Why is accuracy absent in training progress plot?
18 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
I do not see training accuracy as illustrated in the docs. My code for training initialization is below and resultant plot attached.
% 6. specify training options
options = trainingOptions('sgdm', ...
BatchNormalizationStatistics = 'moving', ...
ExecutionEnvironment = 'auto', ...
GradientThreshold = 35, ...
InitialLearnRate = 0.0005, ...
LearnRateSchedule = 'piecewise', ...
LearnRateDropFactor = 0.99, ...
LearnRateDropPeriod = 1, ...
MaxEpochs = 20, ...
MiniBatchSize = 4, ...
Momentum = 0.9, ...
OutputNetwork = 'best-validation-loss', ...
Plots = 'training-progress', ...
ResetInputNormalization = false, ...
ValidationData = validationDS, ...
ValidationFrequency = 25, ...
VerboseFrequency = 5);
[trainedModel, info] = trainSOLOV2(trainingDS, preTrainedModel, options, ...
FreezeSubNetwork = "backbone", ExperimentMonitor = experiments.Monitor);

0 Kommentare
Antworten (1)
Matt J
am 26 Sep. 2023
Probably because the examples in the docs are for trainNetwork, not trainSOLOV2.
0 Kommentare
Siehe auch
Kategorien
Mehr zu Project Management finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!