清空筛选条件
清空筛选条件

skipping augmentedImageDatastore to train a net

1 次查看（过去 30 天）
omer wagner
omer wagner 2024-2-20
评论： Cris LaPierre 2024-2-21
Hi,
Following the example in "Train Deep Learning Network to Classify New Images",
How can I finetune my net without the augmentedImageDatastore step?
(I want to observe the performance when there arent any variations on the data)

请先登录，再回答此问题。

回答（1 个）

Cris LaPierre
Cris LaPierre 2024-2-20
You will need to remove it from your network. Look into removeLayer
  2 个评论
omer wagner
omer wagner 2024-2-21
Could I use this on the same network (after performing the training on the Augmented), or that the layer is there in the final architecture?
no_aug_options = trainingOptions('sgdm', ...
'MiniBatchSize',miniBatchSize, ...
'MaxEpochs',6, ...
'InitialLearnRate',3e-4, ...
'Shuffle','every-epoch', ...
'ValidationData',imdsValidation, ...
'ValidationFrequency',valFrequency, ...
'Verbose',false, ...
'Plots','training-progress');
no_aug_net = trainNetwork(imdsTrain,lgraph,no_aug_options);
Cris LaPierre
Cris LaPierre 2024-2-21
The output of removeLayer is a new network. You decide when and where to use this new network.
I believe you will need to retrain your network if you modify it.
Use analyzeNetwork to view the layers of your network.

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2023b

Community Treasure Hunt

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

Start Hunting!

Translated by