Commencer

YOLO-NAS

Mise à jour importante

Deci, le créateur initial de YOLO-NAS, a été racheté par NVIDIA, et Deci ne maintient plus activement ces modèles. Ultralytics continue de les prendre en charge, mais aucune autre mise à jour de l’équipe d’origine n’est attendue.

Présentation#

Développé par Deci AI, YOLO-NAS est un modèle de détection d’objets issu de la recherche d’architectures neuronales et conçu pour remédier aux limites des anciens modèles YOLO. Il améliore la prise en charge de la quantification et les compromis entre précision et latence.

Comparaison de la précision du modèle YOLO-NAS sur le benchmark COCO Présentation de YOLO-NAS. YOLO-NAS utilise des blocs adaptés à la quantification et une quantification sélective afin de préserver la précision après quantification. Lorsqu’il est converti en version quantifiée INT8, le modèle perd peu en précision, ce qui constitue une amélioration par rapport aux anciens modèles YOLO.

Fonctionnalités clés#

  • Bloc de base adapté à la quantification : YOLO-NAS introduit un nouveau bloc de base adapté à la quantification, qui remédie à l’une des principales limites des précédents modèles YOLO.
  • Entraînement et quantification avancés : YOLO-NAS utilise des stratégies d’entraînement avancées et la quantification après entraînement pour améliorer ses performances.
  • Optimisation AutoNAC et préentraînement : YOLO-NAS utilise l’optimisation AutoNAC et est préentraîné sur des jeux de données tels que COCO, Objects365 et Roboflow 100. Ce préentraînement le rend particulièrement adapté aux tâches de détection d’objets en aval dans un environnement de production.

Modèles préentraînés#

Ultralytics propose des modèles YOLO-NAS préentraînés en trois tailles, chacune offrant un compromis différent entre vitesse et précision :

Performances
ModèlemAP50-95Latence (ms)
YOLO-NAS S47.53.21
YOLO-NAS M51.555.85
YOLO-NAS L52.227.87
YOLO-NAS S INT-847.032.36
YOLO-NAS M INT-851.03.78
YOLO-NAS L INT-852.14.78

Chaque variante de modèle est conçue pour équilibrer la précision moyenne moyenne (mAP) et la latence, afin de t’aider à optimiser tes tâches de détection d’objets en matière de performances et de vitesse.

Exemples d'utilisation#

Le paquet Python ultralytics fournit une API Python et une interface CLI pour exécuter les modèles YOLO-NAS.

Les modèles YOLO-NAS nécessitent le paquet super-gradients, qui requiert un environnement Python 3.10 :

pip install ultralytics super-gradients "setuptools<81"

Les exemples suivants montrent comment utiliser les modèles YOLO-NAS avec le paquet ultralytics pour l’inférence et la validation :

Exemples d’inférence et de validation#

Dans cet exemple, nous validons YOLO-NAS-s sur le jeu de données COCO8.

Exemple

Cet exemple présente du code simple pour l’inférence et la validation de YOLO-NAS. YOLO-NAS prend également en charge l’export, mais le paquet ultralytics ne permet pas de l’entraîner.

Les fichiers de modèle *.pt préentraînés avec PyTorch peuvent être transmis à la classe NAS() pour créer une instance de modèle en Python :

from ultralytics import NAS

# Charger un modèle YOLO-NAS-s préentraîné sur COCO
model = NAS("yolo_nas_s.pt")

# Afficher les informations du modèle (facultatif)
model.info()

# Valider le modèle sur le jeu de données d’exemple COCO8
results = model.val(data="coco8.yaml")

# Lancer l’inférence avec le modèle YOLO-NAS-s sur l’image 'bus.jpg'
results = model("path/to/bus.jpg")

Tâches et modes pris en charge#

YOLO-NAS existe en trois variantes : Small (s), Medium (m) et Large (l). Chaque variante est conçue pour répondre à différents besoins en matière de calcul et de performances :

  • YOLO-NAS-s : optimisé pour les environnements où les ressources de calcul sont limitées, mais où l’efficacité est essentielle.
  • YOLO-NAS-m : offre un compromis équilibré, adapté à la détection d’objets généraliste avec une précision supérieure.
  • YOLO-NAS-l : adapté aux scénarios exigeant une précision maximale, où les ressources de calcul sont moins limitées.

