Albumentations - 快速图像增强库和易于使用的包装其他库-python开发

# Albumentations [](https://badge.fury.io/py/albumentations)  Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to increase the quality of trained models. The purpose of image augmentation is to create new training samples from the existing data. Here is an example of how you can apply some augmentations from Albumentations to create new images from the original one:  ## Why Albumentations - Albumentations **[supports all common computer vision tasks](#i-want-to-use-albumentations-for-the-specific-task-such-as-classification-or-segmentation)** such as classification, semantic segmentation, instance segmentation, object detection, and pose estimation. - The library provides **[a simple unified API](#a-simple-example)** to work with all data types: images (RBG-images, grayscale images, multispectral images), segmentation masks, bounding boxes, and keypoints. - The library contains **[more than 70 different augmentations](#list-of-augmentations)** to generate new training samples from the existing data. - Albumentations is [**fast**](#benchmarking-results). We benchmark each new release to ensure that augmentations provide maximum speed. - It **[works with popular deep learning frameworks](#i-want-to-know-how-to-use-albumentations-with-deep-learning-frameworks)** such as PyTorch and TensorFlow. By the way, Albumentations is a part of the [PyTorch ecosystem](https://pytorch.org/ecosystem/). - [**Written by experts**](#authors). The authors have experience both working on production computer vision systems and participating in competitive machine learning. Many core team members are Kaggle Masters and Grandmasters. - The library is [**widely used**](#who-is-using-albumentations) in industry, deep learning research, machine learning competitions, and open source projects. ## Table of contents - [Authors](#authors) - [Installation](#installation) - [Documentation](#documentation) - [A simple example](#a-simple-example) - [Getting started](#getting-started) - [I am new to image augmentation](#i-am-new-to-image-augmentation) - [I want to use Albumentations for the specific task such as classification or segmentation](#i-want-to-use-albumentations-for-the-specific-task-such-as-classification-or-segmentation) - [I want to know how to use Albumentations with deep learning frameworks](#i-want-to-know-how-to-use-albumentations-with-deep-learning-frameworks) - [I want to explore augmentations and see Albumentations in action](#i-want-to-explore-augmentations-and-see-albumentations-in-action) - [Who is using Albumentations](#who-is-using-albumentations) - [List of augmentations](#list-of-augmentations) - [Pixel-level transforms](#pixel-level-transforms) - [Spatial-level transforms](#spatial-level-transforms) - [A few more examples of augmentations](#a-few-more-examples-of-augmentations) - [Benchmarking results](#benchmarking-results) - [Contributing](#contributing) - [Comments](#comments) - [Citing](#citing) ## Authors [**Alexander Buslaev** — Computer Vision Engineer at Mapbox](https://www.linkedin.com/in/al-buslaev/) | [Kaggle Master](https://www.kaggle.com/albuslaev) [**Alex Parinov** — Tech Lead at SberDevices](https://www.linkedin.com/in/alex-parinov/) | [Kaggle Master](https://www.kaggle.com/creafz) [**Vladimir I. Iglovikov** — Staff Engineer at Lyft Level5](https://www.linkedin.com/in/iglovikov/) | [Kaggle Grandmaster](https://www.kaggle.com/iglovikov) [**Evegene Khvedchenya** — Computer Vision Research Engineer at Piñata Farms](https://www.linkedin.com/in/cvtalks/) | [Kaggle Grandmaster](https://www.kaggle.com/bloodaxe) [**Mikhail Druzhinin** — Computer Vision Engineer at ID R&D](https://www.linkedin.com/in/mikhail-druzhinin-548229100/) | [Kaggle Expert](https://www.kaggle.com/dipetm) ## Installation Albumentations requires Python 3.6 or higher. To install the latest version from PyPI: ``` pip install -U albumentations ``` Other installation options are described in the [documentation](https://albumentations.ai/docs/getting_started/installation/). ## Documentation The full documentation is available at **[https://albumentations.ai/docs/](https://albumentations.ai/docs/)**. ## A simple example ```python import albumentations as A import cv2 # Declare an augmentation pipeline transform = A.Compose([ A.RandomCrop(width=256, height=256), A.HorizontalFlip(p=0.5), A.RandomBrightnessContrast(p=0.2), ]) # Read an image with OpenCV and convert it to the RGB colorspace image = cv2.imread("image.jpg") image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) # Augment an image transformed = transform(image=image) transformed_image = transformed["image"] ``` ## Getting started ### I am new to image augmentation Please start with the [introduction articles](https://albumentations.ai/docs/#introduction-to-image-augmentation) about why image augmentation is important and how it helps to build better models. ### I want to use Albumentations for the specific task such as classification or segmentation If you want to use Albumentations for a specific task such as classification, segmentation, or object detection, refer to the [set of articles](https://albumentations.ai/docs/#getting-started-with-albumentations) that has an in-depth description of this task. We also have a [list of examples](https://albumentations.ai/docs/examples/) on applying Albumentations for different use cases. ### I want to know how to use Albumentations with deep learning frameworks We have [examples of using Albumentations](https://albumentations.ai/docs/#examples-of-how-to-use-albumentations-with-different-deep-learning-frameworks) along with PyTorch and TensorFlow. ### I want to explore augmentations and see Albumentations in action Check the [online demo of the library](https://albumentations-demo.herokuapp.com/). With it, you can apply augmentations to different images and see the result. Also, we have a [list of all available augmentations and their targets](#list-of-augmentations). ## Who is using Albumentations <a href="https://www.lyft.com/" target="_blank"><img src="https://habrastorage.org/webt/ce/bs/sa/cebssajf_5asst5yshmyykqjhcg.png" width="100"/></a> <a href="https://www.x5.ru/en" target="_blank"><img src="https://habrastorage.org/webt/9y/dv/f1/9ydvf1fbxotkl6nyhydrn9v8cqw.png" width="100"/></a> <a href="https://imedhub.org/" target="_blank"><img src="https://habrastorage.org/webt/eq/8x/m-/eq8xm-fjfx_uqkka4_ekxsdwtiq.png" width="100"/></a> <a href="https://recursionpharma.com" target="_blank"><img src="https://pbs.twimg.com/profile_images/925897897165639683/jI8YvBfC_400x400.jpg" width="100"/></a> <a href="https://www.everypixel.com/" target="_blank"><img src="https://www.everypixel.com/i/logo_sq.png" width="100"/></a> <a href="https://neuromation.io/" target="_blank"><img src="https://habrastorage.org/webt/yd/_4/xa/yd_4xauvggn1tuz5xgrtkif6lya.png" width="100"/></a> #### See also: - [A list of papers that cite Albumentations](https://albumentations.ai/whos_using#research). - [A list of teams that were using Albumentations and took high places in machine learning competitions](https://albumentations.ai/whos_using#competitions). - [Open source projects that use Albumentations](https://albumentations.ai/whos_using#open-source). ## List of augmentations ### Pixel-level transforms Pixel-level transforms will change just an input image and will leave any additional targets such as masks, bounding boxes, and keypoints unchanged. The list of pixel-level transforms: - [Blur](https://albumentations.ai/docs/api_reference/augmentations/transforms/#albumentations.augmentations.transforms.Blur) - [CLAHE](https://albumentations.ai/docs/api_reference/augme