. Was it you?

@NeuralNetwork-go5zn Год назад

@@Roboflow yes, sorry

@Roboflow Год назад

@@NeuralNetwork-go5zn I'll make sure to respond on GH as soon as possible.

@NeuralNetwork-go5zn Год назад

@@Roboflow thank yuo!

@ItayHilel Год назад

part 2

@Roboflow Год назад

Soon!

@Manasobura Год назад

create yolo gui app, please

@st43r62 Год назад

Hey Piotr, could you please me? i want to try make object detection on pretrained YoloNasL model but i need to exclude some classes for example class person /// model = models.get(MODEL_ARCH, pretrained_weights="coco").to(DEVICE) image = cv2.imread(SOURCE_IMAGE_PATH) result = list(model.predict(image, conf=0.35))[0] /// how can i set some properties of model like class_names at give array with class names to that property? i checked all properties but didnt find out where or how i can exclude some yolo classes i would be extremely grateful if you try to help thanks in advance!!

@user-ts8tw8lv1p 5 месяцев назад

pt file ?

@Roboflow 5 месяцев назад

Could you be a bit more specific?

@mautushidas8368 11 месяцев назад

ds = sv.Dataset.from_yolo( images_directory_path=f"{dataset.location}/test/images", annotations_directory_path=f"{dataset.location}/test/labels", data_yaml_path=f"{dataset.location}/data.yaml", force_masks=False ) This one is not working

@tomii5644 4 месяца назад

ds =sv.DetectionsDataset.from_yolo(

@varunlw 10 месяцев назад

Getting below error at the time of installation. Installing build dependencies ... done Getting requirements to build wheel ... done Preparing metadata (pyproject.toml) ... done error: subprocess-exited-with-error × Building wheel for pycocotools (pyproject.toml) did not run successfully. │ exit code: 1 ╰─> See above for output. note: This error originates from a subprocess, and is likely not a problem with pip. Building wheel for pycocotools (pyproject.toml) ... error ERROR: Failed building wheel for pycocotools ERROR: Could not build wheels for pycocotools, which is required to install pyproject.toml-based projects