Voici un aperçu détaillé de chaque modèle, avec des liens vers ses poids préentraînés, les tâches prises en charge et sa compatibilité avec les différents modes de fonctionnement.

Type de modèlePoids préentraînésTâches prises en chargeEntraînementValidationInférenceExport
YOLO-NAS-syolo_nas_s.ptDétection d'objets❌✅✅✅
YOLO-NAS-myolo_nas_m.ptDétection d'objets❌✅✅✅
YOLO-NAS-lyolo_nas_l.ptDétection d'objets❌✅✅✅

Citations et remerciements#

Si tu utilises YOLO-NAS dans tes travaux de recherche ou de développement, cite SuperGradients :

Citation
@misc{supergradients,
      doi = {10.5281/ZENODO.7789328},
      url = {https://zenodo.org/records/7789328},
      author = {Aharon,  Shay and {Louis-Dupont} and {Ofri Masad} and Yurkova,  Kate and {Lotem Fridman} and {Lkdci} and Khvedchenya,  Eugene and Rubin,  Ran and Bagrov,  Natan and Tymchenko,  Borys and Keren,  Tomer and Zhilko,  Alexander and {Eran-Deci}},
      title = {Super-Gradients},
      publisher = {GitHub},
      journal = {GitHub repository},
      year = {2021},
}

Nous remercions l’équipe SuperGradients de Deci AI pour ses efforts de création et de maintenance de cette ressource précieuse pour la communauté de la vision par ordinateur.

FAQ#

  • YOLO-NAS, développé par Deci AI, est un modèle de détection d’objets conçu à l’aide de la recherche d’architectures neuronales (NAS). Il répond aux limites des modèles YOLO précédents en introduisant des fonctionnalités comme des blocs de base adaptés à la quantification et des schémas d’entraînement avancés, qui améliorent les performances, en particulier dans les environnements aux ressources de calcul limitées. YOLO-NAS prend aussi en charge la quantification et conserve une précision élevée même lorsqu’il est converti en version INT8, ce qui le rend mieux adapté aux environnements de production.

  • Tu peux intégrer les modèles YOLO-NAS à ton application Python à l’aide du paquet ultralytics. Voici un exemple simple de chargement d’un modèle YOLO-NAS préentraîné et d’exécution de l’inférence :

    from ultralytics import NAS
    
    # Charger un modèle YOLO-NAS-s préentraîné sur COCO
    model = NAS("yolo_nas_s.pt")
    
    # Valider le modèle sur le jeu de données d’exemple COCO8
    results = model.val(data="coco8.yaml")
    
    # Lancer l’inférence avec le modèle YOLO-NAS-s sur l’image 'bus.jpg'
    results = model("path/to/bus.jpg")

    Pour en savoir plus, consulte les exemples d’inférence et de validation.

  • YOLO-NAS présente plusieurs fonctionnalités clés qui en font un excellent choix pour la détection d’objets quantifiée :

    • Bloc de base adapté à la quantification : architecture améliorée qui préserve la précision après quantification.
    • Entraînement et quantification avancés : utilise des stratégies d’entraînement avancées et des techniques de quantification après entraînement.
    • Optimisation AutoNAC et préentraînement : utilise l’optimisation AutoNAC et est préentraîné sur des jeux de données comme COCO, Objects365 et Roboflow 100.

    Ces fonctionnalités contribuent à sa grande précision, à ses performances efficaces et à son adéquation au déploiement en production. Pour en savoir plus, consulte la section Fonctionnalités clés.

  • Les modèles YOLO-NAS prennent en charge la détection d’objets dans les modes de validation, d’inférence et d’exportation. Ils ne prennent pas en charge l’entraînement. Les modèles pris en charge sont YOLO-NAS-s, YOLO-NAS-m et YOLO-NAS-l, chacun étant adapté à différentes capacités de calcul et exigences de performances.

  • Oui, Ultralytics propose des modèles YOLO-NAS préentraînés auxquels tu peux accéder directement. Ces modèles sont préentraînés sur des jeux de données comme COCO. Tu peux les télécharger à l’aide des liens de la section Tâches et modes pris en charge. En voici quelques exemples :

Commentaires21

Pose une question, partage tes résultats ou aide quelqu’un d’autre.

