Évaluation comparative des modèles avec Ultralytics YOLO
Visualisation des benchmarks#
Introduction#
Une fois ton modèle entraîné et validé, l'étape suivante consiste à évaluer ses performances en déploiement. Le mode Benchmark d'Ultralytics YOLO26 mesure la vitesse et la précision de ton modèle dans plusieurs formats d'exportation.
Consulte l’aperçu non publié de YOLO27 pour obtenir des benchmarks préliminaires de vitesse.
Regarder : Évaluer les modèles Ultralytics YOLO26 | Comment comparer les performances des modèles sur différents matériels ?
Pourquoi les benchmarks sont-ils essentiels ?#
- Décisions éclairées : Comprends les compromis entre vitesse et exactitude.
- Allocation des ressources : Comprends les performances des différents formats d’exportation sur divers matériels.
- Optimisation : Découvre quel format d’exportation offre les meilleures performances pour ton cas d’utilisation spécifique.
- Rentabilité : Utilise plus efficacement les ressources matérielles en fonction des résultats des benchmarks.
Indicateurs clés du mode benchmark#
- mAP50-95 : pour la détection d’objets, la segmentation d’instances, l’estimation de pose et OBB.
- mIoU : pour la segmentation sémantique.
- δ1 : pour l’estimation de profondeur.
- accuracy_top1 : Pour la classification d’images.
- Temps d’inférence : Temps nécessaire pour traiter chaque image, en millisecondes.
Formats d’exportation pris en charge#
- ONNX : Pour des performances optimales sur CPU
- TensorRT : Pour une efficacité maximale sur GPU
- OpenVINO : Pour l’optimisation du matériel Intel
- CoreML, TensorFlow SavedModel et autres : Pour répondre à divers besoins de déploiement.
- Exporte vers ONNX ou OpenVINO pour accélérer le CPU jusqu’à 3 fois.
- Exporte vers TensorRT pour accélérer le GPU jusqu’à 5 fois.
Exemples d'utilisation#
Installe Ultralytics avec les dépendances d’exportation avant d’exécuter les benchmarks afin d’éviter les paquets manquants.
pip install "ultralytics[export]"Exécute des benchmarks YOLO26n avec tous les formats d'exportation pris en charge (ONNX, TensorRT, etc.).
from ultralytics.utils.benchmarks import benchmark
# Benchmark sur GPU
benchmark(model="yolo26n.pt", data="coco8.yaml", imgsz=640, device=0)
# Benchmark d’un format d’exportation spécifique
benchmark(model="yolo26n.pt", data="coco8.yaml", imgsz=640, format="onnx")Arguments#
Des arguments tels que model, data, imgsz, quantize, device, verbose et format te permettent d'adapter les benchmarks à tes besoins et de comparer les performances des différents formats d'exportation.
| Clé | Valeur par défaut | Description |
|---|---|---|
model | None | Indique le chemin vers le fichier du modèle. Accepte les formats .pt et .yaml, par exemple "yolo26n.pt" pour les modèles préentraînés ou les fichiers de configuration. |
data | None | Chemin vers le fichier YAML du jeu de données utilisé pour le benchmark, qui inclut généralement les chemins et les paramètres des données de validation. Exemple : "coco8.yaml". Pour la classification, indique plutôt un répertoire de jeu de données ou le nom d’un jeu de données intégré (par exemple, imagenet10). |
imgsz | 640 | Taille de l’image d’entrée du modèle. Doit être un entier unique pour les images carrées (par exemple, 640) ; benchmark() ne prend en charge que les tailles d’image carrées. |
quantize | None | Précision demandée : 16 (FP16) ou 8 (INT8 ; les méthodes PTQ nécessitent des données de calibration data/fraction, contrairement aux méthodes qui ne quantifient que les poids) ; 32/non défini correspond à FP32 lorsque le format le prend en charge — un format qui ne peut pas exporter en FP32 rejette une valeur explicite 32 ou utilise la précision qu'il exige. La ligne PyTorch native n'est pas exportée : seul 16 a un effet sur elle et sélectionne l'inférence FP16 hors CPU ; sinon, elle s'exécute en FP32. Chaque format exécute ensuite l'inférence avec sa propre précision d'exécution. Remplace les indicateurs obsolètes half/int8. |
device | None | Définit l'appareil de calcul utilisé pour l'évaluation des performances, par exemple "cpu" ou "cuda:0" ; si le paramètre n'est pas défini, le premier GPU disponible est utilisé, sinon le CPU. Avec format="openvino" ou "litert", "xpu" et "npu" sélectionnent le GPU et le NPU Intel ; consulte les appareils d'inférence. |
verbose | False | Si la valeur est True ou un nombre décimal, les échecs du benchmark (sauf les assertions) provoquent une exception au lieu de consigner une erreur ; un nombre décimal tel que 0.25 vérifie aussi, par assertion, que la métrique de chaque format réussi dépasse ce seuil. |
eps | 0.001 | Petit epsilon (en millisecondes) ajouté au temps d’inférence par image avant sa conversion en FPS, afin d’éviter une division par zéro. Rarement modifié. |
format | '' | Évalue uniquement le format d’exportation indiqué (par exemple, format=onnx). Laisse ce champ vide pour tester automatiquement tous les formats pris en charge. |
La fonction autonome benchmark() (from ultralytics.utils.benchmarks import benchmark) utilise ses propres valeurs par défaut de signature au lieu des valeurs du tableau ci-dessus, notamment model="yolo26n.pt", imgsz=160 et device="cpu" ; passe explicitement imgsz et device pour obtenir le même comportement que l’interface CLI yolo benchmark.
