docs/en/reference/data/augment.md

metadata

description: >-
  Explore Ultralytics image augmentation techniques like MixUp, Mosaic, and
  Random Perspective for enhancing model training. Improve your deep learning
  models now.
keywords: >-
  Ultralytics, image augmentation, MixUp, Mosaic, Random Perspective, deep
  learning, model training, YOLO

Reference for ultralytics/data/augment.py

!!! success "Improvements"

This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/augment.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/augment.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏

::: ultralytics.data.augment.BaseTransform

---

::: ultralytics.data.augment.Compose

---

::: ultralytics.data.augment.BaseMixTransform

---

::: ultralytics.data.augment.Mosaic

---

::: ultralytics.data.augment.MixUp

---

::: ultralytics.data.augment.CutMix

---

::: ultralytics.data.augment.RandomPerspective

---

::: ultralytics.data.augment.RandomHSV

---

::: ultralytics.data.augment.RandomFlip

---

::: ultralytics.data.augment.LetterBox

---

::: ultralytics.data.augment.CopyPaste

---

::: ultralytics.data.augment.Albumentations

---

::: ultralytics.data.augment.Format

---

::: ultralytics.data.augment.LoadVisualPrompt

---

::: ultralytics.data.augment.RandomLoadText

---

::: ultralytics.data.augment.ClassifyLetterBox

---

::: ultralytics.data.augment.CenterCrop

---

::: ultralytics.data.augment.ToTensor

---

::: ultralytics.data.augment.v8_transforms

---

::: ultralytics.data.augment.classify_transforms

---

::: ultralytics.data.augment.classify_augmentations