'InitalLearnRate' is not an option for solver 'sgdm'.

10 views (last 30 days)
options = trainingOptions('sgdm', ...
'MiniBatchSize',128, ...
'MaxEpochs',1, ...
'InitalLearnRate',1e-4);
I can not set InitalLearnRate
Error using nnet.cnn.TrainingOptionsSGDM (line 128)
'InitalLearnRate' is not an option for solver 'sgdm'.
Error in trainingOptions (line 440)
opts = nnet.cnn.TrainingOptionsSGDM(varargin{:});
Error in test3 (line 159)
options = trainingOptions('sgdm', ...
MATLAB version is R2023b
  1 Comment
KSSV
KSSV on 3 Apr 2024
options = trainingOptions('sgdm')
options =
TrainingOptionsSGDM with properties: Momentum: 0.9000 InitialLearnRate: 0.0100 MaxEpochs: 30 LearnRateSchedule: 'none' LearnRateDropFactor: 0.1000 LearnRateDropPeriod: 10 MiniBatchSize: 128 Shuffle: 'once' CheckpointFrequency: 1 CheckpointFrequencyUnit: 'epoch' SequenceLength: 'longest' PreprocessingEnvironment: 'serial' L2Regularization: 1.0000e-04 GradientThresholdMethod: 'l2norm' GradientThreshold: Inf Verbose: 1 VerboseFrequency: 50 ValidationData: [] ValidationFrequency: 50 ValidationPatience: Inf ObjectiveMetricName: 'loss' CheckpointPath: '' ExecutionEnvironment: 'auto' OutputFcn: [] Metrics: [] Plots: 'none' SequencePaddingValue: 0 SequencePaddingDirection: 'right' InputDataFormats: "auto" TargetDataFormats: "auto" ResetInputNormalization: 1 BatchNormalizationStatistics: 'auto' OutputNetwork: 'auto' Acceleration: "auto"
sgdm supports InitalLearnRate.

Sign in to comment.

Accepted Answer

VBBV
VBBV on 3 Apr 2024
      options = trainingOptions('sgdm', ...
        'MiniBatchSize',128, ...
        'MaxEpochs',1, ...
        'InitialLearnRate',1e-4);

There is a type error in the function

  2 Comments
VBBV
VBBV on 3 Apr 2024
Edited: VBBV on 3 Apr 2024

You have mistyped the spelling in the function. Check the spelling as InitalLearnRate there is a missing 'i'

Sign in to comment.

More Answers (0)

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Products


Release

R2023b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!