Empezar

YOLO-NAS

Actualización importante

Deci, creadora original de YOLO-NAS, ha sido adquirida por NVIDIA y Deci ya no mantiene activamente estos modelos. Ultralytics sigue ofreciendo compatibilidad, pero no se esperan más actualizaciones del equipo original.

Descripción general#

Desarrollado por Deci AI, YOLO-NAS es un modelo de detección de objetos creado mediante búsqueda de arquitecturas neuronales y diseñado para superar las limitaciones de los modelos YOLO anteriores. Mejora la compatibilidad con la cuantización y la relación entre precisión y latencia.

Comparación de la precisión del modelo YOLO-NAS en el benchmark COCO Descripción general de YOLO-NAS. YOLO-NAS utiliza bloques compatibles con la cuantización y cuantización selectiva para conservar la precisión después de cuantizar. Al convertirlo a su versión cuantizada INT8, el modelo pierde poca precisión, lo que supone una mejora respecto a modelos YOLO anteriores.

Características principales#

  • Bloque básico compatible con la cuantización: YOLO-NAS incorpora un nuevo bloque básico compatible con la cuantización, que resuelve una de las limitaciones importantes de los modelos YOLO anteriores.
  • Entrenamiento y cuantización avanzados: YOLO-NAS utiliza métodos de entrenamiento avanzados y cuantización posterior al entrenamiento para mejorar el rendimiento.
  • Optimización y preentrenamiento AutoNAC: YOLO-NAS utiliza la optimización AutoNAC y está preentrenado con conjuntos de datos como COCO, Objects365 y Roboflow 100. Este preentrenamiento lo hace idóneo para tareas de detección de objetos posteriores en producción.

Modelos preentrenados#

Ultralytics ofrece modelos YOLO-NAS preentrenados en tres tamaños, cada uno con un equilibrio diferente entre velocidad y precisión:

Rendimiento
ModelomAP50-95Latencia (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

Cada variante del modelo está diseñada para ofrecer un equilibrio entre la precisión media promedio (mAP) y la latencia, lo que te ayuda a optimizar tus tareas de detección de objetos tanto en rendimiento como en velocidad.

Ejemplos de uso#

El paquete de Python ultralytics proporciona una API de Python y una CLI para ejecutar modelos YOLO-NAS.

Los modelos YOLO-NAS necesitan el paquete super-gradients, que requiere un entorno de Python 3.10:

pip install ultralytics super-gradients "setuptools<81"

Los siguientes ejemplos muestran cómo usar los modelos YOLO-NAS con el paquete ultralytics para realizar inferencias y validaciones:

Ejemplos de inferencia y validación#

En este ejemplo, validamos YOLO-NAS-s con el conjunto de datos COCO8.

Ejemplo

Este ejemplo proporciona código sencillo de inferencia y validación para YOLO-NAS. YOLO-NAS también admite la exportación, pero el paquete ultralytics no permite entrenarlo.

Puedes pasar archivos de modelo *.pt preentrenados con PyTorch a la clase NAS() para crear una instancia del modelo en Python:

from ultralytics import NAS

# Carga un modelo YOLO-NAS-s preentrenado con COCO
model = NAS("yolo_nas_s.pt")

# Mostrar información del modelo (opcional)
model.info()

# Valida el modelo con el conjunto de datos de ejemplo COCO8
results = model.val(data="coco8.yaml")

# Ejecuta inferencias con el modelo YOLO-NAS-s en la imagen 'bus.jpg'
results = model("path/to/bus.jpg")

Tareas y modos compatibles#

YOLO-NAS está disponible en tres variantes: Small (s), Medium (m) y Large (l). Cada variante está diseñada para satisfacer distintas necesidades computacionales y de rendimiento:

  • YOLO-NAS-s: optimizado para entornos con recursos de cálculo limitados, donde la eficiencia es fundamental.
  • YOLO-NAS-m: ofrece un enfoque equilibrado, adecuado para la detección de objetos de uso general con mayor precisión.
  • YOLO-NAS-l: diseñado para situaciones que requieren la máxima precisión y en las que los recursos de cálculo no son una limitación importante.

