> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/mlfoundations/open_clip/llms.txt
> Use this file to discover all available pages before exploring further.

# AugmentationCfg

> Configuration dataclass for image augmentation during training

## Overview

`AugmentationCfg` defines data augmentation parameters for training image transforms. It controls random augmentations like resized cropping, color jitter, and random erasing.

## Class Definition

```python theme={null}
@dataclass
class AugmentationCfg:
    scale: Tuple[float, float] = (0.9, 1.0)
    ratio: Optional[Tuple[float, float]] = None
    color_jitter: Optional[Union[float, Tuple[float, float, float], Tuple[float, float, float, float]]] = None
    re_prob: Optional[float] = None
    re_count: Optional[int] = None
    use_timm: bool = False
    color_jitter_prob: float = None
    gray_scale_prob: float = None
```

## Fields

<ParamField path="scale" type="Tuple[float, float]" default="(0.9, 1.0)">
  Range of size of the random crop relative to the original image size. Used in RandomResizedCrop.

  * First value: minimum crop scale (e.g., 0.08 = crop can be 8% of original)
  * Second value: maximum crop scale (e.g., 1.0 = crop can be 100% of original)

  Common values:

  * `(0.08, 1.0)`: Standard ImageNet training
  * `(0.9, 1.0)`: Light augmentation
</ParamField>

<ParamField path="ratio" type="Tuple[float, float]" default="None">
  Range of aspect ratio of the random crop. Used in RandomResizedCrop.

  * First value: minimum aspect ratio (e.g., 0.75 = 3:4)
  * Second value: maximum aspect ratio (e.g., 1.33 = 4:3)

  If None, defaults to (3/4, 4/3) in torchvision.
</ParamField>

<ParamField path="color_jitter" type="Union[float, Tuple[float, ...]]" default="None">
  Color jitter augmentation strength. Can be specified as:

  * **float**: Applied to brightness, contrast, saturation (e.g., `0.4`)
  * **Tuple\[float, float, float]**: (brightness, contrast, saturation)
  * **Tuple\[float, float, float, float]**: (brightness, contrast, saturation, hue)

  Values are typically in range \[0, 1]. Higher values = stronger augmentation.

  Example: `(0.4, 0.4, 0.4, 0.1)` = moderate jitter with slight hue variation
</ParamField>

<ParamField path="re_prob" type="float" default="None">
  Random erasing probability. Probability of applying random erasing augmentation.

  * `0.0`: No random erasing
  * `0.25`: 25% chance of erasing per image
  * `1.0`: Always apply random erasing

  Requires `use_timm=True`.
</ParamField>

<ParamField path="re_count" type="int" default="None">
  Number of random erasing operations per image when random erasing is applied.

  Requires `use_timm=True`.
</ParamField>

<ParamField path="use_timm" type="bool" default="False">
  Whether to use timm (PyTorch Image Models) augmentation transforms.

  When True, enables advanced augmentations from timm:

  * RandAugment
  * Random erasing
  * More sophisticated augmentation pipelines

  When False, uses simple torchvision-based augmentations.
</ParamField>

<ParamField path="color_jitter_prob" type="float" default="None">
  Probability of applying color jitter when `use_timm=False`.

  * `0.0`: Never apply color jitter
  * `0.8`: Apply color jitter 80% of the time (common default)
  * `1.0`: Always apply color jitter

  Only used when `use_timm=False`.
</ParamField>

<ParamField path="gray_scale_prob" type="float" default="None">
  Probability of converting image to grayscale (with 3 channels) when `use_timm=False`.

  * `0.0`: Never grayscale
  * `0.2`: 20% chance of grayscale (common default)
  * `1.0`: Always grayscale

  Only used when `use_timm=False`.
</ParamField>

## Examples

### Standard ImageNet augmentation

```python theme={null}
from open_clip import AugmentationCfg, PreprocessCfg, image_transform_v2

# ImageNet-style training augmentation
aug_cfg = AugmentationCfg(
    scale=(0.08, 1.0),
    ratio=(0.75, 1.33),
    color_jitter=(0.4, 0.4, 0.4, 0.1),
    color_jitter_prob=0.8,
    gray_scale_prob=0.2
)

preprocess_cfg = PreprocessCfg(size=224)
train_transform = image_transform_v2(
    cfg=preprocess_cfg,
    is_train=True,
    aug_cfg=aug_cfg
)
```

### Light augmentation

```python theme={null}
# Minimal augmentation for fine-tuning
aug_cfg = AugmentationCfg(
    scale=(0.9, 1.0),  # Only small crops
    color_jitter=0.2,   # Light color jitter
    color_jitter_prob=0.5
)
```

### Strong augmentation with timm

```python theme={null}
# Advanced augmentation with timm
aug_cfg = AugmentationCfg(
    scale=(0.08, 1.0),
    color_jitter=0.4,
    re_prob=0.25,      # Random erasing
    re_count=1,
    use_timm=True      # Enable timm augmentations
)
```

### No augmentation

```python theme={null}
# Training without augmentation (only random crop)
aug_cfg = AugmentationCfg(
    scale=(1.0, 1.0),  # No scale variation
    ratio=None,
    color_jitter=None
)
```

### Custom aspect ratio range

```python theme={null}
# Allow more extreme aspect ratios
aug_cfg = AugmentationCfg(
    scale=(0.5, 1.0),
    ratio=(0.5, 2.0),  # From 1:2 to 2:1
    color_jitter=0.3
)
```

### Grayscale augmentation

```python theme={null}
# High grayscale probability for robustness
aug_cfg = AugmentationCfg(
    scale=(0.8, 1.0),
    gray_scale_prob=0.5  # 50% chance of grayscale
)
```

## Usage with image\_transform\_v2

```python theme={null}
import open_clip

preprocess_cfg = open_clip.PreprocessCfg(size=224)

# Create augmentation config
aug_cfg = open_clip.AugmentationCfg(
    scale=(0.08, 1.0),
    color_jitter=0.4,
    color_jitter_prob=0.8
)

# Create training transform
train_transform = open_clip.image_transform_v2(
    cfg=preprocess_cfg,
    is_train=True,
    aug_cfg=aug_cfg
)

# Use with dataset
from torchvision.datasets import ImageFolder
train_dataset = ImageFolder('data/train', transform=train_transform)
```

## Augmentation Strategy Guide

<CardGroup cols={2}>
  <Card title="Light Augmentation" icon="feather">
    * scale: (0.9, 1.0)
    * color\_jitter: 0.2
    * Best for: Fine-tuning, small datasets
  </Card>

  <Card title="Standard Augmentation" icon="image">
    * scale: (0.08, 1.0)
    * color\_jitter: 0.4
    * Best for: Training from scratch
  </Card>

  <Card title="Strong Augmentation" icon="bolt">
    * use\_timm: True
    * re\_prob: 0.25
    * Best for: Large-scale training
  </Card>

  <Card title="Minimal Augmentation" icon="minimize">
    * scale: (0.95, 1.0)
    * No color jitter
    * Best for: High-quality datasets
  </Card>
</CardGroup>

## Notes

* Only used when `is_train=True` in `image_transform_v2()`
* `color_jitter_prob` and `gray_scale_prob` are ignored when `use_timm=True`
* Random erasing (`re_prob`, `re_count`) requires `use_timm=True`
* Default values provide minimal augmentation; increase for stronger regularization
* For contrastive learning, stronger augmentation typically improves performance

## See Also

* [`PreprocessCfg`](/api/preprocess-cfg) - Preprocessing configuration
* [`image_transform_v2()`](/api/image-transform) - Create transforms with config