Neural network training - 2 input parameter to 1 output result training
조회 수: 1 (최근 30일)
이전 댓글 표시
Ridza Effendi Abd Razak
2020년 9월 3일
댓글: Ridza Effendi Abd Razak
2020년 9월 29일
im stuck at training net with 2 parameter.
right now im trying to clasify test data. by using example "Classify Text Data Using Deep Learning".
for that example if i want to have "description" and "category" as training input and "resolution" as target output.
which part of code in the example that i have to change.
i need help
댓글 수: 0
채택된 답변
Madhav Thakker
2020년 9월 8일
편집: Madhav Thakker
2020년 9월 8일
Hi Ridza,
I understand that you want to train the LSTM network using description and category values instead of just description. As the preprocessText function, tokenization of input data is taking place. One simple way of training the network on both these values is to just prepend category data and continue with the procedure in the same way.
Note that you will have to change the target length of your training data by visualizing the histogram of the document length.
sequenceLength = %new Sequence Length;
XTrain = doc2sequence(enc,documentsTrain,'Length',sequenceLength);
Attaching code snippet for better explanation.
documentsTrain = preprocessText(dataTrain.Description + " " + dataTrain.Category);
documentsValidation = preprocessText(dataValidation.Description + " " + dataValidation.Category);
YTrain = categorical(dataTrain.Resolution);
YValidation = categorical(dataValidation.Resolution);
Refer this example for details -
Hope this helps.
추가 답변 (0개)
참고 항목
카테고리
Help Center 및 File Exchange에서 Deep Learning Toolbox에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!