Formats d’exportation#
Les benchmarks tentent automatiquement de s’exécuter avec tous les formats d’exportation possibles indiqués ci-dessous. Tu peux aussi exécuter des benchmarks pour un format spécifique en utilisant l’argument format, qui accepte n’importe lequel des formats mentionnés ci-dessous.
| Format | Argument format | Modèle | Métadonnées | Arguments |
|---|---|---|---|---|
| PyTorch | - | yolo26n.pt | ✅ | - |
| TorchScript | torchscript | yolo26n.torchscript | ✅ | imgsz, quantize, dynamic, nms, batch, device |
| ONNX | onnx | yolo26n.onnx | ✅ | imgsz, quantize, dynamic, simplify, opset, nms, batch, data, fraction, device |
| OpenVINO | openvino | yolo26n_openvino_model/ | ✅ | imgsz, quantize, dynamic, nms, batch, data, fraction, device |
| TensorRT | engine | yolo26n.engine | ✅ | imgsz, quantize, dynamic, simplify, opset, workspace, nms, batch, data, fraction, device |
| CoreML | coreml | yolo26n.mlpackage | ✅ | imgsz, dynamic, quantize, nms, batch, device |
| Apple Core AI | coreai | yolo26n.aimodel | ✅ | imgsz, batch, quantize |
| TF SavedModel | saved_model | yolo26n_saved_model/ | ✅ | imgsz, quantize, opset, nms, batch, data, fraction, device |
| TF GraphDef | pb | yolo26n.pb | ❌ | imgsz, opset, batch, device |
| TF Edge TPU | edgetpu | yolo26n_edgetpu.tflite | ✅ | imgsz, quantize, opset, data, fraction, device |
| LiteRT | litert | yolo26n.tflite | ✅ | imgsz, quantize, batch, data, fraction, device |
| PaddlePaddle | paddle | yolo26n_paddle_model/ | ✅ | imgsz, batch, device |
| MNN | mnn | yolo26n.mnn | ✅ | imgsz, batch, dynamic, quantize, simplify, opset, nms, device |
| NCNN | ncnn | yolo26n_ncnn_model/ | ✅ | imgsz, quantize, device |
| IMX500 | imx | yolo11n_imx_model/ | ✅ | imgsz, quantize, data, fraction, nms, device |
| RKNN | rknn | yolo26n_rknn_model/ | ✅ | imgsz, batch, name, quantize, simplify, opset, data, fraction, device |
| ExecuTorch | executorch | yolo26n_executorch_model/ | ✅ | imgsz, quantize, batch, data, fraction, device |
| Axelera | axelera | yolo26n_axelera_model/ | ✅ | imgsz, batch, quantize, data, fraction, device |
| DEEPX | deepx | yolo26n_deepx_model/ | ✅ | imgsz, quantize, simplify, opset, data, optimize, device |
| Qualcomm QNN | qnn | yolo26n_qnn.onnx | ✅ | imgsz, batch, name, quantize, simplify, opset, data, fraction, device |
| Hailo | hailo | yolo26n_hailo_model/ | ✅ | imgsz, name, quantize, data, fraction, simplify, conf, iou, device |
| Huawei Ascend | ascend | yolo26n_ascend_model/ | ✅ | imgsz, batch, name, quantize, opset, simplify, nms, device |
| AMD Xilinx | xilinx | yolo26n_xilinx_model/ | ✅ | imgsz, name, quantize, data, fraction, opset, simplify, device |
| NXP | nxp | yolo26n_nxp.tflite | ✅ | imgsz, quantize, data, fraction, device |
nms=None utilise par défaut les sorties brutes pour une NMS externe (YOLO26 conserve sa tête sans NMS sur Axelera). Définis nms=False pour sélectionner une tête sans NMS disponible ; les formats non pris en charge reviennent à leur chemin de sortie natif. Les entrées nms ci-dessus identifient les formats qui peuvent intégrer la NMS avec nms=True.
