DeepLearning/Tensor/RandomCrop
randomly shuffle a Tensor to specified shape
DeepLearning/Tensor/RandomShuffle
randomly shuffle a Tensor along its first dimension
Calling Sequence
Parameters
Options
Description
Examples
Compatibility
RandomCrop(t,shape,opts)
RandomShuffle(t,opts)
t
-
Tensor
shape
list of integers
opts
zero or more options as specified below
name=string
The value of option name specifies an optional name for this Tensor, to be displayed in output and when visualizing the dataflow graph.
seed=integer[8]
The value of option seed specifies an initial seed for the random number generator. It is equivalent to invoking SetRandomSeed(seed). For more information see SetRandomSeed.
The RandomCrop(t,shape,opts) command constructs a Tensor with shape shape by randomly slicing data from t with uniform probability.
The RandomShuffle(t,opts) command randomly shuffles a Tensor along its first dimension.
Crop a random 3x2 slice from a 4x3 Tensor.
with⁡DeepLearning:
C ≔ Constant⁡3.5,7.9,−0.5,1|−3.8,−4.2,9.5,3|4.,−7.2,−8.2,2
C≔DeepLearning TensorShape: [4, 3]Data Type: float[8]
t1 ≔ RandomCrop⁡C,3,2
t1≔DeepLearning TensorShape: [3, 2]Data Type: float[8]
Shape⁡t1
3,2
Shuffle a Tensor along its first dimension.
t2 ≔ RandomShuffle⁡C
t2≔DeepLearning TensorShape: [4, 3]Data Type: float[8]
The DeepLearning/Tensor/RandomCrop and DeepLearning/Tensor/RandomShuffle commands were introduced in Maple 2018.
For more information on Maple 2018 changes, see Updates in Maple 2018.
See Also
DeepLearning Overview
DeepLearning,RandomTensor
DeepLearning,SetRandomSeed
Download Help Document
What kind of issue would you like to report? (Optional)