ultralytics/docs/en/yolov5/tutorials/test_time_augmentation.md

---
comments: true
description: Boost your YOLOv5 performance with Test-Time Augmentation (TTA). Learn setup, testing, and inference techniques to elevate mAP and Recall.
keywords: YOLOv5, Test-Time Augmentation, TTA, machine learning, deep learning, object detection, mAP, Recall, PyTorch
---

# Test-Time Augmentation (TTA)

📚 This guide explains how to use Test Time Augmentation (TTA) during testing and inference for improved mAP and [Recall](https://www.ultralytics.com/glossary/recall) with YOLOv5 🚀.

## Before You Start

Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases).

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

## Test Normally

Before trying TTA we want to establish a baseline performance to compare to. 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 please see our [YOLOv5 documentation](https://docs.ultralytics.com/models/yolov5/).

```bash
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

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 with TTA

Append `--augment` to any existing `val.py` command to enable TTA, and increase the image size by about 30% for improved results. Note that inference with TTA enabled will typically take about 2-3X the time of normal inference as the images are being left-right flipped and processed at 3 different resolutions, with the outputs merged before [NMS](https://www.ultralytics.com/glossary/non-maximum-suppression-nms). Part of the speed decrease is simply due to larger image sizes (832 vs 640), while part is due to the actual TTA operations, so ensure your GPU has enough memory headroom before increasing `--img`.

```bash
python val.py --weights yolov5x.pt --data coco.yaml --img 832 --augment --half
```

Output:

```
val: data=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=832, conf_thres=0.001, iou_thres=0.6, task=val, device=, single_cls=False, augment=True, 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...
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  /pytorch/c10/core/TensorImpl.h:1156.)
  return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
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, 2885.61it/s]
val: New cache created: ../datasets/coco/val2017.cache
               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 157/157 [07:29<00:00,  2.86s/it]
                 all       5000      36335      0.718      0.656      0.695      0.503
Speed: 0.2ms pre-process, 80.6ms inference, 2.7ms NMS per image at shape (32, 3, 832, 832)  # <--- TTA speed

Evaluating pycocotools mAP... saving runs/val/exp-2/yolov5x_predictions.json...
...
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.516  # <--- TTA mAP
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.701
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.562
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.361
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.564
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.656
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.388
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.640
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.696  # <--- TTA mAR
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.553
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.744
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.833
```

## Inference with TTA

`detect.py` TTA inference operates identically to `val.py` TTA: simply append `--augment` to any existing `detect.py` command:

```bash
python detect.py --weights yolov5s.pt --img 832 --source data/images --augment
```

Output:

```
YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB)

Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5s.pt to yolov5s.pt...
100% 14.1M/14.1M [00:00<00:00, 81.9MB/s]

Fusing layers...
Model Summary: 224 layers, 7266973 parameters, 0 gradients
image 1/2 /content/yolov5/data/images/bus.jpg: 832x640 4 persons, 1 bus, 1 fire hydrant, Done. (0.029s)
image 2/2 /content/yolov5/data/images/zidane.jpg: 480x832 3 persons, 3 ties, Done. (0.024s)
Results saved to runs/detect/exp
Done. (0.156s)
```

<img src="https://cdn.jsdelivr.net/gh/ultralytics/assets@main/docs/yolov5-test-time-augmentations.avif" width="500" alt="YOLOv5 test time augmentations">

### PyTorch Hub TTA

TTA is automatically integrated into all [YOLOv5 PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/) models, and can be accessed by passing `augment=True` at inference time.

```python
import torch

# Model
model = torch.hub.load("ultralytics/yolov5", "yolov5s")  # or yolov5m, yolov5x, custom

# Images
img = "https://ultralytics.com/images/zidane.jpg"  # or file, PIL, OpenCV, numpy, multiple

# Inference
results = model(img, augment=True)  # <--- TTA inference

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.
```

### Customize

You can customize the TTA operations applied in the [YOLOv5 `forward_augment()` method](https://github.com/ultralytics/yolov5/blob/8c6f9e15bfc0000d18b976a95b9d7c17d407ec91/models/yolo.py#L125-L137).

## Benefits of Test-Time Augmentation

Test-Time Augmentation offers several key advantages for [object detection](https://www.ultralytics.com/glossary/object-detection) tasks:

- **Improved Accuracy**: As demonstrated in the results above, TTA increases mAP from 0.504 to 0.516 and mAR from 0.681 to 0.696.
- **Better Small Object Detection**: TTA particularly enhances detection of small objects, with small area AP improving from 0.351 to 0.361.
- **Increased Robustness**: By testing multiple variations of each image, TTA reduces the impact of viewing angle, lighting, and other environmental factors.
- **Simple Implementation**: Requires only adding the `--augment` flag to existing commands.

The tradeoff is increased inference time, making TTA more suitable for applications where accuracy is prioritized over speed.

## Supported Environments

Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects.

- **Free GPU Notebooks**: <a href="https://bit.ly/yolov5-paperspace-notebook"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a> <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <a href="https://www.kaggle.com/models/ultralytics/yolov5"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md)
- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md)
- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md)
- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) <a href="https://hub.docker.com/r/ultralytics/yolov5"><img src="https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker" alt="Docker Pulls"></a>

## Project Status

<a href="https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml"><img src="https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml/badge.svg" alt="YOLOv5 CI"></a>

This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit.