Stay updated

News & Insights
API ReferenceTransforms & Targets
Lib ComparisonTargets by TransformFAQLicense Guide
Multi-TargetUltralytics CustomD4 TransformReplayCompose DebugSimple PipelineDomain AdaptationHuggingFace HubText on Imagesexample_xymaskingFace LandmarksSave/Load PipelineKeep All BboxesKeras ClassificationChromatic AberrationTorchvision MigrationMorphologicalMosaic TransformOBB Affine BoatsOverlay ElementsPyTorch ClassificationPyTorch SegmentationRandomGridShuffleKeras SegmentationShowcaseSegmentation (Kaggle)Bounding BoxesKeypointsWeather Transforms

title: "example weather transforms" notebookName: "example_weather_transforms.ipynb"

Open in Google ColabRun this notebook interactively

Weather augmentations in Albumentations

This notebook demonstrates weather augmentations that are supported by Albumentations.

Import the required libraries

import albumentations as A
import cv2
from matplotlib import pyplot as plt

/opt/homebrew/Caskroom/miniconda/base/envs/albumentations_examples/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

Define a function to visualize an image

def visualize(image):
    plt.figure(figsize=(20, 10))
    plt.axis("off")
    plt.imshow(image)

Load the image from the disk

image = cv2.imread("images/weather_example.jpg", cv2.IMREAD_COLOR_RGB)

Visualize the original image

visualize(image)

No code provided

png

No code provided

RandomRain

We fix the random seed for visualization purposes, so the augmentation will always produce the same result. In a real computer vision pipeline, you shouldn't fix the random seed before applying a transform to the image because, in that case, the pipeline will always output the same image. The purpose of image augmentation is to use different transformations each time.

transform = A.Compose(
    [A.RandomRain(brightness_coefficient=0.8, drop_width=1, blur_value=5, p=1, rain_type="heavy")],
    strict=True,
    seed=137,
)
transformed = transform(image=image)
visualize(transformed["image"])

No code provided

png

No code provided

RandomSnow

transform = A.Compose(
    [A.RandomSnow(brightness_coeff=2.5, snow_point_range=(0.3, 0.5), p=1)],
    strict=True,
    seed=137,
)
transformed = transform(image=image)
visualize(transformed["image"])

No code provided

png

No code provided

RandomSunFlare

transform = A.Compose(
    [A.RandomSunFlare(flare_roi=(0, 0, 1, 0.5), p=1)],
    strict=True,
    seed=137,
)
transformed = transform(image=image)
visualize(transformed["image"])

No code provided

png

No code provided

RandomShadow

transform = A.Compose(
    [A.RandomShadow(num_shadows_limit=(4, 4), shadow_dimension=5, shadow_roi=(0, 0.5, 1, 1), p=1)],
    strict=True,
    seed=137,
)

transformed = transform(image=image)
visualize(transformed["image"])

No code provided

png

No code provided

RandomFog

transform = A.Compose(
    [A.RandomFog(fog_coef_range=(1, 1), alpha_coef=0.4, p=1)],
    strict=True,
    seed=137,
)
transformed = transform(image=image)
visualize(transformed["image"])

No code provided

png

No code provided