Python Utilisation
Welcome to the YOLO11 Python Usage documentation! This guide is designed to help you seamlessly integrate YOLO11 into your Python projects for object detection, segmentation, and classification. Here, you'll learn how to load and use pretrained models, train new models, and perform predictions on images. The easy-to-use Python interface is a valuable resource for anyone looking to incorporate YOLO11 into their Python projects, allowing you to quickly implement advanced object detection capabilities. Let's get started!
Regarde : Mastering Ultralytics YOLO11: Python
Par exemple, les utilisateurs peuvent charger un modèle, l'entraîner, évaluer ses performances sur un ensemble de validation et même l'exporter au format ONNX avec seulement quelques lignes de code.
Python
from ultralytics import YOLO
# Create a new YOLO model from scratch
model = YOLO("yolo11n.yaml")
# Load a pretrained YOLO model (recommended for training)
model = YOLO("yolo11n.pt")
# Train the model using the 'coco8.yaml' dataset for 3 epochs
results = model.train(data="coco8.yaml", epochs=3)
# Evaluate the model's performance on the validation set
results = model.val()
# Perform object detection on an image using the model
results = model("https://ultralytics.com/images/bus.jpg")
# Export the model to ONNX format
success = model.export(format="onnx")
Train
Train mode is used for training a YOLO11 model on a custom dataset. In this mode, the model is trained using the specified dataset and hyperparameters. The training process involves optimizing the model's parameters so that it can accurately predict the classes and locations of objects in an image.
Train
Val
Val mode is used for validating a YOLO11 model after it has been trained. In this mode, the model is evaluated on a validation set to measure its accuracy and generalization performance. This mode can be used to tune the hyperparameters of the model to improve its performance.
Val
Prévoir
Predict mode is used for making predictions using a trained YOLO11 model on new images or videos. In this mode, the model is loaded from a checkpoint file, and the user can provide images or videos to perform inference. The model predicts the classes and locations of objects in the input images or videos.
Prévoir
import cv2
from PIL import Image
from ultralytics import YOLO
model = YOLO("model.pt")
# accepts all formats - image/dir/Path/URL/video/PIL/ndarray. 0 for webcam
results = model.predict(source="0")
results = model.predict(source="folder", show=True) # Display preds. Accepts all YOLO predict arguments
# from PIL
im1 = Image.open("bus.jpg")
results = model.predict(source=im1, save=True) # save plotted images
# from ndarray
im2 = cv2.imread("bus.jpg")
results = model.predict(source=im2, save=True, save_txt=True) # save predictions as labels
# from list of PIL/ndarray
results = model.predict(source=[im1, im2])
# results would be a list of Results object including all the predictions by default
# but be careful as it could occupy a lot memory when there're many images,
# especially the task is segmentation.
# 1. return as a list
results = model.predict(source="folder")
# results would be a generator which is more friendly to memory by setting stream=True
# 2. return as a generator
results = model.predict(source=0, stream=True)
for result in results:
# Detection
result.boxes.xyxy # box with xyxy format, (N, 4)
result.boxes.xywh # box with xywh format, (N, 4)
result.boxes.xyxyn # box with xyxy format but normalized, (N, 4)
result.boxes.xywhn # box with xywh format but normalized, (N, 4)
result.boxes.conf # confidence score, (N, 1)
result.boxes.cls # cls, (N, 1)
# Segmentation
result.masks.data # masks, (N, H, W)
result.masks.xy # x,y segments (pixels), List[segment] * N
result.masks.xyn # x,y segments (normalized), List[segment] * N
# Classification
result.probs # cls prob, (num_class, )
# Each result is composed of torch.Tensor by default,
# in which you can easily use following functionality:
result = result.cuda()
result = result.cpu()
result = result.to("cpu")
result = result.numpy()
Exporter
Export mode is used for exporting a YOLO11 model to a format that can be used for deployment. In this mode, the model is converted to a format that can be used by other software applications or hardware devices. This mode is useful when deploying the model to production environments.
Exporter
Export an official YOLO11n model to ONNX with dynamic batch-size and image-size.
Poursuivre
Track mode is used for tracking objects in real-time using a YOLO11 model. In this mode, the model is loaded from a checkpoint file, and the user can provide a live video stream to perform real-time object tracking. This mode is useful for applications such as surveillance systems or self-driving cars.
Poursuivre
from ultralytics import YOLO
# Load a model
model = YOLO("yolo11n.pt") # load an official detection model
model = YOLO("yolo11n-seg.pt") # load an official segmentation model
model = YOLO("path/to/best.pt") # load a custom model
# Track with the model
results = model.track(source="https://youtu.be/LNwODJXcvt4", show=True)
results = model.track(source="https://youtu.be/LNwODJXcvt4", show=True, tracker="bytetrack.yaml")
Point de repère
Benchmark mode is used to profile the speed and accuracy of various export formats for YOLO11. The benchmarks provide information on the size of the exported format, its mAP50-95
métriques (pour la détection et la segmentation d'objets) ou accuracy_top5
(pour la classification), et le temps d'inférence en millisecondes par image dans différents formats d'exportation tels que ONNX, OpenVINO, TensorRT et autres. Ces informations peuvent aider les utilisateurs à choisir le format d'exportation optimal pour leur cas d'utilisation spécifique en fonction de leurs exigences en matière de vitesse et de précision.
