Assemblaggio di modelli
📚 This guide explains how to use YOLOv5 🚀 model ensembling during testing and inference for improved mAP and Recall.
Da https://en.wikipedia.org/wiki/Ensemble_learning:
Ensemble modeling is a process where multiple diverse models are created to predict an outcome, either by using many different modeling algorithms or using different training data sets. The ensemble model then aggregates the prediction of each base model and results in once final prediction for the unseen data. The motivation for using ensemble models is to reduce the generalization error of the prediction. As long as the base models are diverse and independent, the prediction error of the model decreases when the ensemble approach is used. The approach seeks the wisdom of crowds in making a prediction. Even though the ensemble model has multiple base models within the model, it acts and performs as a single model.
Prima di iniziare
Clona il repo e installa il file requirements.txt in un file di tipo Python>=3.8.0 con l'inclusione di PyTorch>=1.8. I modelli e i dataset vengono scaricati automaticamente dall'ultimarelease di YOLOv5 .
git clone https://github.com/ultralytics/yolov5 # clone
cd yolov5
pip install -r requirements.txt # install
Prova normalmente
Prima di procedere all'assemblaggio, vogliamo stabilire le prestazioni di base di un singolo modello. Questo comando testa YOLOv5x su COCO val2017 con un'immagine di 640 pixel. yolov5x.pt
è il modello più grande e accurato disponibile. Le altre opzioni sono yolov5s.pt
, yolov5m.pt
e yolov5l.pt
oppure il tuo checkpoint dall'addestramento di un set di dati personalizzato ./weights/best.pt
. Per maggiori dettagli su tutti i modelli disponibili, consulta il nostro README. Tavolo.
Uscita:
val: data=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True
YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB)
Fusing layers...
Model Summary: 476 layers, 87730285 parameters, 0 gradients
val: Scanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2846.03it/s]
val: New cache created: ../datasets/coco/val2017.cache
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [02:30<00:00, 1.05it/s]
all 5000 36335 0.746 0.626 0.68 0.49
Speed: 0.1ms pre-process, 22.4ms inference, 1.4ms NMS per image at shape (32, 3, 640, 640) # <--- baseline speed
Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...
...
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.504 # <--- baseline mAP
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.546
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.628
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.681 # <--- baseline mAR
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.826
Test dell'ensemble
Più modelli preaddestrati possono essere assemblati insieme al momento del test e dell'inferenza, semplicemente aggiungendo modelli extra al file --weights
in qualsiasi comando val.py o detect.py esistente. Questo esempio testa un insieme di 2 modelli insieme:
- YOLOv5x
- YOLOv5l6
Uscita:
val: data=./data/coco.yaml, weights=['yolov5x.pt', 'yolov5l6.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.6, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True
YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB)
Fusing layers...
Model Summary: 476 layers, 87730285 parameters, 0 gradients # Model 1
Fusing layers...
Model Summary: 501 layers, 77218620 parameters, 0 gradients # Model 2
Ensemble created with ['yolov5x.pt', 'yolov5l6.pt'] # Ensemble notice
val: Scanning '../datasets/coco/val2017.cache' images and labels... 4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:00<00:00, 49695545.02it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [03:58<00:00, 1.52s/it]
all 5000 36335 0.747 0.637 0.692 0.502
Speed: 0.1ms pre-process, 39.5ms inference, 2.0ms NMS per image at shape (32, 3, 640, 640) # <--- ensemble speed
Evaluating pycocotools mAP... saving runs/val/exp3/yolov5x_predictions.json...
...
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.515 # <--- ensemble mAP
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.699
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.557
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.356
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.563
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.668
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.387
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.638
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.689 # <--- ensemble mAR
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.526
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.743
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.844
Inferenza di gruppo
Aggiungi dei modelli extra al file --weights
per eseguire l'inferenza d'insieme:
Uscita:
YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB)
Fusing layers...
Model Summary: 476 layers, 87730285 parameters, 0 gradients
Fusing layers...
Model Summary: 501 layers, 77218620 parameters, 0 gradients
Ensemble created with ['yolov5x.pt', 'yolov5l6.pt']
image 1/2 /content/yolov5/data/images/bus.jpg: 640x512 4 persons, 1 bus, 1 tie, Done. (0.063s)
image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 3 persons, 2 ties, Done. (0.056s)
Results saved to runs/detect/exp2
Done. (0.223s)
Ambienti supportati
Ultralytics offre una serie di ambienti pronti all'uso, ognuno dei quali è preinstallato con le dipendenze essenziali, come ad esempio CUDA, CUDNN, Python, e PyTorchper dare il via ai tuoi progetti.
- Taccuini gratuiti GPU:
- Google Cloud: Guida rapida a GCP
- Amazon: Guida rapida di AWS
- Azure: Guida rapida ad AzureML
- Docker: Guida rapida a Docker
Stato del progetto
Questo badge indica che tutti i test di YOLOv5 GitHub Actions Continuous Integration (CI) sono stati superati con successo. Questi test CI verificano rigorosamente la funzionalità e le prestazioni di YOLOv5 in vari aspetti chiave: formazione, validazione, inferenza, esportazione e benchmark. Assicurano un funzionamento coerente e affidabile su macOS, Windows e Ubuntu, con test condotti ogni 24 ore e su ogni nuovo commit.