A continuación encontrarás una descripción detallada de cada modelo, con enlaces a sus pesos preentrenados, las tareas que admite y su compatibilidad con distintos modos de funcionamiento.

Tipo de modeloPesos preentrenadosTareas compatiblesEntrenamientoValidaciónInferenciaExportar
YOLO-NAS-syolo_nas_s.ptDetección de objetos❌✅✅✅
YOLO-NAS-myolo_nas_m.ptDetección de objetos❌✅✅✅
YOLO-NAS-lyolo_nas_l.ptDetección de objetos❌✅✅✅

Citas y agradecimientos#

Si utilizas YOLO-NAS en tu trabajo de investigación o desarrollo, cita SuperGradients:

Cita
@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},
}

Agradecemos al equipo de SuperGradients de Deci AI su trabajo para crear y mantener este valioso recurso para la comunidad de visión artificial.

Preguntas frecuentes#

  • YOLO-NAS, desarrollado por Deci AI, es un modelo de detección de objetos diseñado mediante búsqueda de arquitectura neuronal (NAS). Aborda las limitaciones de modelos YOLO anteriores al introducir características como bloques básicos compatibles con la cuantización y esquemas de entrenamiento avanzados, que mejoran el rendimiento, especialmente en entornos con recursos computacionales limitados. YOLO-NAS también admite la cuantización y mantiene una alta precisión incluso al convertirse a su versión INT8, lo que aumenta su idoneidad para entornos de producción.

  • Puedes integrar modelos YOLO-NAS en tu aplicación Python con el paquete ultralytics. Aquí tienes un ejemplo sencillo de cómo cargar un modelo YOLO-NAS preentrenado y ejecutar la inferencia:

    from ultralytics import NAS
    
    # Carga un modelo YOLO-NAS-s preentrenado con COCO
    model = NAS("yolo_nas_s.pt")
    
    # Valida el modelo con el conjunto de datos de ejemplo COCO8
    results = model.val(data="coco8.yaml")
    
    # Ejecuta inferencias con el modelo YOLO-NAS-s en la imagen 'bus.jpg'
    results = model("path/to/bus.jpg")

    Para obtener más información, consulta Ejemplos de inferencia y validación.

  • YOLO-NAS incorpora varias funciones clave que lo convierten en una excelente opción para la detección de objetos cuantizada:

    • Bloque básico compatible con la cuantización: arquitectura mejorada que conserva la precisión después de cuantizar.
    • Entrenamiento y cuantización avanzados: utiliza métodos de entrenamiento avanzados y técnicas de cuantización posterior al entrenamiento.
    • Optimización y preentrenamiento AutoNAC: utiliza la optimización AutoNAC y está preentrenado con conjuntos de datos como COCO, Objects365 y Roboflow 100.

    Estas características contribuyen a su gran precisión, rendimiento eficiente e idoneidad para el despliegue en entornos de producción. Descubre más en la sección Características principales.

  • Los modelos YOLO-NAS admiten la detección de objetos en los modos de validación, inferencia y exportación. No admiten el entrenamiento. Los modelos compatibles son YOLO-NAS-s, YOLO-NAS-m y YOLO-NAS-l, cada uno adaptado a distintas capacidades computacionales y necesidades de rendimiento.

  • Sí, Ultralytics ofrece modelos YOLO-NAS preentrenados a los que puedes acceder directamente. Estos modelos están preentrenados con conjuntos de datos como COCO. Puedes descargarlos mediante los enlaces de la sección Tareas y modos compatibles. Aquí tienes algunos ejemplos:

Comentarios21

Haz una pregunta, comparte tus resultados o ayuda a otra persona.

  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(editado)

      @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(editado)

      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(editado)

      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(editado)

      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(editado)

      @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(editado)

      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.