Consulte tous les détails de export sur la page Exportation.
FAQ#
Ultralytics YOLO26 propose un mode Benchmark pour évaluer les performances de ton modèle avec différents formats d’exportation. Ce mode indique des métriques clés comme la précision moyenne (mAP50-95), la précision et le temps d’inférence en millisecondes. Pour lancer des benchmarks, tu peux utiliser Python ou des commandes CLI. Par exemple, pour effectuer un benchmark sur GPU :
Exemplefrom ultralytics.utils.benchmarks import benchmark # Benchmark sur GPU benchmark(model="yolo26n.pt", data="coco8.yaml", imgsz=640, device=0)Pour plus de détails sur les arguments des benchmarks, consulte la section Arguments.
L’exportation des modèles YOLO26 vers différents formats, tels que ONNX, TensorRT et OpenVINO, te permet d’optimiser les performances en fonction de ton environnement de déploiement. Par exemple :
- ONNX : Accélère le CPU jusqu’à 3 fois.
- TensorRT : Accélère le GPU jusqu’à 5 fois.
- OpenVINO : Spécifiquement optimisé pour le matériel Intel.
Ces formats améliorent la vitesse d’inférence sur le matériel cible et rendent tes modèles plus efficaces dans diverses applications réelles. Consulte la page Exportation pour obtenir tous les détails.
Évaluer tes modèles YOLO26 à l’aide de benchmarks est essentiel pour plusieurs raisons :
- Décisions éclairées : Comprends les compromis entre vitesse et exactitude.
- Allocation des ressources : Évalue les performances sur différentes options matérielles.
- Optimisation : Détermine quel format d’exportation offre les meilleures performances pour des cas d’utilisation spécifiques.
- Rentabilité : Optimise l’utilisation du matériel en fonction des résultats des benchmarks.
Des métriques clés comme mAP50-95, la précision Top-1 et le temps d’inférence facilitent ces évaluations. Consulte la section Métriques clés pour en savoir plus.
YOLO26 prend en charge divers formats d’exportation, chacun adapté à du matériel et à des cas d’utilisation spécifiques :
- ONNX : Idéal pour les performances CPU.
- TensorRT : Idéal pour l’efficacité GPU.
- OpenVINO : Optimisé pour le matériel Intel.
- CoreML et TensorFlow : CoreML pour les appareils Apple ; les formats TensorFlow pour le déploiement mobile, web et ML général.
Pour obtenir la liste complète des formats pris en charge et de leurs avantages respectifs, consulte la section Formats d’exportation pris en charge.
Lors de l’exécution de benchmarks, plusieurs arguments peuvent être personnalisés selon tes besoins spécifiques :
- model : Chemin vers le fichier du modèle (par exemple, « yolo26n.pt »).
- data : Chemin vers le fichier YAML du jeu de données (par exemple,
"coco8.yaml") ; pour la classification, indique plutôt un répertoire de jeu de données ou le nom d’un jeu de données intégré (par exemple,imagenet10). - imgsz : Taille de l’image d’entrée carrée, exprimée par un seul entier, comme
640. Le mode benchmark utilise la même taille d’image carrée pour PyTorch et les formats exportés afin de garantir une comparaison équitable. - quantize : précision demandée :
16pour FP16,8pour INT8 (utile pour les appareils en périphérie) ;32/non défini correspond à FP32 lorsque le format le prend en charge — un format qui ne peut pas exporter en FP32 rejette une valeur explicite32ou utilise la précision qu'il exige. La ligne PyTorch native n'est pas exportée : seul16a un effet sur elle et sélectionne l'inférence FP16 hors CPU ; sinon, elle s'exécute en FP32. Chaque format exécute ensuite l'inférence avec sa propre précision d'exécution. - device : indique l'appareil de calcul (par exemple, « cpu », « cuda:0 »), ou « xpu » et « npu » pour le GPU et le NPU Intel avec
format="openvino"ou"litert". - verbose : Déclenche une exception en cas d’échec du benchmark au lieu de consigner l’erreur ; passe un nombre décimal pour exiger également que la métrique de chaque format dépasse ce seuil.
Pour obtenir la liste complète des arguments, consulte la section Arguments.
Commentaires39
Pose une question, partage tes résultats ou aide quelqu’un d’autre.
bayda369
Hi, I want to customize the yolov8 to detect and track only the objects determined by the user, like selecting 3 persons in different positions out of 10 persons in the video appears in the first frame of the video and ignore any other persons, what are your suggestions?
