ImageAugmentationLayer

ImageAugmentationLayer[{h,w}]

represents a net layer that applies random image transformations to produce images of height h and width w.

Details and Options

Examples

open allclose all

Basic Examples  (2)

Create an ImageAugmentationLayer whose output dimensions are {n,80,80}:

In[1]:=
Click for copyable input
Out[1]=

Create an ImageAugmentationLayer that takes an image of size 128×128 and returns an image crop of size 80×80:

In[1]:=
Click for copyable input
Out[1]=

Apply the layer to an image, obtaining the center crop:

In[2]:=
Click for copyable input
Out[2]=

Apply the layer to an image, specifying that training behavior be used:

In[3]:=
Click for copyable input
Out[3]=

The layer threads across a batch of examples:

In[4]:=
Click for copyable input
Out[4]=

Options  (1)

Possible Issues  (1)

See Also

SpatialTransformationLayer  ConvolutionLayer  PoolingLayer  ResizeLayer  NetChain  NetGraph  NetTrain  NetEvaluationMode  ImageTransformation  ImageCrop  ImageReflect  ImageRotate

Introduced in 2017
(11.1)