4.1. data_augmentor module

4.1.1. Summary

Classes:

Blur Gaussian blur filter.
Brightness Adjust image brightness.
Color Adjust image color.
Contrast Adjust image contrast.
Crop Crop image.
FlipLeftRight Flip left right.
FlipTopBottom Flip top bottom.
Hue Change image hue.
Pad Add padding to images.
RandomErasing Class that performs Random Erasing in Random Erasing Data Augmentation by Zhong et al.
RandomErasingForDetection Class that performs Random Erasing in Random Erasing Data Augmentation by Zhong et al.
RandomPatchCut Cut out random patches of the image.
Rotate Rotate.
SSDRandomCrop SSD random crop.

4.1.2. Reference

class lmnet.data_augmentor.Blur(value=(0, 1))

Gaussian blur filter.

Reference:
http://pillow.readthedocs.io/en/4.3.x/Referenceserence/ImageFilter.html#PIL.ImageFilter.GaussianBlur
Parameters:value (int | list | tuple) – Blur radius. Default is random number from 0 to 1. References default is 2.
class lmnet.data_augmentor.Brightness(value=(0.75, 1.25))

Adjust image brightness.

Reference:
http://pillow.readthedocs.io/en/4.2.x/Referenceserence/ImageEnhance.html#PIL.ImageEnhance.Brightness
Parameters:value (int | list | tuple) – An enhancement factor of 0.0 gives a black image. A factor of 1.0 gives the original image.
class lmnet.data_augmentor.Color(value=(0.75, 1.25))

Adjust image color.

Reference:
http://pillow.readthedocs.io/en/4.2.x/Referenceserence/ImageEnhance.html#PIL.ImageEnhance.Color
Parameters:value (int | list | tuple) – An enhancement factor of 0.0 gives a black and white image. A factor of 1.0 gives the original image.
class lmnet.data_augmentor.Contrast(value=(0.75, 1.25))

Adjust image contrast.

Reference:
http://pillow.readthedocs.io/en/4.2.x/Referenceserence/ImageEnhance.html#PIL.ImageEnhance.Contrast
Parameters:value (int | list | tuple) – An enhancement factor of 0.0 gives a solid grey image. A factor of 1.0 gives the original image.
class lmnet.data_augmentor.Crop(size, resize=None)

Crop image.

Parameters:
  • size (int | list | tuple) – Crop to this size.
  • resize (int | list | tuple) – If there are resize param, resize and crop.
class lmnet.data_augmentor.FlipLeftRight(probability=0.5)

Flip left right.

Parameters:probability (number) – Probability for flipping.
class lmnet.data_augmentor.FlipTopBottom(probability=0.5)

Flip top bottom.

Parameters:probability (number) – Probability for flipping.
class lmnet.data_augmentor.Hue(value=(-10, 10))

Change image hue.

Parameters:value (int | list | tuple) – Assume the value in -255, 255. When the value is 0, nothing to do.
class lmnet.data_augmentor.Pad(value, fill=0)

Add padding to images.

Parameters:
  • value (int or tuple) – Padding on each border. If a single int is provided this is used to pad all borders. If tuple of length 2 is provided this is the padding on left/right and top/bottom respectively. If a tuple of length 4 is provided this is the padding for the left, top, right and bottom borders respectively.
  • fill (int) – Pixel fill value. Default is 0.
class lmnet.data_augmentor.RandomErasing(probability=0.5, sl=0.02, sh=0.4, r1=0.3, content_type='mean', mean=[125, 122, 114])

Class that performs Random Erasing in Random Erasing Data Augmentation by Zhong et al. The following Args(hyper parameters) are referred to the paper.

Parameters:
  • probability (float) – The probability that the operation will be performed.
  • sl (float) – min erasing area
  • sh (float) – max erasing area
  • r1 (float) – min aspect ratio
  • content_type (string) – type of erasing value: {“mean”, “random”}
  • mean (list) – erasing value if you use “mean” mode (mean ImageNet pixel value)
class lmnet.data_augmentor.RandomErasingForDetection(probability=0.5, sl=0.02, sh=0.2, r1=0.3, content_type='mean', mean=[125, 122, 114], i_a=True, o_a=True)

Class that performs Random Erasing in Random Erasing Data Augmentation by Zhong et al. The following Args(hyper parameters) are referred to the paper. This Augmentation can be used when you train object detection task.

Parameters:
  • probability (float) – The probability that the operation will be performed.
  • sl (float) – min erasing area
  • sh (float) – max erasing area
  • r1 (float) – min aspect ratio
  • content_type (string) – type of erasing value: {“mean”, “random”}
  • mean (list) – erasing value if you use “mean” mode (mean ImageNet pixel value)
  • i_a (bool) – image-aware, random erase an entire image.
  • o_a (bool) – object-aware, random erase each object bounding boxes.
class lmnet.data_augmentor.RandomPatchCut(num_patch=1, max_size=10, square=True)

Cut out random patches of the image.

Parameters:
  • num_patch (int) – number of random patch cut-outs to generate
  • max_size (int) – maximum size of the patch edge, in percentages of image size
  • square (bool) – force square aspect ratio for patch shape
class lmnet.data_augmentor.Rotate(angle_range=(0, 90))

Rotate.

Parameters:angle_range (int | list | tuple) – Angle range.
class lmnet.data_augmentor.SSDRandomCrop(min_crop_ratio=0.3)

SSD random crop.

References

https://github.com/amdegroot/ssd.pytorch/blob/master/utils/augmentations.py#L208

Parameters:min_crop_ratio (number) – Minimum crop ratio for cropping the