DynaML v1.5.3-beta.1 Release Notes
Release Date: 2018-03-09 // about 6 years ago-
โ Additions
Tensorflow Utilities
๐ฆ Package
dynaml.tensorflow
The
dtfpipe
object is created to house data pipelines and workflows around tensorflow primitives.dtfpipe.gaussian_standardization
performs Gaussian Scaling of the data and returnsGaussianScalerTF
objects, one each for the input and output data.dtfpipe.minmax_standardization
performs[0, 1]
scaling of the features and ouputs, returningMinMaxScalerTF
objects.
Usage
import io.github.mandar2812.dynaml.tensorflow.\_import org.platanios.tensorflow.api.\_val (inputs, outputs): (Tensor, Tensor) = ...val (scaledData, (features\_scaler, targets\_scaler)) = dtfpipe.gaussian\_standardization(inputs, outputs)
๐ฆ Package
dynaml.tensorflow.utils
- โ Added
GaussianScalerTF
andMinMaxScalerTF
, to enable scaling-rescaling of tensorflow data sets.
๐ฆ Package
dynaml.tensorflow.layers
Dynamical Systems: Continuous Time RNN
The continuous time recurrent neural network; CTRNN, when discretised for a finite time horizon is represented as the computational layer
FiniteTimeCTRNN
.๐ฆ Package
dynaml.tensorflow.learn
- โ Added
MVTimeSeriesLoss
which helps quantify the average L2 loss over a finite time slice of a multivariate time series.