1
Paula DerrengerUltralytics@bayda369 hello,
For customizing YOLOv8 to detect and track specific objects (like selecting certain individuals from a video), you can approach this by integrating a pre-processing step to identify and tag the objects of interest in the first frame. Here’s a brief outline on how you might proceed:
- Object Detection: Use YOLOv8 to detect all persons in the first frame.
- Object Selection: Implement a method to select the desired objects. This could be manual selection via bounding box coordinates or an automated method based on certain criteria.
- Tracking: Once the objects are tagged, you can use the tracking functionality to follow these objects across frames. You might need to modify the tracking logic to focus only on the tagged objects.
For the tracking part, you can utilize the existing tracking capabilities of YOLOv8, which supports multiple tracking algorithms. You may need to customize the tracking code to ensure it only tracks the initially selected objects.
This approach requires some custom coding, especially for the selection and modified tracking logic. If you need further guidance on the specific code modifications, feel free to ask!
bayda369
yes please, I need further guidance on the specific code modifications
Paula DerrengerUltralytics(modifié)Hello @bayda369,
Absolutely, I'd be happy to guide you through the code needed to track only selected objects in a video. The simplest way is to use the built-in tracker, which gives every person a persistent ID, and then keep only the IDs you selected in the first frame.
Step-by-Step Guide
- Track persons: run tracking with
classes=[0](person). - Select IDs: choose the IDs of the persons you want from the first frame (manually or by criteria).
- Filter: ignore every other ID in later frames.
Code Example
from ultralytics import YOLO model = YOLO("yolo26n.pt") selected_ids = None for r in model.track("path/to/your/video/file.mp4", classes=[0], persist=True, stream=True): if r.boxes.id is None: continue ids = r.boxes.id.int().tolist() if selected_ids is None: # For simplicity, select the first 3 persons; replace with your own selection method selected_ids = set(ids[:3]) keep = [i for i, t in enumerate(ids) if t in selected_ids] boxes = r.boxes.xyxy[keep] # boxes of the selected persons only track_ids = [ids[i] for i in keep] print(track_ids, boxes)Feel free to customize the selection method as per your requirements. If you need further assistance, don't hesitate to ask! 😊
- Track persons: run tracking with
AA278-HUB
it seems benchmark only run on Linux System ,It couldn't run on Window Enviroment?
Glenn JocherUltralytics(modifié)It runs on Windows too—only some export formats are OS‑specific (e.g., CoreML, EdgeTPU and RKNN aren’t supported on Windows); try a single supported format to verify your setup:
yolo benchmark model=yolo26n.pt data=coco8.yaml format=onnx device=cpuIf it still fails, please paste the
yolo checksoutput and the full traceback here; format/OS notes are summarized in the benchmarks reference at ultralytics.utils.benchmarks.AA278-HUB
thank you,Very appreciate to your help .
Glenn JocherUltralytics(modifié)Glad it helped! On Windows you can also benchmark a fast CPU path with OpenVINO:
yolo benchmark model=yolo26n.pt data=coco8.yaml format=openvinoSetup and tips are in the OpenVINO export guide.
andyg2
Which GPUs are used in these benchmarks? I imagine the result would be different between a GTX 1650 and an H100?
Glenn JocherUltralytics(modifié)@andyg2 you're absolutely right that benchmark results vary significantly between different GPU models. The documentation doesn't specify which exact GPUs were used for the benchmark results shown. For accurate performance metrics on your specific hardware, I'd recommend running the benchmarks directly on your system using:
from ultralytics.utils.benchmarks import benchmark benchmark(model="yolo26n.pt", data="coco8.yaml", imgsz=640, device=0)This will give you hardware-specific results for your GTX 1650 or any other GPU you're using, which will be much more relevant for your deployment needs than generic benchmark numbers.
andyg2
What's the use of a benchmark that doesn't have a bench?
Glenn JocherUltralytics@andyg2 that's a very valid point! Benchmark results without hardware specifications are indeed not very meaningful for comparison purposes. You're absolutely right that performance metrics should always include the testing hardware context. For meaningful benchmarks, it's best to run tests on your specific hardware setup to get accurate performance expectations for your deployment environment.
andyg2(modifié)
@glenn-jocher Thanks for the reply. My problem is I need to purchase over 120 small GPUs for a computer vision project.
I guess I need to buy 10 GPUs and see how each of them do, because nobody at Ultralytics can remember how they tested their own code.
Sorry if I'm coming across a little sarcastic here, I'm just so flabbergasted, not that this information is not included - everyone makes mistakes in documentation, but that nobody there thinks it should be included.
Glenn JocherUltralytics@andyg2 you're absolutely right, and I completely understand your frustration. This is a valid oversight on our part - benchmark results without hardware specifications are essentially meaningless for making informed purchasing decisions, especially at your scale.
