Hi,
i would like to know is there any ways to generate back the training progress plot or verbose result from the saved trained model if i forgot screenshot/save both data manually?
the code that i use to save the trained model is as below.
testnet = trainNetwork(augimdsTrain,lgraph,options);
save testnet
training progress plot
bernose result

 採用された回答

KSSV
KSSV 2021 年 7 月 26 日

0 投票

[testnet,traininfo] = trainNetwork(augimdsTrain,lgraph,options);
save('data.mat','testnet','traininfo')
traininfo has the details you want, you can plot them later if you save it.

6 件のコメント

Teo
Teo 2021 年 7 月 27 日
thanks @KSSV, may i know why the traininfo data for validation loss and validation accuracy are NaN at the middle?
KSSV
KSSV 2021 年 7 月 27 日
Try changing the learning rate.......check the inputs......
Teo
Teo 2021 年 7 月 27 日
noted @KSSV. Sorry to bother you, i got another question? is it possible to tabulate the same table as verbose table from traininfo instead of copy paste it manually?
KSSV
KSSV 2021 年 7 月 27 日
You can convert the structre traininfo_ into a table using stuct2table.
Teo
Teo 2021 年 7 月 29 日
Thanks @KSSV
Teo
Teo 2021 年 12 月 10 日
Hi @KSSV,
sorry to distueb you again. i trying to regenerate verbose table as shown below from the traininfo that i saved earlier after finish running the model.
However, when i treid to tabulate the data from traininfo using struct2table i get the following table which is completely different from original verbose table that we got after finish training the model in matlab. And i notice the epoch column are also missing.
Appreciate if you could help on this. Thank You.

サインインしてコメントする。

その他の回答 (0 件)

カテゴリ

ヘルプ センター および File Exchange で Matrix Indexing についてさらに検索

製品

リリース

R2021a

タグ

質問済み:

Teo
2021 年 7 月 26 日

コメント済み:

Teo
2021 年 12 月 10 日

Community Treasure Hunt

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

Start Hunting!

Translated by