  1. riobastian09GitHub

    Hi. i want to know is there any pre-configured of YOLO-NAS model? i want to use this to my experiment using the custom architecture YOLO-NAS model. Thank you!

    1. Glenn JocherUltralytics

      @riobastian09 thank you for your question! Yes, pre-configured YOLO-NAS models, such as YOLO-NAS-s, YOLO-NAS-m, and YOLO-NAS-l, are available and optimized for inference, validation, and export. You can access these pre-trained models and easily integrate them into your experiments using the Ultralytics Python package. Unfortunately, custom architecture modifications or training directly with YOLO-NAS are not supported. For more, refer to the YOLO-NAS documentation: https://docs.ultralytics.com/models/yolo-nas/

  2. User

    您好,我使用如下脚本将torch模型转成onnx模型时,出现如下错误: raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'") AttributeError: 'YoloNAS_S' object has no attribute 'args'我该如何解决?

    1. User

      from ultralytics import NAS model = NAS('yolo_nas_s') model.export( imgsz = [480,640], format = "onnx", simplify = True, opset = 17 )

    2. Glenn JocherUltralytics

      @Stephen-Hao it seems like the error you're encountering is due to the 'args' attribute not being present in the 'YoloNAS_S' object. This might be related to the specific version of the model or the Ultralytics package you are using. Please ensure you have the latest version of the Ultralytics package installed. If the issue persists, consider checking the model's documentation or reaching out to the community for further assistance.

  3. NoviceAlchemistGitHub

    我训练使用的代码是:import torch import warnings from ultralytics import YOLO

    忽略与“deterministic”和“non-deterministic”相关的所有警告

    warnings.filterwarnings("ignore", category=UserWarning, message=".deterministic.")

    if name == 'main': # 关闭PyTorch的确定性算法 torch.use_deterministic_algorithms(False)

    # 初始化YOLO模型
    # model_path = r'D:\ultralytics-main\ultralytics\cfg\models\v8\yolov8_attiton.yaml'
    model_path = r'D:\ultralytics-main\model train\model\yolo_nas_s.pt'
    model = YOLO(model_path)
    
    # 设置正确的数据集路径
    data_path = r"C:\Users\13579\Downloads\etiketlenmis_3.v6i.yolov8\data.yaml"
    
    # 训练模型配置信息
    model.train(data=data_path,
                imgsz=640,
                batch=32,
                epochs=200,
                name='NAS_S',
                )
    
    # 设置验证集验证效果
    # model.val()

    但是会出现D:\Anaconda3\envs\yolov8\python.exe "D:\ultralytics-main\model train\My train\yolo nas.py" The console stream is logged into C:\Users\13579\sg_logs\console.log [2024-09-06 10:23:49] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it [2024-09-06 10:23:49,572] torch.distributed.elastic.multiprocessing.redirects: [WARNING] NOTE: Redirects are currently not supported in Windows or MacOs. [WARNING]No module named 'pycocotools' [2024-09-06 10:23:51] WARNING - env_sanity_check.py - Failed to verify operating system: Deci officially supports only Linux kernels. Some features may not work as expected. WARNING ⚠️ The file 'D:\ultralytics-main\model train\model\yolo_nas_s.pt' appears to be improperly saved or formatted. For optimal results, use model.save('filename.pt') to correctly save YOLO models. Traceback (most recent call last): File "D:\ultralytics-main\model train\My train\yolo nas.py", line 15, in model = YOLO(model_path) File "D:\ultralytics-main\ultralytics\models\yolo\model.py", line 23, in init super().init(model=model, task=task, verbose=verbose) File "D:\ultralytics-main\ultralytics\engine\model.py", line 149, in init self._load(model, task=task) File "D:\ultralytics-main\ultralytics\engine\model.py", line 230, in _load self.model, self.ckpt = attempt_load_one_weight(weights) File "D:\ultralytics-main\ultralytics\nn\tasks.py", line 855, in attempt_load_one_weight ckpt, weight = torch_safe_load(weight) # load ckpt File "D:\ultralytics-main\ultralytics\nn\tasks.py", line 809, in torch_safe_load ckpt = {"model": ckpt.model} File "D:\Anaconda3\envs\yolov8\lib\site-packages\torch\nn\modules\module.py", line 1695, in getattr raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'") AttributeError: 'YoloNAS_S' object has no attribute 'model'