For your project requiring 120 GPUs, I'd suggest focusing on a few key considerations: look for GPUs with sufficient VRAM for your model size (typically 8GB+ for larger YOLO models), prioritize newer architectures that support TensorRT optimization well (RTX 30/40 series, A-series), and consider power efficiency for large-scale deployments.
Your approach of testing with 10 GPUs first is actually the most reliable path forward given the current documentation gap. This will give you real-world performance data specific to your models, datasets, and deployment constraints.
Thank you for the feedback - this highlights an important area where our documentation needs improvement to better serve users making hardware decisions.
1
josiahkim29
How do i proceed to calculate the mean Average Precision of the predictions? I have noted the predictions = model(10 sample images from COCO val2017 dataset)
is a bit different especially when you want to get the classes and scores of the predictions
for pred in predictions[0]:
x, y, w, h, class_id, score = pred[:6]
Glenn JocherUltralyticsTo calculate mean Average Precision (mAP) for your predictions, you can use the
valmethod in Ultralytics YOLO, which evaluates the model on a dataset and provides mAP metrics. For more details, refer to the benchmarking guide.josiahkim29
@glenn-jocher thank you for the response. Based on the benchmarking guide I see that I need a custom.yaml file for this specific images I am using. Is this the case? If so how do you proceed to create a custom.yaml file.
Glenn JocherUltralyticsTo create a custom
yamlfile for your specific images, you'll need to define the dataset paths and class names. You can start by copying an existing dataset file likecoco128.yamland modifying it to suit your dataset structure. For detailed guidance, please refer to the dataset preparation section in the documentation.
xpeedent289
Hi there, I have a question that, which dataset is use to benchmark, train, val or test ?
Glenn JocherUltralytics@Xpeedent the benchmark mode uses the validation dataset specified in the
dataargument, typically defined in a YAML file likecoco8.yaml. For more details, please visit the Benchmarking Documentation.
xpeedent289
Hi sir! when I use benchmark for "yolov8n.pt", it auto exports TorchScript, ONNX,... and auto benchmark for these too, but I just wanna benchmark for yolov8n.pt, so how can I adjust it ?
Glenn JocherUltralytics(modifié)To benchmark only the
yolov8n.ptmodel without exporting to other formats, you can use theformatargument to limit the benchmark to the PyTorch model. Here's how you can do it:from ultralytics.utils.benchmarks import benchmark # Benchmark only the PyTorch model ("-" is the PyTorch format) benchmark(model="yolov8n.pt", data="coco8.yaml", imgsz=640, device=0, format="-")Or using the CLI:
yolo benchmark model=yolov8n.pt data=coco8.yaml imgsz=640 device=0 format=-This will ensure that only the PyTorch model is benchmarked. For more details, you can visit the benchmark documentation.
themeowsketeer
@glenn-jocher I got this error. TypeError: benchmark() got an unexpected keyword argument 'format' I don't think by default benchmark can accept custom format argument?
Glenn JocherUltralytics(modifié)The
benchmarkfunction supports aformatargument that limits the run to one export format, e.g.format=onnx. To benchmark only the PyTorch model, useformat="-", for exampleyolo benchmark model=yolov8n.pt data=coco8.yaml format=-. Leaveformatunset to benchmark all formats. See the benchmark documentation for details.
