Deep.Net


MSE

Namespace: Models

Mean over samples of squared error.

Functions and values

Function or valueDescription
error trgt pred
Signature: trgt:Tensor<'T> -> pred:Tensor<'T> -> float
Type parameters: 'T

Calculates the mean squared error. The mean is taken over the samples. The error is summed over all other dimensions. Shapes: pred[smpl, ...], target[smpl, ...]

ofPredictor (...)
Signature: dataset:TrnValTst<'S> -> batchSize:int64 -> trgtFn:('S -> Tensor<'T>) -> predFn:('S -> Tensor<'T>) -> float * float * float
Type parameters: 'S, 'T

Calculates the MSE of a predictor on the training, validation and test sets.

Fork me on GitHub