    进程已结束,退出代码为 1

    这个怎么解决呀

    1. Glenn JocherUltralytics(modifié)

      @NoviceAlchemist YOLO-NAS models in Ultralytics are pretrained and support only validation, inference and export, not training (see the Training column in the YOLO-NAS docs), so model.train() isn't available for yolo_nas_s.pt. To train on your own dataset, use a model with training support such as YOLO26 (e.g. yolo26s.pt). If you hit model-loading errors, verify that pycocotools is installed and try the latest version of the Ultralytics package.

  4. dota2015GitHub

    from ultralytics import NAS import cv2

    Load a COCO-pretrained YOLO-NAS-s model

    model = NAS('yolo_nas_s.pt')

    Display model information (optional)

    model.info() results = model.predict('000000000009.jpg')

    run reslult:

    C:\Users\makef.conda\envs\yolov8\python.exe -X pycache_prefix=C:\Users\makef\AppData\Local\JetBrains\PyCharm2023.3\cpython-cache "C:/Program Files/JetBrains/PyCharm 2023.3.4/plugins/python/helpers/pydev/pydevd.py" --multiprocess --qt-support=auto --client 127.0.0.1 --port 62105 --file D:\02Code\code\yolov8\v8_2\yolo_nas.py Connected to pydev debugger (build 233.15026.15) The console stream is logged into C:\Users\makef\sg_logs\console.log [2024-04-28 16:29:38] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it [2024-04-28 16:29:39] WARNING - redirects.py - NOTE: Redirects are currently not supported in Windows or MacOs. [WARNING]No module named 'pycocotools' [2024-04-28 16:29:45] WARNING - env_sanity_check.py - Failed to verify operating system: Deci officially supports only Linux kernels. Some features may not work as expected. Model summary: 685 layers, 19053888 parameters, 19053888 gradients

    Traceback (most recent call last): File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\torch\autograd\grad_mode.py", line 43, in generator_context response = gen.send(None) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\engine\predictor.py", line 228, in stream_inference self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz)) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\nn\autobackend.py", line 624, in warmup self.forward(im) # warmup File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\nn\autobackend.py", line 450, in forward y = self.model(im, augment=augment, visualize=visualize, embed=embed) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) TypeError: forward() got an unexpected keyword argument 'augment' python-BaseException

    Process finished with exit code 1

    1. Paula DerrengerUltralytics

      Hey there! 👋 It looks like you're encountering a TypeError related to the augment keyword argument when running inference with the YOLO-NAS model. The error suggests that the forward() method in the model doesn't recognize the augment argument. This could be due to an oversight in the code or an issue with the model's compatibility with the Ultralytics framework.

      Let's try running the model without any additional arguments that aren't expected. Here's how you can do it:

      from ultralytics import NAS
      
      # Load a COCO-pretrained YOLO-NAS-s model
      model = NAS('yolo_nas_s.pt')
      
      # Run inference with the YOLO-NAS-s model on the 'bus.jpg' image
      results = model('path/to/bus.jpg')

      This simplifies the call to the model's inference method by removing the augment argument, which seems to be causing the issue.

      If you continue to face problems or if the issue is due to something else, it might be a good idea to check the Ultralytics documentation for YOLO-NAS compatibility or raise an issue on the GitHub repository for more specific help! Hope this sorts it out for you! 😊

    2. dota2015GitHub(modifié)

      Hey there! So, I've decked out my project with all the latest packages, but guess what? The issue is still lurking like it's on a vacation!