themeowsketeer
Greetings, I'm facing the following error when trying to benchmark using trained weight from RT-DeTR-L model, which is known to be fully supported by Ultralytics:
KeyError Traceback (most recent call last) File /opt/conda/lib/python3.10/site-packages/ultralytics/utils/benchmarks.py:133, in benchmark(model, data, imgsz, half, int8, device, verbose) 132 assert i != 5 or platform.system() == "Darwin", "inference only supported on macOS>=10.13" # CoreML --> 133 exported_model.predict(ASSETS / "bus.jpg", imgsz=imgsz, device=device, half=half) 135 # Validate
File /opt/conda/lib/python3.10/site-packages/ultralytics/engine/model.py:563, in Model.predict(self, source, stream, predictor, **kwargs) 562 self.predictor.set_prompts(prompts) --> 563 return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
File /opt/conda/lib/python3.10/site-packages/ultralytics/engine/predictor.py:168, in BasePredictor.call(self, source, model, stream, *args, **kwargs) 167 else: --> 168 return list(self.stream_inference(source, model, *args, **kwargs))
File /opt/conda/lib/python3.10/site-packages/torch/utils/_contextlib.py:36, in _wrap_generator..generator_context(*args, **kwargs) 35 with ctx_factory(): ---> 36 response = gen.send(None) 38 while True:
File /opt/conda/lib/python3.10/site-packages/ultralytics/engine/predictor.py:274, in BasePredictor.stream_inference(self, source, model, *args, **kwargs) 273 if self.args.verbose or self.args.save or self.args.save_txt or self.args.show: --> 274 s[i] += self.write_results(i, Path(paths[i]), im, s) 276 # Print batch results
File /opt/conda/lib/python3.10/site-packages/ultralytics/engine/predictor.py:334, in BasePredictor.write_results(self, i, p, im, s) 333 result.save_dir = self.save_dir.str() # used in other locations --> 334 string += f"{result.verbose()}{result.speed['inference']:.1f}ms" 336 # Add predictions to image
File /opt/conda/lib/python3.10/site-packages/ultralytics/engine/results.py:633, in Results.verbose(self) 632 n = (boxes.cls == c).sum() # detections per class --> 633 log_string += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " 634 return log_string
KeyError: 25
During handling of the above exception, another exception occurred:
AssertionError Traceback (most recent call last) Cell In[11], line 3 1 from ultralytics.utils.benchmarks import benchmark ----> 3 benchmark( 4 model = "/kaggle/working/weight_rtdetr/last_rtdetr.pt", 5 data = "Yolo_path_fixed.yaml", 6 imgsz = 640, 7 device = 0, 8 half = False, 9 verbose = True 10 )
File /opt/conda/lib/python3.10/site-packages/ultralytics/utils/benchmarks.py:146, in benchmark(model, data, imgsz, half, int8, device, verbose) 144 except Exception as e: 145 if verbose: --> 146 assert type(e) is AssertionError, f"Benchmark failure for {name}: {e}" 147 LOGGER.warning(f"ERROR ❌️ Benchmark failure for {name}: {e}") 148 y.append([name, emoji, round(file_size(filename), 1), None, None, None]) # mAP, t_inference
AssertionError: Benchmark failure for PyTorch: 25
Any idea how this exception is caused? My code snippet is as follows: from ultralytics.utils.benchmarks import benchmark
benchmark( model = "/kaggle/working/weight_rtdetr/last_rtdetr.pt", data = "Yolo_path_fixed.yaml", imgsz = 640, device = 0, half = False, verbose = True )
Glenn JocherUltralytics@themeowsketeer thank you for reporting this issue. It seems like the error is related to a missing class name in the model's
namesattribute. Please ensure that your model and dataset are correctly configured and that the latest versions of the Ultralytics package are installed. If the issue persists, try running the benchmark with a different model or dataset to isolate the problem. For more details on benchmarking, you can refer to our documentation.themeowsketeer
YOLO model works flawlessly with the command, while RT-DeTR models just do not work at all. AssertionError returns different error code everytime: 8, 13 or 25. Any other method I could try?
Glenn JocherUltralyticsIt seems like the issue might be related to the RT-DeTR model's class names. Please ensure your dataset and model are correctly configured, and try running the benchmark with the latest version of the Ultralytics package. If the problem persists, consider testing with a different model or dataset to isolate the issue. For more details, refer to our benchmarking documentation.
WooFy11
@title Speed Tracker
import cv2 import numpy as np from ultralytics import YOLO
from ultralytics.utils.checks import check_imshow from ultralytics.utils.plotting import Annotator, colors
from collections import defaultdict
track_history = defaultdict(lambda: []) model = YOLO("/content/drive/MyDrive/DATASET_TUGASAKHIR/PlayerResults/weights/best.pt") names = model.model.names video_path = "/content/drive/MyDrive/DATASET_TUGASAKHIR/testvid/BDEvid1.mp4" cap = cv2.VideoCapture(video_path) assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
result = cv2.VideoWriter("SpeedTracker.avi", cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
time_per_frame = 1.0 / fps real_world_scale = 0.05 # Example: 0.05 meters per pixel
