Model Ensembling (original) (raw)

YOLOv5 Model Ensembling

📚 This guide explains how to use Ultralytics YOLOv5 🚀 model ensembling during testing and inference for improved mAP and Recall.

From 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.

Before You Start

Clone repo and install requirements.txt in a Python>=3.8.0 environment, including PyTorch>=1.8. Models and datasets download automatically from the latest YOLOv5 release.

git clone https://github.com/ultralytics/yolov5 # clone cd yolov5 pip install -r requirements.txt # install

Test Normally

Before ensembling, establish the baseline performance of a single model. This command tests YOLOv5x on COCO val2017 at image size 640 pixels. yolov5x.pt is the largest and most accurate model available. Other options are yolov5s.pt, yolov5m.pt and yolov5l.pt, or your own checkpoint from training a custom dataset ./weights/best.pt. For details on all available models, see the pretrained checkpoints table.

python val.py --weights yolov5x.pt --data coco.yaml --img 640 --half

Output:

`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_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

Ensemble Test

Multiple pretrained models can be ensembled together at test and inference time by simply appending extra models to the --weights argument in any existing val.py or detect.py command. This example tests an ensemble of 2 models together:

YOLOv5x
YOLOv5l6

python val.py --weights yolov5x.pt yolov5l6.pt --data coco.yaml --img 640 --half

Output:

`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_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

Ensemble Inference

Append extra models to the --weights argument to run ensemble inference:

python detect.py --weights yolov5x.pt yolov5l6.pt --img 640 --source data/images

Output:

`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) `

YOLO inference result

Benefits of Model Ensembling

Model ensembling with YOLOv5 offers several advantages:

Improved Accuracy: As demonstrated in the examples above, ensembling multiple models increases mAP from 0.504 to 0.515 and mAR from 0.681 to 0.689.
Better Generalization: Combining diverse models helps reduce overfitting and improves performance on varied data.
Enhanced Robustness: Ensembles are typically more robust to noise and outliers in the data.
Complementary Strengths: Different models may excel at detecting different types of objects or in different environmental conditions.

The primary trade-off is increased inference time, as shown in the speed metrics (22.4ms for single model vs. 39.5ms for ensemble).

When to Use Model Ensembling

Consider using model ensembling in these scenarios:

When accuracy is more important than inference speed
For critical applications where false negatives must be minimized
When processing challenging images with varied lighting, occlusion, or scale
During competitions or benchmarking where maximum performance is required

For real-time applications with strict latency requirements, single model inference may be more appropriate.

Supported Environments

Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as CUDA, CUDNN, Python, and PyTorch, to kickstart your projects.

Project Status

This badge indicates that all YOLOv5 GitHub Actions Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: training, validation, inference, export, and benchmarks. They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit.

📅 Created 1 year ago ✏️ Updated 28 days ago