name=string

seed=integer[8]

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.

$\mathrm{with}\left(\mathrm{DeepLearning}\right)\:$

$C≔\mathrm{Constant}\left(⟨⟨3.5\,7.9\,-0.5\,1⟩\left|⟨-3.8\,-4.2\,9.5\,3⟩\right|⟨4.\,-7.2\,-8.2\,2⟩⟩\right)$

$C≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Shape:\; [4,\; 3]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$\mathrm{t1}≔\mathrm{RandomCrop}\left(C\,\left[3\,2\right]\right)$

$\mathrm{t1}≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Shape:\; [3,\; 2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$\mathrm{Shape}\left(\mathrm{t1}\right)$

$\left[3\,2\right]$

$\mathrm{t2}≔\mathrm{RandomShuffle}\left(C\right)$

$\mathrm{t2}≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Shape:\; [4,\; 3]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

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.