while cap.isOpened(): success, frame = cap.read() if success: results = model.track(frame, persist=True, verbose=False, tracker="/content/drive/MyDrive/DATASET_TUGASAKHIR/Tracker/bytetrack.yaml") boxes = results[0].boxes.xyxy.cpu()
if results[0].boxes.id is not None: # Extract prediction results clss = results[0].boxes.cls.cpu().tolist() track_ids = results[0].boxes.id.int().cpu().tolist() confs = results[0].boxes.conf.float().cpu().tolist() # Annotator Init annotator = Annotator(frame, line_width=2) for box, cls, track_id in zip(boxes, clss, track_ids): # Store tracking history track = track_history[track_id] track.append((int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2))) if len(track) > 30: track.pop(0) if len(track) >= 2: # Calculate pixel distance between the last and second to last points dx = track[-1][0] - track[-2][0] dy = track[-1][1] - track[-2][1] pixel_distance = (dx ** 2 + dy ** 2) ** 0.5 real_distance = pixel_distance * real_world_scale speed = real_distance / time_per_frame # speed in meters per second label = f"{names[int(cls)]} {track_id} {speed:.2f} m/s" annotator.box_label(box, color=colors(int(cls), True), label=label) # Plot tracks points = np.array(track, dtype=np.int32).reshape((-1, 1, 2)) cv2.circle(frame, (track[-1]), 7, colors(int(cls), True), -1) cv2.polylines(frame, [points], isClosed=False, color=colors(int(cls), True), thickness=2) else: label = f"{names[int(cls)]} {track_id}" annotator.box_label(box, color=colors(int(cls), True), label=label) result.write(frame) if cv2.waitKey(1) & 0xFF == ord("q"): break else: breakresult.release() cap.release() cv2.destroyAllWindows()
how to collect the ground truth ID's from this code
WooFy11
@title Speed Tracker
import cv2 import numpy as np from ultralytics import YOLO
from ultralytics.utils.checks import check_imshow from ultralytics.utils.plotting import Annotator, colors
from collections import defaultdict
track_history = defaultdict(lambda: []) model = YOLO("/content/drive/MyDrive/DATASET_TUGASAKHIR/PlayerResults/weights/best.pt") names = model.model.names video_path = "/content/drive/MyDrive/DATASET_TUGASAKHIR/testvid/BDEvid1.mp4" cap = cv2.VideoCapture(video_path) assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
result = cv2.VideoWriter("SpeedTracker.avi", cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
time_per_frame = 1.0 / fps real_world_scale = 0.05 # Example: 0.05 meters per pixel
while cap.isOpened(): success, frame = cap.read() if success: results = model.track(frame, persist=True, verbose=False, tracker="/content/drive/MyDrive/DATASET_TUGASAKHIR/Tracker/bytetrack.yaml") boxes = results[0].boxes.xyxy.cpu()
if results[0].boxes.id is not None: # Extract prediction results clss = results[0].boxes.cls.cpu().tolist() track_ids = results[0].boxes.id.int().cpu().tolist() confs = results[0].boxes.conf.float().cpu().tolist() # Annotator Init annotator = Annotator(frame, line_width=2) for box, cls, track_id in zip(boxes, clss, track_ids): # Store tracking history track = track_history[track_id] track.append((int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2))) if len(track) > 30: track.pop(0) if len(track) >= 2: # Calculate pixel distance between the last and second to last points dx = track[-1][0] - track[-2][0] dy = track[-1][1] - track[-2][1] pixel_distance = (dx ** 2 + dy ** 2) ** 0.5 real_distance = pixel_distance * real_world_scale speed = real_distance / time_per_frame # speed in meters per second label = f"{names[int(cls)]} {track_id} {speed:.2f} m/s" annotator.box_label(box, color=colors(int(cls), True), label=label) # Plot tracks points = np.array(track, dtype=np.int32).reshape((-1, 1, 2)) cv2.circle(frame, (track[-1]), 7, colors(int(cls), True), -1) cv2.polylines(frame, [points], isClosed=False, color=colors(int(cls), True), thickness=2) else: label = f"{names[int(cls)]} {track_id}" annotator.box_label(box, color=colors(int(cls), True), label=label) result.write(frame) if cv2.waitKey(1) & 0xFF == ord("q"): break else: breakresult.release() cap.release() cv2.destroyAllWindows()
how do we benchmark the bytetrack perfomance per player ID?
Zency-Sun
Hi, what should I do if I want to benchmark using only Pytorch, ONNX, openvino and tensorRT?
Paula DerrengerUltralytics(modifié)Hey there! 😊 To benchmark only PyTorch, ONNX, OpenVINO, and TensorRT, use the
formatargument ofbenchmark, which limits the run to one export format. Call it once per format ("-"is the PyTorch model):from ultralytics.utils.benchmarks import benchmark # "-" = PyTorch, then ONNX, OpenVINO (CPU only) and TensorRT (GPU only) for fmt, device in [("-", 0), ("onnx", 0), ("openvino", "cpu"), ("engine", 0)]: benchmark(model="yolo26n.pt", data="coco8.yaml", imgsz=640, device=device, format=fmt)And for CLI:
yolo benchmark model=yolo26n.pt data=coco8.yaml imgsz=640 device=0 format=onnx yolo benchmark model=yolo26n.pt data=coco8.yaml imgsz=640 device=cpu format=openvino yolo benchmark model=yolo26n.pt data=coco8.yaml imgsz=640 device=0 format=engineBenchmark exports the model for you, so you don't need to export it first. Hope this helps! If there are more questions, feel free to ask.