Point de repère
Explorateur
L'API Explorer peut être utilisée pour explorer des ensembles de données avec des fonctions avancées de recherche sémantique, de similarité vectorielle et de recherche SQL, entre autres. Elle permet également de rechercher des images en fonction de leur contenu à l'aide du langage naturel en utilisant la puissance des LLM. L'API Explorer te permet d'écrire tes propres carnets ou scripts d'exploration d'ensembles de données pour obtenir des informations sur tes ensembles de données.
Recherche sémantique à l'aide d'Explorer
from ultralytics import Explorer
# create an Explorer object
exp = Explorer(data="coco8.yaml", model="yolo11n.pt")
exp.create_embeddings_table()
similar = exp.get_similar(img="https://ultralytics.com/images/bus.jpg", limit=10)
print(similar.head())
# Search using multiple indices
similar = exp.get_similar(
img=["https://ultralytics.com/images/bus.jpg", "https://ultralytics.com/images/bus.jpg"], limit=10
)
print(similar.head())
from ultralytics import Explorer
# create an Explorer object
exp = Explorer(data="coco8.yaml", model="yolo11n.pt")
exp.create_embeddings_table()
similar = exp.get_similar(idx=1, limit=10)
print(similar.head())
# Search using multiple indices
similar = exp.get_similar(idx=[1, 10], limit=10)
print(similar.head())
Utiliser les formateurs
YOLO
La classe de modèle est une enveloppe de haut niveau sur les classes de formateurs. Chaque tâche YOLO a son propre formateur qui hérite de la classe BaseTrainer
.
Exemple d'entraîneur à la détection
from ultralytics.models.yolo import DetectionPredictor, DetectionTrainer, DetectionValidator
# trainer
trainer = DetectionTrainer(overrides={})
trainer.train()
trained_model = trainer.best
# Validator
val = DetectionValidator(args=...)
val(model=trained_model)
# predictor
pred = DetectionPredictor(overrides={})
pred(source=SOURCE, model=trained_model)
# resume from last weight
overrides["resume"] = trainer.last
trainer = detect.DetectionTrainer(overrides=overrides)
Tu peux facilement personnaliser les formateurs pour prendre en charge des tâches personnalisées ou explorer des idées de recherche et développement. En savoir plus sur la personnalisation Trainers
, Validators
et Predictors
pour répondre aux besoins de ton projet dans la section Personnalisation.
FAQ
How can I integrate YOLO11 into my Python project for object detection?
Integrating Ultralytics YOLO11 into your Python projects is simple. You can load a pre-trained model or train a new model from scratch. Here's how to get started:
from ultralytics import YOLO
# Load a pretrained YOLO model
model = YOLO("yolo11n.pt")
# Perform object detection on an image
results = model("https://ultralytics.com/images/bus.jpg")
# Visualize the results
for result in results:
result.show()
Tu trouveras des exemples plus détaillés dans notre section sur le mode prédictif.
What are the different modes available in YOLO11?
Ultralytics YOLO11 provides various modes to cater to different machine learning workflows. These include:
- Train: Entraîne un modèle à l'aide d'ensembles de données personnalisés.
- Val: Valide les performances du modèle sur un ensemble de validation.
- Prévoir: Fais des prédictions sur les nouvelles images ou les nouveaux flux vidéo.
- Exportation: Exporte les modèles vers différents formats tels que ONNX, TensorRT.
- Piste: Suivi d'objets en temps réel dans les flux vidéo.
- Point de repère: Analyse les performances du modèle dans différentes configurations.
Chaque mode est conçu pour offrir des fonctionnalités complètes à différentes étapes du développement et du déploiement du modèle.
How do I train a custom YOLO11 model using my dataset?
To train a custom YOLO11 model, you need to specify your dataset and other hyperparameters. Here's a quick example:
from ultralytics import YOLO
# Load the YOLO model
model = YOLO("yolo11n.yaml")
# Train the model with custom dataset
model.train(data="path/to/your/dataset.yaml", epochs=10)
Pour plus de détails sur la formation et des hyperliens vers des exemples d'utilisation, visite notre page Mode de formation.
How do I export YOLO11 models for deployment?
Exporting YOLO11 models in a format suitable for deployment is straightforward with the export
fonction. Par exemple, tu peux exporter un modèle au format ONNX :
from ultralytics import YOLO
# Load the YOLO model
model = YOLO("yolo11n.pt")
# Export the model to ONNX format
model.export(format="onnx")
Pour connaître les différentes options d'exportation, reporte-toi à la documentation sur le mode d'exportation.
Can I validate my YOLO11 model on different datasets?
Yes, validating YOLO11 models on different datasets is possible. After training, you can use the validation mode to evaluate the performance:
from ultralytics import YOLO
# Load a YOLO11 model
model = YOLO("yolo11n.yaml")
# Train the model
model.train(data="coco8.yaml", epochs=5)
# Validate the model on a different dataset
model.val(data="path/to/separate/data.yaml")
Consulte la page Mode Val pour des exemples et une utilisation détaillés.