      Here's the riveting tale of the pip upgrade:

      Downloading ultralytics-8.2.4-py3-none-any.whl (752 kB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 752.1/752.1 kB 28.1 kB/s eta 0:00:00 Installing collected packages: ultralytics Attempting uninstall: ultralytics Found existing installation: ultralytics 8.2.1 Uninstalling ultralytics-8.2.1: Successfully uninstalled ultralytics-8.2.1 Successfully installed ultralytics-8.2.4


      Behold, the saga of the runtime logs unfolds below:

      C:\Users\makef.conda\envs\yolov8\python.exe D:\02Code\code\yolov8\v8_2\yolo_nas.py The console stream is logged into C:\Users\makef\sg_logs\console.log [2024-04-29 10:42:17] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it [2024-04-29 10:42:18] WARNING - redirects.py - NOTE: Redirects are currently not supported in Windows or MacOs. [WARNING]No module named 'pycocotools' [2024-04-29 10:42:21] WARNING - env_sanity_check.py - Failed to verify operating system: Deci officially supports only Linux kernels. Some features may not work as expected. Model summary: 685 layers, 19053888 parameters, 19053888 gradients

      Behold, the saga of the runtime logs unfolds below: Traceback (most recent call last): File "D:\02Code\code\yolov8\v8_2\yolo_nas.py", line 10, in results = model.predict('000000000009.jpg') File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\engine\model.py", line 452, in predict return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\engine\predictor.py", line 168, in call return list(self.stream_inference(source, model, *args, **kwargs)) # merge list of Result into one File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\torch\autograd\grad_mode.py", line 43, in generator_context response = gen.send(None) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\engine\predictor.py", line 228, in stream_inference self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz)) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\nn\autobackend.py", line 627, in warmup self.forward(im) # warmup File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\nn\autobackend.py", line 453, in forward y = self.model(im, augment=augment, visualize=visualize, embed=embed) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) TypeError: forward() got an unexpected keyword argument 'augment'

      Process finished with exit code 1

    3. Paula DerrengerUltralytics(modifié)

      Hey there! 😄 It looks like you're having a bit of a rough ride with the augment argument not being recognized during prediction. No worries, let's tidy this up!

      The error message you're seeing is due to the augment argument being passed where it was not expected. It's a simple fix; you just need to ensure you're using the prediction functionality without this argument, like so:

      from ultralytics import NAS
      
      # Load the COCO-pretrained YOLO-NAS-s model
      model = NAS('yolo_nas_s.pt')
      
      # Run inference on an image
      results = model('path/to/000000000009.jpg')
      
      # To visualize the results, you can do:
      results[0].show()

      This should run smoothly and get your project back on track! If issues persist or you have further questions, feel free to reach out. And remember, for the latest and greatest on usage, our docs page is always there to help you out. Happy coding! 🚀

    4. dota2015GitHub

      I used your code, but the problem still persists, like a mischievous little gremlin playing hide and seek.

    5. Paula DerrengerUltralytics(modifié)

      Hey there! 🌟 It looks like that mischievous gremlin of an issue is quite stubborn. Not to worry, let's tackle it together.

      Based on your feedback and the details from the YOLO-NAS docs, it seems like you're on the right track. However, if you're still encountering issues with predictions or validation, it's possible there might be a version mismatch or a missing dependency, especially pycocotools which is crucial for dataset operations and was flagged in your logs.

      Firstly, please ensure you've installed pycocotools by running:

      pip install pycocotools-windows

      If you're not on Windows, just pycocotools should work.

      Moreover, the error regarding the augment argument not being expected might suggest an incompatibility issue or an outdated piece of code. Let's try simplifying the inference code snippet to not use this argument, as shown in the Ultralytics YOLO-NAS docs:

      from ultralytics import NAS
      
      # Load the COCO-pretrained YOLO-NAS-s model
      model = NAS('yolo_nas_s.pt')
      
      # Run inference with the YOLO-NAS-s model on a local image file
      results = model('path/to/bus.jpg')
      
      # Visualize the results
      results[0].show()

      This code directly uses the model without additional settings that may not be supported, like augment.

      If the problem continues, it could be helpful to check for updates to the Ultralytics package or consider reaching out on the GitHub issues page for more targeted support. Sometimes, issues like these have been encountered and solved by others in the community!