1Zency-Sun
when I use the under code to deploy: ' model = YOLO("yolov8s.engine") metrics = model.val(data="ultralytics/cfg/datasets/coco128.yaml",device='cuda:0') ' but I meet the error,What should I do?,Thanks your reply!!!
Traceback (most recent call last): File "/media/zency/SSD-Data/Codes/yolov8_v8.1.0/ultralytics/nn/autobackend.py", line 220, in init import tensorrt as trt # noqa https://developer.nvidia.com/nvidia-tensorrt-download File "/home/zency/anaconda3/envs/yolov8plus/lib/python3.9/site-packages/tensorrt/init.py", line 68, in from .tensorrt import * ImportError: libnvinfer.so.8: cannot open shared object file: No such file or directory
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "/media/zency/SSD-Data/Codes/yolov8_v8.1.0/run_test.py", line 190, in yolo_mytest() File "/media/zency/SSD-Data/Codes/yolov8_v8.1.0/run_test.py", line 116, in yolo_mytest metrics = model.val(data="ultralytics/cfg/datasets/coco128.yaml",device='cuda:0') # cpu cuda:0 File "/media/zency/SSD-Data/Codes/yolov8_v8.1.0/ultralytics/engine/model.py", line 513, in val validator(model=self.model) File "/home/zency/anaconda3/envs/yolov8plus/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/media/zency/SSD-Data/Codes/yolov8_v8.1.0/ultralytics/engine/validator.py", line 124, in call model = AutoBackend( File "/home/zency/anaconda3/envs/yolov8plus/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/media/zency/SSD-Data/Codes/yolov8_v8.1.0/ultralytics/nn/autobackend.py", line 224, in init import tensorrt as trt # noqa File "/home/zency/anaconda3/envs/yolov8plus/lib/python3.9/site-packages/tensorrt/init.py", line 68, in from .tensorrt import * ImportError: libnvinfer.so.8: cannot open shared object file: No such file or directory Ultralytics YOLOv8.1.24 🚀 Python-3.9.18 torch-1.12.1 CUDA:0 (NVIDIA GeForce RTX 3090, 24268MiB) Loading yolov8s.engine for TensorRT inference...
Zency-Sun
I solved the problem above, but there is a new problem:
[TRT] [W] CUDA initialization failure with error: 35
Paula DerrengerUltralyticsHey there! 🌟 It looks like you've encountered the CUDA initialization failure error with code 35, which usually indicates a CUDA driver/runtime version mismatch or an issue with accessing your GPU.
Here are a couple of steps you can try to resolve the issue:
- Check CUDA Compatibility: Ensure that the installed CUDA version is compatible with the version required by TensorRT.
- Update Drivers: Sometimes, simply updating your NVIDIA drivers can resolve such issues.
- Environment Check: Make sure your environment variables (like
PATHandLD_LIBRARY_PATHfor Linux) are correctly set to include paths to CUDA toolkit and libraries.
If these steps don't help, could you provide a bit more context about your setup? Specifically:
- The versions of CUDA, TensorRT, and PyTorch you're using.
- The output of
nvidia-smito check if the GPU is being recognized properly.
This information can help pinpoint the issue more accurately. Thanks for reaching out, and looking forward to getting you past this hurdle! 🚀
Zency-Sun
Thank you for your patient reply, I have resolved the above issue!
Paula DerrengerUltralytics(modifié)@Zency-Sun i'm glad to hear you've resolved your previous issue! Regarding your question about model benchmarking, it's a great way to understand your model's performance across different formats. Here's a quick overview of what you might find useful:
- Why Benchmark?: Helps you make informed decisions by understanding the trade-off between speed and accuracy across different formats and on varied hardware.
- Key Metrics: Look at mAP50-95 for detection accuracy, and inference time for speed. This gives you a holistic view of how well your model performs.
For benchmarking specific formats like PyTorch, ONNX, OpenVINO, and TensorRT, use the
benchmarkutility with theformatargument. It exports the model for you:from ultralytics.utils.benchmarks import benchmark # "-" = PyTorch; OpenVINO runs on CPU, TensorRT on GPU for fmt, device in [("-", "cuda:0"), ("onnx", "cuda:0"), ("openvino", "cpu"), ("engine", "cuda:0")]: benchmark(model="yolo26n.pt", data="coco8.yaml", imgsz=640, device=device, format=fmt)And for CLI:
yolo benchmark model=yolo26n.pt data=coco8.yaml imgsz=640 device=0 format=onnx # Repeat with format=openvino (device=cpu) and format=engineRemember, exporting to ONNX or OpenVINO can speed up CPU inference, and TensorRT is excellent for maximizing GPU efficiency. 🚀
Let me know if there's anything else you need help with!