      Don't let those gremlins get you down; you're closer to a solution than you think! 🚀

  5. dota2015GitHub

    C:\Users\makef.conda\envs\yolov8\python.exe D:\02Code\code\yolov8\v8_2\yolo_nas.py The console stream is logged into C:\Users\makef\sg_logs\console.log [2024-04-28 16:27:19] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it [2024-04-28 16:27:20] WARNING - redirects.py - NOTE: Redirects are currently not supported in Windows or MacOs. [WARNING]No module named 'pycocotools' [2024-04-28 16:27:23] WARNING - env_sanity_check.py - Failed to verify operating system: Deci officially supports only Linux kernels. Some features may not work as expected. Model summary: 685 layers, 19053888 parameters, 19053888 gradients Traceback (most recent call last): File "D:\02Code\code\yolov8\v8_2\yolo_nas.py", line 10, in results = model.predict('000000000009.jpg') File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\engine\model.py", line 452, in predict return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\engine\predictor.py", line 168, in call return list(self.stream_inference(source, model, *args, **kwargs)) # merge list of Result into one File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\torch\autograd\grad_mode.py", line 43, in generator_context response = gen.send(None) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\engine\predictor.py", line 228, in stream_inference self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz)) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\nn\autobackend.py", line 624, in warmup self.forward(im) # warmup File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\ultralytics\nn\autobackend.py", line 450, in forward y = self.model(im, augment=augment, visualize=visualize, embed=embed) File "C:\Users\makef.conda\envs\yolov8\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) TypeError: forward() got an unexpected keyword argument 'augment'

    Process finished with exit code 1

    1. dota2015GitHub

      from ultralytics import NAS import cv2

      Load a COCO-pretrained YOLO-NAS-s model

      model = NAS('yolo_nas_s.pt')

      Display model information (optional)

      model.info()

      results = model.predict('000000000009.jpg')

    2. Paula DerrengerUltralytics

      Hey there! 👋 It looks like you're trying to run predictions with the YOLO-NAS model and encountered an issue regarding the augment argument in the forward() method. This error typically occurs if there's a version mismatch or if the model and method usage doesn't align with the expected input parameters.

      Based on your usage:

      from ultralytics import NAS
      import cv2
      
      # Load a COCO-pretrained YOLO-NAS-s model
      model = NAS('yolo_nas_s.pt')
      
      # Display model information (optional)
      model.info()
      
      results = model.predict('000000000009.jpg')

      It seems correct on the surface, suggesting it might be related to the version of Ultralytics library you're using or specific to the model's implementation.

      Here are a couple of steps you might want to try:

      1. Ensure you have the latest version of the Ultralytics package by running:
        pip install --upgrade ultralytics
      2. Check if the YOLO-NAS model you are using is compatible with the predict function in terms of its expected arguments. You can refer to the official Ultralytics documentation for the YOLO-NAS model and verify the correct method usage.

      If you're still facing issues, feel free to share more details, such as the specific error messages and your environment setup. Hopefully, this helps you move forward! 🚀

  6. Pragyy-GGitHub

    How to train out this Yolo-nas model? like fine tune it on custom dataset?

    1. Glenn JocherUltralytics(modifié)

      @Pragyy-G hey there! 🙌 YOLO-NAS in Ultralytics is limited to pretrained weights for inference, validation and export; training and fine-tuning aren't supported (see the Training column in the YOLO-NAS docs), and there is no Dataset class to import.

      To train on a custom dataset, use a model with full training support such as YOLO26:

      from ultralytics import YOLO
      
      model = YOLO("yolo26n.pt")
      model.train(data="path/to/data.yaml", epochs=100, imgsz=640)

      Your dataset should follow the expected format, with a YAML file defining the train/val paths and classes.

    2. ashish-reddy26GitHub

      Hi Glenn,

      I tried training with the provided information, but I am getting the error that says 'Dataset' cannot be imported from ultralytics. Is Ultralytics not providing the resources to Dataset?

      Can you clarify this and also please provide your inputs for training yolo-nas for object detection tasks (I am using yolov8 & yolov9, but I also want to try with yolo-nas as well).

      Thank you, Ashish

    3. Glenn JocherUltralytics(modifié)

      Hi Ashish,

      Dataset isn't a directly importable class from the ultralytics package. For custom training datasets, you structure your data in the expected format and use a YAML file to define paths and classes.

      YOLO-NAS in Ultralytics supports inference, validation and export only, not training, so to train on a custom dataset use a model like YOLO26. To validate YOLO-NAS:

      from ultralytics import NAS
      
      # Load the model
      model = NAS("yolo_nas_s.pt")
      
      # Validate the model
      results = model.val(data="path/to/your/data.yaml")

      Please ensure your dataset follows the structure expected by the Ultralytics framework and that the YAML file correctly points to your train and validation images and labels.